{ "n": 200, "datasets": { "drama_03": 100, "drama_04": 100 }, "source": [ "/primus_chat_aigc_sh_oss/users/liuyichen/video_example/drama_03/train_mtss_time_refine_test.json", "/primus_chat_aigc_sh_oss/users/liuyichen/video_example/drama_04/train_mtss_time_refine_test.json" ], "prompts": [ { "dataset": "drama_03", "clip_id": "clip_16051", "media_path": "drama_03/clip_16051.mp4", "source_media_path": "clips/clip_16051.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, red lipstick, and an elegant demeanor", "attributes": "clothing: Green traditional dress with red and gold accents, hairstyle: Elaborate updo with gold hairpins and dangling ornaments, accessories: Gold earrings, gold hairpieces" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with a simpler, neat appearance", "attributes": "clothing: Light blue and white traditional dress with small red and blue dot patterns, hairstyle: Neat updo with simple hairpins, accessories: Simple dangling earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Warm, hazy lighting with a mirror in the foreground" } ], "visual_description": "[PERSON_1] is looking at her reflection in a mirror, resting her chin on her hand with a slightly bored or contemplative expression. [PERSON_2] stands quietly in the background. The shot has a warm, soft-focus filter.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.5, 5.2 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A close-up focuses on [PERSON_1]'s neck, revealing a distinct red mark. Her fingers gently come up to touch the spot.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.2, 5.7 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "The camera cuts to [PERSON_2], who is looking towards [PERSON_1] with a neutral but attentive expression.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 1.0 ], "content": { "description": "A sharp, ringing metallic sound effect." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 4.4, 5.3 ], "content": { "speaker": "PERSON_1", "line": "里怎么有蚊子啊", "description": "Confused and slightly annoyed tone." } } ], "scene_description": "A noblewoman in a palace setting notices a red mark on her neck while looking in the mirror and mistakenly attributes it to a mosquito bite, while her attendant watches.", "global_style": "Historical drama aesthetic with warm, soft lighting and elaborate traditional costumes.", "global_audio": "Quiet ambient sound with a distinct sound effect at the beginning and clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_13481", "media_path": "drama_03/clip_13481.mp4", "source_media_path": "clips/clip_13481.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair", "attributes": "Wearing a grey button-up jacket over a black and white striped shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor area with a blurred background, possibly a sports court or campus" } ], "visual_description": "[PERSON_1] pats his chest with his hand, looking down as if searching for something missing from his jacket.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 3.9 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] looks up with a surprised and confused expression, speaking to someone off-camera.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.9, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair", "attributes": "Wearing a black jacket over a black shirt, carrying a black backpack" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A small, open notebook with lined pages" }, "SCENE_1" ], "visual_description": "[PERSON_2] is holding [OBJECT_1] open in his hands, looking down at it and reading aloud.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 2.0, 4.2 ], "content": { "speaker": "PERSON_1", "line": "这是我的记账本怎么到你那了", "description": "Surprised and questioning tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.2, 4.8 ], "content": { "speaker": "PERSON_2", "line": "三月五日", "description": "Reading aloud in a calm, neutral tone." } } ], "scene_description": "Two young men are outdoors. One realizes his notebook is missing, and the other is found holding and reading from it.", "global_style": "Bright, outdoor daytime lighting with a shallow depth of field focusing on the characters.", "global_audio": "Clear dialogue with faint outdoor ambient noise." } }, { "dataset": "drama_03", "clip_id": "clip_5805", "media_path": "drama_03/clip_5805.mp4", "source_media_path": "clips/clip_5805.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, wearing glasses", "attributes": "Blue button-down shirt, black cardigan" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with blurred bookshelves and decorative items in the background", "attributes": "Indoor, modern, well-lit" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long straight black hair", "attributes": "Grey blazer, black top with lace-up front, small hoop earrings" } ], "visual_description": "[PERSON_1] turns his head to look towards [PERSON_2].", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.3, 5.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] looks at [PERSON_1] and speaks to him.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Emotional background music with vocals." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.3, 2.8 ], "content": { "speaker": "PERSON_2", "line": "对了", "description": "Casual but serious tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.8, 4.2 ], "content": { "speaker": "PERSON_2", "line": "半个月后", "description": "Informative tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.2, 4.8 ], "content": { "speaker": "PERSON_2", "line": "别忘了去领", "description": "Firm and decisive tone." } } ], "scene_description": "A woman reminds a man about their upcoming divorce.", "global_style": "Modern drama, serious and slightly tense atmosphere.", "global_audio": "Emotional background music playing throughout the scene." } }, { "dataset": "drama_03", "clip_id": "clip_20506", "media_path": "drama_03/clip_20506.mp4", "source_media_path": "clips/clip_20506.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with short black hair", "attributes": "Black suit jacket, white shirt" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with long dark hair tied half up, fair skin", "attributes": "Beige sleeveless top, pearl necklace, pearl earrings, black skirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A plain grey wall serving as the backdrop" } ], "visual_description": "[PERSON_1] stands close to [PERSON_2], holding her against [SCENE_1] with his hand on her neck. [PERSON_2] looks uncomfortable and distressed.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.2, 4.4 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "A close-up view shows [PERSON_2] grabbing the wrist of [PERSON_1] with both hands, attempting to pull his hand away.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.4, 6.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] pushes [PERSON_1] away, creating distance between them. She stares at him with a shocked and defensive expression.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Slight pan" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 0.9 ], "content": { "speaker": "PERSON_1", "line": "要了", "description": "Assertive and domineering tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 6.0 ], "content": { "description": "Dramatic pop song playing in the background." } } ], "scene_description": "A tense confrontation between a man and a woman, where the woman physically resists the man's aggressive advance.", "global_style": "Dramatic, modern, slightly dark lighting.", "global_audio": "Dramatic background music." } }, { "dataset": "drama_03", "clip_id": "clip_15762", "media_path": "drama_03/clip_15762.mp4", "source_media_path": "clips/clip_15762.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short dark hair, wearing a brown patterned jacket over a white shirt, and a watch on his left wrist", "attributes": "short dark hair, brown patterned jacket, white shirt, wristwatch" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A brightly lit room with a plain, light-colored background" } ], "visual_description": "[PERSON_1] looks forward and reaches his left hand out while speaking.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.3, 3.7 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long dark hair, wearing a beige coat", "attributes": "long dark hair, beige coat" }, "SCENE_1" ], "visual_description": "A close-up of [PERSON_2]'s face as [PERSON_1]'s hand gently touches her hair.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.7, 4.3 ], "references": [ "PERSON_1", "SCENE_1", "PERSON_2" ], "visual_description": "[PERSON_1] continues to look at [PERSON_2] and speaks, with his hand still raised.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.3, 5.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2]'s hand comes up and pushes [PERSON_1]'s hand away.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 1.8 ], "content": { "speaker": "PERSON_1", "line": "和莫南星比", "description": "Confident statement" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.8, 3.3 ], "content": { "speaker": "PERSON_1", "line": "你更喜欢我", "description": "Assertive and slightly arrogant tone" } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Soft, dramatic background music" } } ], "scene_description": "A man confidently tells a woman that she prefers him over someone else while touching her hair, but she rejects his advance by pushing his hand away.", "global_style": "Bright, soft lighting typical of a modern romantic drama.", "global_audio": "Dialogue accompanied by soft, dramatic background music." } }, { "dataset": "drama_03", "clip_id": "clip_18792", "media_path": "drama_03/clip_18792.mp4", "source_media_path": "clips/clip_18792.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with her hair tied up, wearing makeup, large hoop earrings, and a delicate necklace", "attributes": "clothing: Gold off-the-shoulder ruffled dress with a sequined bodice, hairstyle: Updo with some loose strands, accessories: Gold hoop earrings, thin gold necklace, gold bracelet" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A background with a light-colored floral or damask pattern" } ], "visual_description": "[PERSON_1] stands in front of [SCENE_1] with her arms crossed, looking directly at the camera and speaking.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 3.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long dark wavy hair, wearing makeup and a necklace", "attributes": "clothing: White ruffled V-neck shirt, blue denim jeans, hairstyle: Long dark wavy hair, accessories: Thin gold necklace, small stud earrings" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A plain dark grey or black background, possibly in a studio setting" } ], "visual_description": "[PERSON_2] stands in front of [SCENE_2], looking slightly off-camera to her left and speaking.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.2, 4.7 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man with short dark hair, clean-shaven", "attributes": "clothing: White button-down shirt with the top buttons undone, hairstyle: Short dark hair, styled slightly upwards, accessories: None" }, "SCENE_2", "PERSON_2" ], "visual_description": "[PERSON_3] stands in front of [SCENE_2], looking off-camera to his right with a serious expression while [PERSON_2] continues speaking off-screen.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 1.3 ], "content": { "speaker": "PERSON_1", "line": "我都是", "description": "Confident statement" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.3, 3.2 ], "content": { "speaker": "PERSON_2", "line": "我又是简行的经纪人", "description": "Explaining her role" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.2, 4.1 ], "content": { "speaker": "PERSON_2", "line": "我也是他的生活助理", "description": "Continuing to explain her role" } } ], "scene_description": "A sequence of three individuals, with two women stating their roles or identities, and a man listening.", "global_style": "Clean, well-lit portrait shots with a dramatic aesthetic.", "global_audio": "Clear spoken dialogue with no background music." } }, { "dataset": "drama_03", "clip_id": "clip_19741", "media_path": "drama_03/clip_19741.mp4", "source_media_path": "clips/clip_19741.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair and a square face", "attributes": "Wearing a long-sleeved, dark blue button-up shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious outdoor area surrounded by old, multi-story brick buildings with multiple windows and doors", "attributes": "Daylight, concrete or paved ground" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], looking slightly off-camera with a serious expression. He holds his right hand up slightly.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 5.2, 6.7 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts to a profile view of [PERSON_1] in [SCENE_1]. He is looking to his left, speaking intensely.", "camera": { "shot_type": "Medium close-up", "angle": "Profile", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 3.8 ], "content": { "speaker": "NARRATOR_1", "line": "其中国字脸男人开口声音严肃", "description": "Serious and descriptive narration." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.8, 6.3 ], "content": { "speaker": "PERSON_1", "line": "我们是军区保卫科的现在接到举报", "description": "Stern, authoritative, and accusatory tone." } } ], "scene_description": "A dramatic scene where a man, identified as a security officer, confronts someone off-camera with a serious accusation of illegal foreign involvement, accompanied by a voiceover narration setting the scene.", "global_style": "Realistic, dramatic, period-piece aesthetic.", "global_audio": "Clear dialogue and voiceover with no prominent background music or sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_22411", "media_path": "drama_03/clip_22411.mp4", "source_media_path": "clips/clip_22411.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short, styled black hair, fair skin, and a serious expression", "attributes": "black suit jacket, black dress shirt, black tie, wristwatch with a dark dial" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring a dark grey curtain on the left and warm, decorative lighting in the background" } ], "visual_description": "[PERSON_1] stands with his back to the camera in [SCENE_1], facing a grey curtain. He adjusts the front of his jacket with his right hand and begins to turn around to his left.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.2, 5.0 ], "references": [ "PERSON_1", "SCENE_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A dark-colored smartphone" } ], "visual_description": "The camera cuts to a closer view of [PERSON_1] as he finishes turning around to face forward. He looks slightly off-camera with a serious expression, then looks down and brings up [OBJECT_1] to look at the screen.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 2.0 ], "content": { "speaker": "PERSON_2", "line": "大少爷，少奶奶在试衣间里等您呢", "description": "Respectful and informative tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 4.0, 5.0 ], "content": { "description": "Electronic beeping sounds of a phone dialing." } } ], "scene_description": "A man in a formal suit is informed by an unseen person that someone is waiting for him in a fitting room. He turns around and checks his phone.", "global_style": "Elegant and dramatic with warm, soft lighting.", "global_audio": "Quiet ambient background with clear dialogue and distinct sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_16071", "media_path": "drama_03/clip_16071.mp4", "source_media_path": "clips/clip_16071.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with fair skin and dark hair styled up", "attributes": "Wearing a green embroidered dress with gold hair ornaments and earrings" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman with dark hair pulled back", "attributes": "Wearing a light blue and green outfit with a red sash" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with blurred background, showing warm glowing lights from candles or lamps" } ], "visual_description": "[PERSON_1] is sitting in [SCENE_1], eating sunflower seeds from a small bowl and speaking. [PERSON_3] stands quietly in the background behind her.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.8, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with fair skin and dark hair styled in a large updo", "attributes": "Wearing a light blue dress with a large, elaborate gold headpiece and dangling earrings" }, "SCENE_1", "PERSON_1" ], "visual_description": "The camera cuts to [PERSON_2] in [SCENE_1]. She is listening to [PERSON_1] speak off-screen. She looks slightly downcast, then her eyes move slightly as she processes the words.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 2.2 ], "content": { "speaker": "PERSON_1", "line": "幸好太子殿下厌恶她", "description": "Speaking casually while eating." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.4, 3.6 ], "content": { "speaker": "PERSON_1", "line": "没母家", "description": "Continuing her thought." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.6, 4.3 ], "content": { "speaker": "PERSON_1", "line": "翻不起风浪", "description": "Concluding her statement with a dismissive tone." } } ], "scene_description": "Two women in historical attire are in a room. One woman casually gossips about someone being disliked by the Crown Prince and lacking family backing, while the other woman listens quietly.", "global_style": "Historical Chinese drama aesthetic with elaborate costumes, warm lighting, and soft focus.", "global_audio": "Clear dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_22241", "media_path": "drama_03/clip_22241.mp4", "source_media_path": "clips/clip_22241.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark hair", "attributes": "Wearing a black turtleneck and a long black coat" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long dark hair", "attributes": "Wearing a light beige coat, a light-colored dress, and beige boots" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A modern interior space near a doorway" } ], "visual_description": "[PERSON_1] stands at the doorway looking at [PERSON_2], who is standing just outside.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 1.3, 2.2 ], "references": [ "PERSON_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A dark-colored door handle with an electronic lock mechanism" } ], "visual_description": "A close-up shows [PERSON_1]'s hand pulling down the handle of [OBJECT_1].", "camera": { "shot_type": "Close-up", "angle": "High angle", "movement": "Static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.2, 4.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_1] pulls [PERSON_2] inside by the hand. The door closes behind them, and they stand facing each other in [SCENE_1].", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "SFX_2" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.0, 2.0 ], "content": { "description": "Sound of a door handle being pulled and the door closing." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 2.0, 3.0 ], "content": { "description": "Electronic beep sound from a door lock." } } ], "scene_description": "A man pulls a woman inside an apartment and closes the door behind them.", "global_style": "Modern, slightly dramatic lighting.", "global_audio": "Quiet ambient noise with distinct door and lock sounds." } }, { "dataset": "drama_03", "clip_id": "clip_20172", "media_path": "drama_03/clip_20172.mp4", "source_media_path": "clips/clip_20172.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, wearing a white lab coat over a black shirt, with an ID badge on a blue lanyard", "attributes": "white lab coat, black shirt, ID badge, blue lanyard, short black hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A brightly lit room with white walls and a blurred plant in the background" } ], "visual_description": "[PERSON_1] is holding a black landline phone receiver to his ear, looking down with an urgent expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.1, 3.0 ], "references": [ "PERSON_1" ], "visual_description": "An extreme close-up of [PERSON_1]'s mouth as he speaks into the phone receiver.", "camera": { "shot_type": "extreme close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.0, 4.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with short black hair, sweating profusely on her forehead, wearing a light-colored ribbed top", "attributes": "short black hair, sweating, light-colored ribbed top" } ], "visual_description": "A close-up shot of a pregnant belly covered in light-colored ribbed fabric.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.0, 5.7 ], "references": [ "PERSON_2" ], "visual_description": "A close-up of [PERSON_2]'s face. She is sweating profusely, looking down, and appears to be in pain or panting.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.1, 2.1 ], "content": { "speaker": "PERSON_1", "line": "护士", "description": "Urgent tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.1, 2.6 ], "content": { "speaker": "PERSON_1", "line": "准备手术室", "description": "Commanding, urgent tone" } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.2, 3.2 ], "content": { "description": "Dramatic swoosh sound effect" } } ], "scene_description": "A doctor urgently calls for an operating room to be prepared for a pregnant woman who is in labor and experiencing pain.", "global_style": "Dramatic medical drama style with close-up shots emphasizing urgency and tension.", "global_audio": "Tense background atmosphere with dramatic sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_7310", "media_path": "drama_03/clip_7310.mp4", "source_media_path": "clips/clip_7310.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long wavy brown hair, wearing a white zip-up top under a white blazer, and pearl earrings", "attributes": "long wavy brown hair, white zip-up top, white blazer, pearl earrings" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A person seen from the back wearing a white medical coat", "attributes": "white medical coat, short black hair" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A person with short black hair seen from the back in the foreground", "attributes": "short black hair, dark clothing" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with white curtains in the background and bright lighting", "attributes": "white curtains, bright lighting" } ], "visual_description": "[PERSON_1] stands facing [PERSON_2], listening attentively. [PERSON_3] is visible in the foreground. [PERSON_1] nods and speaks to [PERSON_2] with a relieved expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 1.3 ], "content": { "speaker": "PERSON_2", "line": "就会恢复", "description": "Reassuring tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.5, 2.1 ], "content": { "speaker": "PERSON_1", "line": "好谢谢医生", "description": "Grateful and relieved tone" } } ], "scene_description": "A woman receives reassuring medical news from a doctor regarding a patient's recovery.", "global_style": "Bright, clean, clinical aesthetic with soft lighting.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_12196", "media_path": "drama_03/clip_12196.mp4", "source_media_path": "clips/clip_12196.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Young woman with long reddish-brown hair, fair skin, and light makeup", "attributes": "Grey textured wrap coat with a belt, dark inner top, silver necklace, earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Interior room with wooden furniture, a couch, and warm lighting" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], looking slightly surprised and attentive.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.9, 4.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Woman with dark hair tied back, fair skin", "attributes": "Blue double-breasted coat, sitting with hands clasped" }, "SCENE_1" ], "visual_description": "[PERSON_2] sits on a couch in [SCENE_1] with her hands clasped, speaking sternly to someone off-camera.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.1, 0.9 ], "content": { "speaker": "PERSON_1", "line": "啊", "description": "Surprised utterance" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 0.9, 2.2 ], "content": { "speaker": "PERSON_2", "line": "这位先生", "description": "Stern address" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.2, 3.6 ], "content": { "speaker": "PERSON_2", "line": "你的戏演完了没有", "description": "Sarcastic question" } } ], "scene_description": "A tense confrontation in a living room where an older woman sternly dismisses someone off-camera while a younger woman watches in surprise.", "global_style": "Dramatic, well-lit interior, soap opera or drama style.", "global_audio": "Dialogue with no prominent background music." } }, { "dataset": "drama_03", "clip_id": "clip_28052", "media_path": "drama_03/clip_28052.mp4", "source_media_path": "clips/clip_28052.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "An elderly woman with deep wrinkles, grey hair pulled back, and a sorrowful expression", "attributes": "Wearing a dark blue traditional Chinese-style top with a mandarin collar and knot buttons. Hair is styled in a bun with a wooden hairpin" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor setting with blurred traditional Chinese architecture in the background, featuring wooden structures and warm lighting", "attributes": "Warm, golden hour lighting, slightly out of focus" } ], "visual_description": "A close-up shot of [PERSON_1] standing in [SCENE_1]. She has her eyes closed and a pained, sorrowful expression on her face. She slightly opens her eyes and looks downwards, appearing deeply moved or saddened.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.8, 5.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts to a medium shot of [PERSON_1] in [SCENE_1]. She looks forward and speaks, raising her right hand slightly in a conversational gesture.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 1.9 ], "content": { "speaker": "PERSON_2", "line": "随即叹了口气", "description": "Narrative voiceover describing an action." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.7, 4.1 ], "content": { "speaker": "PERSON_2", "line": "也是个可怜的", "description": "Narrative voiceover with a sympathetic tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.1, 4.7 ], "content": { "speaker": "PERSON_1", "line": "你躺走啊", "description": "Spoken with a lamenting, conversational tone." } } ], "scene_description": "An elderly woman in a traditional setting expresses sorrow and speaks about a relative, accompanied by a sympathetic voiceover narration.", "global_style": "Cinematic, realistic, with warm golden hour lighting and a shallow depth of field focusing on the character's emotional expressions.", "global_audio": "Quiet ambient background with clear, prominent dialogue and voiceover." } }, { "dataset": "drama_03", "clip_id": "clip_18931", "media_path": "drama_03/clip_18931.mp4", "source_media_path": "clips/clip_18931.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with short black hair, wearing a brown suit jacket over a white collared shirt", "attributes": "short black hair, brown suit jacket, white shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A modern indoor environment, possibly an office or living space, with soft lighting and a blurred background", "attributes": "indoor, blurred background, soft lighting" } ], "visual_description": "[PERSON_1] is shown in a close-up shot, looking slightly off-camera and speaking with a subtle smile in [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.8, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with long black hair and bangs, wearing a white turtleneck, a white coat, and large white flower earrings", "attributes": "long black hair, bangs, white turtleneck, white coat, large white flower earrings" }, "SCENE_1" ], "visual_description": "The camera cuts to a close-up of [PERSON_2] in [SCENE_1]. She looks thoughtful and responds briefly.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 2.3 ], "content": { "speaker": "PERSON_1", "line": "他才会相信吧", "description": "Speaking calmly with a slight smile, explaining a point." } } ], "scene_description": "A brief conversation between a man and a woman in a modern indoor setting, where the man explains something and the woman thoughtfully acknowledges it.", "global_style": "Modern, cinematic lighting, shallow depth of field, realistic.", "global_audio": "Quiet indoor ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_846", "media_path": "drama_03/clip_846.mp4", "source_media_path": "clips/clip_846.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 7.4 ], "references": [ { "ref_id": "SCENE_1", "type": "scene", "id_features": "A wide stone-paved pathway lined with glowing lamps and scattered with dead bodies, leading to a large traditional Chinese building adorned with glowing red lanterns" }, { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with long dark hair, appearing exhausted or injured", "attributes": "Wearing dark blue traditional Chinese robes with intricate patterns and a necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with an elaborate, tall hairstyle", "attributes": "Wearing vibrant red traditional Chinese robes with gold accents" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A long, straight sword lying flat on the stone ground" } ], "visual_description": "The camera starts with a wide, high-angle view of [SCENE_1], showing [PERSON_1] kneeling in the center of the pathway with [OBJECT_1] resting on the ground in front of him. [PERSON_2] stands a short distance behind him. The camera slowly pushes in, transitioning to a closer view of the two figures amidst the fallen bodies.", "camera": { "shot_type": "wide shot to medium shot", "angle": "high angle to eye level", "movement": "zoom in" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 7.4, 7.8 ], "references": [ "PERSON_1", { "ref_id": "PERSON_3", "type": "person", "id_features": "An older man with a stern expression", "attributes": "Wearing traditional Chinese military armor and a helmet" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A man with a serious expression", "attributes": "Wearing traditional Chinese military armor and a helmet" } ], "visual_description": "A medium shot focuses on [PERSON_1] as [PERSON_3] and [PERSON_4] step into the frame from the left and right sides, forcefully grabbing his shoulders. [PERSON_1] looks up with a tense expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.8, 6.9 ], "content": { "speaker": "PERSON_2", "line": "今日就是你的死期", "description": "Pronouncing a death sentence firmly and dramatically." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 6.0, 8.0 ], "content": { "description": "The heavy clanking sound of armor and physical movement as soldiers grab the man." } } ], "scene_description": "A dramatic confrontation in a courtyard filled with fallen soldiers, where a defeated warrior is captured and sentenced to death by a woman in red.", "global_style": "Dark, cinematic, traditional Chinese fantasy aesthetic with dramatic lighting from red lanterns and a moody, tense atmosphere.", "global_audio": "A tense, dramatic ambient soundscape that underscores the gravity of the execution sentence." } }, { "dataset": "drama_03", "clip_id": "clip_3794", "media_path": "drama_03/clip_3794.mp4", "source_media_path": "clips/clip_3794.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with short dark hair, blood smeared on the right side of his face and nose", "attributes": "Wearing a black suit jacket over a black shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit room with concrete floors and indistinct background elements, possibly an abandoned warehouse" } ], "visual_description": "[PERSON_1] is shown in profile, looking off-camera with a tense expression. Blood is visible on his face. The background [SCENE_1] is dark and out of focus.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 2.2, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with long, wavy dark hair and bright red lipstick", "attributes": "Wearing a black jacket with a small white logo on the left chest, and black gloves" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A long, thin metal blade, resembling a katana or straight sword" }, "SCENE_1" ], "visual_description": "[PERSON_2] is kneeling on the ground in [SCENE_1]. She draws [OBJECT_1] with both hands, looking up sharply towards the camera with a concerned and urgent expression.", "camera": { "shot_type": "medium shot", "angle": "slightly high angle", "movement": "static" }, "active_events": [ "SFX_1", "DIALOGUE_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.5, 3.0 ], "content": { "description": "The metallic sound of a sword being drawn from a scabbard." } } ], "scene_description": "A tense confrontation in a dark setting where a wounded man is observed by an armed woman who calls out to him.", "global_style": "Dark, gritty, cinematic lighting with cool tones.", "global_audio": "Quiet ambient background noise punctuated by the sharp sound of a sword and a single line of dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_7994", "media_path": "drama_03/clip_7994.mp4", "source_media_path": "clips/clip_7994.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with black hair tied back, wearing a white top with gold buttons and blue jeans", "attributes": "black hair, tied back hair, white top, gold buttons, blue jeans" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A piece of lined paper with handwritten Chinese text in black ink", "attributes": "lined paper, handwritten text, black ink" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with a teal window frame and some plants and flowers in the background", "attributes": "teal window frame, plants, flowers, indoor" } ], "visual_description": "[PERSON_1] is standing in [SCENE_1], holding and reading [OBJECT_1] with a serious and slightly sad expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.8, 5.0 ], "references": [ "PERSON_1", "OBJECT_1" ], "visual_description": "A close-up view of [OBJECT_1] held by the hands of [PERSON_1]. The letter contains handwritten text.", "camera": { "shot_type": "close-up", "angle": "over-the-shoulder", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Soft, melancholic piano music playing in the background." } } ], "scene_description": "A young woman reads a handwritten letter from the past, looking emotional.", "global_style": "Soft lighting, nostalgic and emotional tone.", "global_audio": "Melancholic piano background music." } }, { "dataset": "drama_03", "clip_id": "clip_22204", "media_path": "drama_03/clip_22204.mp4", "source_media_path": "clips/clip_22204.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with a fair complexion and soft makeup", "attributes": "Long dark wavy hair, white V-neck top, delicate silver necklace, butterfly-shaped earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit, blurred background with neutral tones" } ], "visual_description": "[PERSON_1] is shown in a close-up shot, looking slightly off-camera to her left. She is speaking softly. The background [SCENE_1] is out of focus.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 0.1, 1.1 ], "content": { "speaker": "PERSON_1", "line": "宋", "description": "Saying a name with a gentle tone." } } ], "scene_description": "A young woman is speaking softly, looking slightly off-camera and mentioning a name.", "global_style": "Soft lighting, close-up portrait style with a shallow depth of field.", "global_audio": "Quiet dialogue with no noticeable background noise." } }, { "dataset": "drama_03", "clip_id": "clip_12936", "media_path": "drama_03/clip_12936.mp4", "source_media_path": "clips/clip_12936.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with fair skin and dark hair styled in an elaborate updo", "attributes": "Wearing a yellow patterned robe, a pearl necklace, gold earrings, and intricate gold and jewel hair ornaments" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A grand room with wooden screens, lit candles, and low tables set with food and drinks" } ], "visual_description": "[PERSON_1] speaks with a serious expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.8, 3.9 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with facial hair, including a mustache and goatee", "attributes": "Wearing a gold crown and a yellow robe with intricate embroidery" }, "SCENE_1" ], "visual_description": "[PERSON_2] sits at a table and speaks briefly.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.9, 5.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "Viewed from behind [PERSON_2], [PERSON_1] walks towards the center of the room. Other attendants are visible in the background.", "camera": { "shot_type": "wide shot", "angle": "high angle", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 2.4 ], "content": { "speaker": "PERSON_1", "line": "皇上妾上有要事禀", "description": "Serious and formal tone." } } ], "scene_description": "A formal gathering in a palace where a consort approaches the emperor to report an important matter.", "global_style": "Historical Chinese drama with rich colors, ornate costumes, and elaborate set design.", "global_audio": "Clear dialogue with ambient room noise." } }, { "dataset": "drama_03", "clip_id": "clip_28967", "media_path": "drama_03/clip_28967.mp4", "source_media_path": "clips/clip_28967.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long black hair", "attributes": "Wearing a light grey suit jacket over a white blouse, and a silver watch on her left wrist" } ], "visual_description": "[PERSON_1] looks down at her watch on her left wrist while speaking.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.7, 4.3 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "An older woman with short black hair", "attributes": "Wearing a dark grey suit jacket over a white shirt" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A smartphone with a large screen displaying a text message" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An office with a desk, chair, and neutral-colored walls" } ], "visual_description": "[PERSON_2] is seated at a desk in [SCENE_1], holding [OBJECT_1] and looking at the screen.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.3, 4.7 ], "references": [ "PERSON_2", "OBJECT_1" ], "visual_description": "A close-up view of [OBJECT_1] held by [PERSON_2], displaying a text message on the screen.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.1, 4.1 ], "content": { "speaker": "PERSON_1", "line": "宏昌实业的第一期预付款应该已经到公司账上了", "description": "Informative and professional tone." } } ], "scene_description": "An assistant informs her boss that an advance payment should have arrived, which is confirmed by a text message on the boss's phone.", "global_style": "Professional, modern corporate drama style.", "global_audio": "Quiet office ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_28522", "media_path": "drama_03/clip_28522.mp4", "source_media_path": "clips/clip_28522.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young girl with large brown eyes, a small nose, and a gentle smile", "attributes": "Black hair with straight bangs, wearing a beaded necklace and a light-colored garment with orange patterns" } ], "visual_description": "A close-up shot of [PERSON_1] smiling gently and looking directly at the camera.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.8, 1.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A male character with sharp brown eyes, a scar under his right eye, and a '#' symbol on his forehead. Later appears as a large, imposing shadow with a jagged, crown-like headpiece", "attributes": "Black hair, stern expression" } ], "visual_description": "A close-up shot of [PERSON_2] with a stern expression. The camera rapidly zooms into his right eye, transitioning through the pupil into the next scene.", "camera": { "shot_type": "close-up to extreme close-up", "angle": "eye-level", "movement": "zoom in" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 1.8, 6.0 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring a wooden desk with papers, an inkstone, and a brush. A large shadow is cast on the wall behind the desk", "attributes": "Dim lighting, mysterious atmosphere" } ], "visual_description": "A wider shot in [SCENE_1] showing [PERSON_1] sitting at a desk, looking up at a large, imposing shadow of [PERSON_2] cast on the wall in front of her.", "camera": { "shot_type": "medium shot", "angle": "side view", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.0, 3.0 ], "content": { "description": "A dramatic whoosh and zooming sound effect." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.3, 5.2 ], "content": { "speaker": "PERSON_2", "line": "胆子都是不小", "description": "Deep, resonant, and slightly intimidating tone." } } ], "scene_description": "A young girl innocently asks a stern, imposing figure if he is her father, leading to a dramatic visual transition where she faces his large shadow in a dimly lit room.", "global_style": "3D animation with a mix of cute and dark, mysterious aesthetics.", "global_audio": "Quiet ambient background with prominent dialogue and dramatic transition sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_9507", "media_path": "drama_03/clip_9507.mp4", "source_media_path": "clips/clip_9507.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, fair skin, and a sharp jawline", "attributes": "Wearing a beige v-neck sweater and a silver metal collar with black details" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with dark brown hair tied back, fair skin, and soft makeup", "attributes": "Wearing a white top under a light blue fluffy cardigan" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A thick, silver metal collar with a black rectangular section containing two silver studs" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit room with a bed featuring white sheets and light blue curtains in the background" } ], "visual_description": "Close-up of [PERSON_1]'s neck wearing [OBJECT_1]. [PERSON_2]'s hand gently touches [OBJECT_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 2.3 ], "references": [ "PERSON_1", "OBJECT_1", "SCENE_1" ], "visual_description": "Medium shot of [PERSON_1] lying on a bed, touching [OBJECT_1] on his neck with his right hand, looking uncomfortable.", "camera": { "shot_type": "medium shot", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.3, 3.9 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "Close-up of [PERSON_2] looking down at [PERSON_1] with a calm, slightly serious expression.", "camera": { "shot_type": "close-up", "angle": "low angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 3.9, 5.0 ], "references": [ "PERSON_1", "OBJECT_1", "SCENE_1", "PERSON_2" ], "visual_description": "Medium shot of [PERSON_1] looking up at [PERSON_2], his hand still resting on [OBJECT_1].", "camera": { "shot_type": "medium shot", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.1, 1.1 ], "content": { "speaker": "PERSON_2", "line": "怎么样", "description": "Soft, inquiring tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Soft, dramatic background music." } } ], "scene_description": "A woman asks a man how a metal collar feels on his neck, and he replies that it is a bit tight.", "global_style": "Soft, dramatic lighting with a slightly tense and intimate atmosphere.", "global_audio": "Dialogue accompanied by soft, dramatic background music." } }, { "dataset": "drama_03", "clip_id": "clip_10391", "media_path": "drama_03/clip_10391.mp4", "source_media_path": "clips/clip_10391.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with dark hair tied back in an updo, wearing a beige cardigan over a grey v-neck top, a gold necklace with a dark pendant, and pearl earrings", "attributes": "beige cardigan, grey v-neck top, gold necklace, pearl earrings, dark hair in updo" } ], "visual_description": "[PERSON_1] is shown in a close-up, looking angry and emotional as she speaks.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.5, 4.7 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "An older man with short dark hair, wearing a grey suit, white shirt, and dark tie", "attributes": "grey suit, white shirt, dark tie" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A conference room with wood-paneled walls, a large wooden table, beige leather chairs, and a painting on the wall", "attributes": "wood-paneled walls, large wooden table, beige leather chairs, painting" } ], "visual_description": "The camera cuts to a wide shot showing [PERSON_1] and [PERSON_2] standing facing each other in [SCENE_1]. [PERSON_1] continues to speak.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.9, 4.2 ], "content": { "speaker": "PERSON_1", "line": "你没资格跟我提我妈当年", "description": "Angry and resentful tone." } } ], "scene_description": "A tense confrontation between a young woman and an older man in a conference room.", "global_style": "Dramatic, well-lit, professional setting.", "global_audio": "Clear dialogue with a tense atmosphere." } }, { "dataset": "drama_03", "clip_id": "clip_2169", "media_path": "drama_03/clip_2169.mp4", "source_media_path": "clips/clip_2169.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Asian man with short black hair and glasses", "attributes": "Light blue dress shirt" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Asian man with wavy, medium-length brown hair", "attributes": "White dress shirt, grey vest, black tie" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with light-colored curtains and a wooden desk" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "Old-looking papers, documents, and maps spread on a desk" } ], "visual_description": "[PERSON_1] and [PERSON_2] are standing at a desk in [SCENE_1], looking at [OBJECT_1]. [PERSON_1] points at a document. They then look up, smile, and shake hands.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.4, 4.7 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "Older Asian man with short grey hair and wrinkles", "attributes": "Black suit jacket, white dress shirt, black tie" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "An office with a blurred presentation board in the background" } ], "visual_description": "[PERSON_3] stands in [SCENE_2], looking directly forward with a serious expression.", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 1.8 ], "content": { "speaker": "PERSON_NARRATOR", "line": "在一周后圆满结束", "description": "Narrating a successful outcome." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.8, 4.1 ], "content": { "speaker": "PERSON_NARRATOR", "line": "他们不仅没有查出局里的任何重大问题", "description": "Narrating the results of an investigation." } } ], "scene_description": "A sequence showing two men successfully concluding their work by shaking hands, followed by an older man looking serious, accompanied by a narration about an investigation finding no issues.", "global_style": "Professional, dramatic, corporate.", "global_audio": "Voiceover narration." } }, { "dataset": "drama_03", "clip_id": "clip_24584", "media_path": "drama_03/clip_24584.mp4", "source_media_path": "clips/clip_24584.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with a fair complexion, his hair tied up in a topknot", "attributes": "Wearing a black and gold patterned outer robe over a bright red inner garment, with an ornate gold hairpiece" } ], "visual_description": "[PERSON_1] is seen from the chest up, smiling subtly and looking slightly off-camera to his right.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.1, 3.7 ], "references": [ { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious room with polished wooden floors, blue curtains draped on the sides, and warm lighting from numerous candles or small lanterns in the background" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin and elaborate traditional makeup", "attributes": "Wearing a light pink flowing dress, with her hair styled intricately, featuring braids and adorned with floral and jeweled hairpins" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A reddish-brown, traditional-style teapot" } ], "visual_description": "A wide view of [SCENE_1] shows [PERSON_2] seated alone at a wooden table in the center of the room. In the blurred foreground, [OBJECT_1] and a matching cup rest on a wooden surface.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.7, 5.0 ], "references": [ "PERSON_2", { "ref_id": "OBJECT_2", "type": "object", "id_features": "A small, ornate teacup with gold detailing" }, { "ref_id": "OBJECT_3", "type": "object", "id_features": "A plate filled with dark purple grapes" } ], "visual_description": "The camera cuts to a closer view of [PERSON_2]. She is holding [OBJECT_2] near her mouth, about to take a sip. [OBJECT_3] is visible on the table in front of her. She pauses her movement and looks up, reacting to a sound.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1", "SFX_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Gentle, traditional-sounding instrumental background music." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 4.0, 5.0 ], "content": { "description": "A distinct sound of a man clearing his throat." } } ], "scene_description": "A man smiles knowingly, followed by a scene of a woman in a traditional room who is interrupted from drinking tea by the sound of someone clearing their throat.", "global_style": "Historical Chinese drama aesthetic with rich, warm colors, elaborate costumes, and traditional set design.", "global_audio": "Traditional instrumental background music accompanied by a prominent throat-clearing sound effect near the end." } }, { "dataset": "drama_03", "clip_id": "clip_14553", "media_path": "drama_03/clip_14553.mp4", "source_media_path": "clips/clip_14553.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.8 ], "references": [ { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious outdoor courtyard surrounded by a two-story traditional building with white walls and dark wooden beams. The area features a small roofed entrance, a yellow parasol, and several books scattered across the stone floor" }, { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with long dark hair, standing in the courtyard", "attributes": "Dark red and black flowing robes" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with dark hair tied in a high ponytail, wearing a delicate silver forehead accessory", "attributes": "Green robe with a black quilted vest featuring silver embroidery" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man with dark hair styled with intricate silver hairpins and ornaments", "attributes": "Blue robe with silver patterns over a white inner layer" } ], "visual_description": "A high-angle wide shot of [SCENE_1]. [PERSON_1] stands on the left side of the courtyard, throwing his head back in laughter. [PERSON_2] and [PERSON_3] stand in the center, observing him, while other figures are positioned near the building's entrance. Books are scattered on the ground between them.", "camera": { "shot_type": "wide shot", "angle": "high angle", "movement": "static" }, "active_events": [ "EVENT_1", "EVENT_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.8, 2.6 ], "references": [ "PERSON_2" ], "visual_description": "A close-up of [PERSON_2]. She looks off-camera to the left with a serious, slightly concerned expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "EVENT_1", "EVENT_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.6, 5.0 ], "references": [ "PERSON_3" ], "visual_description": "A close-up of [PERSON_3]. He looks off-camera to the left, holding a dark cylindrical object in his hand, maintaining a stoic and focused expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "EVENT_2" ] } ], "events": [ { "event_id": "EVENT_1", "type": "dialogue", "time_range": [ 0.1, 1.5 ], "content": { "speaker": "PERSON_1", "line": "哈哈哈哈哈哈", "description": "Loud, villainous laughter." } }, { "event_id": "EVENT_2", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Tense, dramatic instrumental background music." } } ], "scene_description": "A tense confrontation in a traditional courtyard where a man laughs menacingly while others observe him cautiously.", "global_style": "Historical Chinese fantasy drama (Xianxia/Wuxia) with elaborate costumes and traditional architecture.", "global_audio": "Dramatic instrumental music accompanied by loud, echoing laughter." } }, { "dataset": "drama_03", "clip_id": "clip_24353", "media_path": "drama_03/clip_24353.mp4", "source_media_path": "clips/clip_24353.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with long wavy brown hair, seen from behind", "attributes": "teal coat, long wavy brown hair" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A man standing in the background wearing an apron", "attributes": "black apron, white shirt" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman standing in the background", "attributes": "striped long-sleeve shirt, short hair" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "A man standing in the background", "attributes": "grey jacket" }, { "ref_id": "PERSON_6", "type": "person", "id_features": "A man standing in the background", "attributes": "grey button-up shirt" }, { "ref_id": "PERSON_7", "type": "person", "id_features": "A man sitting on a chair in the background", "attributes": "dark shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with bare concrete walls, a green ceiling fan, a desk with folders, and banners hanging on the walls" } ], "visual_description": "[PERSON_1] stands with her back to the camera, facing a group of people including [PERSON_3], [PERSON_4], [PERSON_5], [PERSON_6], and [PERSON_7] inside [SCENE_1].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.4, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short black hair, wearing casual clothing", "attributes": "plaid shirt, olive green t-shirt, blue jeans, short black hair" }, "SCENE_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A black duffel bag with handles" } ], "visual_description": "[PERSON_2] opens a door with a plaid curtain and enters [SCENE_1], carrying [OBJECT_1]. He walks forward towards the camera and speaks.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1", "SFX_1", "DIALOGUE_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Dramatic, tense background music." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.8, 2.5 ], "content": { "description": "Sound of a door opening." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 3.8, 4.8 ], "content": { "speaker": "PERSON_2", "line": "水象不是金鸾殿", "description": "Serious and assertive tone." } } ], "scene_description": "A woman confronts a group of people in a rundown room before a man enters through a door, carrying a bag, and makes a serious statement.", "global_style": "Gritty, dramatic, and slightly desaturated visual style.", "global_audio": "Tense background music with clear dialogue and foley sounds." } }, { "dataset": "drama_03", "clip_id": "clip_6326", "media_path": "drama_03/clip_6326.mp4", "source_media_path": "clips/clip_6326.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with dark hair tied back, wearing a white long-sleeved shirt under a dark brown vest, and a silver leaf pendant necklace", "attributes": "dark hair tied back, white shirt, dark brown vest, leaf pendant necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with warm lighting and a blurred background suggesting a dining area" } ], "visual_description": "[PERSON_1] is sitting at a table. She looks to her right, makes a scoffing expression, and then turns her gaze forward, looking thoughtful or slightly annoyed.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.3, 4.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with dark hair, wearing glasses, a dark suit jacket, a white shirt, and a striped tie", "attributes": "dark hair, glasses, dark suit, white shirt, striped tie" }, "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2] sitting across the table. He is looking down, listening or talking quietly, and then slightly raises his eyes. Another person's hand is briefly visible gesturing in the foreground.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.5, 2.6 ], "content": { "speaker": "PERSON_1", "line": "果然", "description": "Internal monologue, spoken with a tone of realization." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.9, 4.3 ], "content": { "speaker": "PERSON_1", "line": "对别人都是随会有亲", "description": "Internal monologue, spoken with a hint of observation or jealousy." } } ], "scene_description": "A woman observes a man in a restaurant setting, noting his friendly demeanor towards others through her internal monologue.", "global_style": "Soft, warm lighting with a shallow depth of field, typical of a modern drama.", "global_audio": "Quiet ambient restaurant noise with clear voiceover dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_21266", "media_path": "drama_03/clip_21266.mp4", "source_media_path": "clips/clip_21266.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with a fair complexion, wearing a gold crown", "attributes": "Black hair, gold crown, black and gold patterned robe" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden lattice windows and traditional decor" } ], "visual_description": "[PERSON_1] is sitting in [SCENE_1], speaking with a regretful expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.1, 4.1 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with a fair complexion and a red mark on her forehead, wearing elaborate hair accessories", "attributes": "Black hair, purple and silver hairpins, light purple dress, gold necklace" }, "SCENE_1" ], "visual_description": "[PERSON_2] is shown looking downwards with a sad expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.1, 7.7 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] continues speaking, looking forward with a melancholic expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.6, 2.4 ], "content": { "speaker": "PERSON_1", "line": "怪朕當時疏忽了", "description": "Regretful tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.4, 4.3 ], "content": { "speaker": "PERSON_1", "line": "如今他要隨駙馬回江南", "description": "Resigned tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.3, 4.5 ], "content": { "speaker": "PERSON_1", "line": "再", "description": "Melancholic tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 6.4, 7.2 ], "content": { "speaker": "PERSON_1", "line": "也不知是何時了", "description": "Melancholic tone" } } ], "scene_description": "An emperor expresses regret over a past negligence and melancholy about a woman leaving for Jiangnan with her husband, unsure of when they will meet again.", "global_style": "Historical Chinese drama aesthetic with rich costumes and traditional settings.", "global_audio": "Quiet dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_16695", "media_path": "drama_03/clip_16695.mp4", "source_media_path": "clips/clip_16695.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with dark hair tied in a side braid, fair skin, and light makeup", "attributes": "clothing: Light-colored, possibly white or pale pink, v-neck top., hairstyle: Dark hair, parted, with a side braid., accessories: Small stud earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit room with blurred lights in the background, suggesting a modern, urban environment" } ], "visual_description": "[PERSON_1] is shown in a close-up, looking slightly off-camera to her left. She speaks with a serious expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.9, 5.4 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with dark hair, wearing glasses, with a serious expression", "attributes": "clothing: Black turtleneck sweater under a black coat or blazer., hairstyle: Dark hair, neatly styled with a slight part., accessories: Wire-rimmed glasses, a wristwatch on his left wrist" }, "SCENE_1", "PERSON_1" ], "visual_description": "The camera cuts to a medium shot of [PERSON_2]. He is sitting with his hands clasped in front of him, looking towards where [PERSON_1] would be. He responds to her.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 2.1 ], "content": { "speaker": "PERSON_1", "line": "够", "description": "Firm and decisive tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.1, 2.9 ], "content": { "speaker": "PERSON_1", "line": "能不能日结", "description": "Inquiring, slightly demanding tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.9, 4.5 ], "content": { "speaker": "PERSON_2", "line": "可以", "description": "Calm and agreeable tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 4.5, 5.0 ], "content": { "speaker": "PERSON_2", "line": "日结时间", "description": "Stating a condition or following up on the agreement." } } ], "scene_description": "A woman and a man are having a serious conversation, seemingly negotiating payment terms.", "global_style": "Cinematic, modern, with shallow depth of field and cool-toned lighting.", "global_audio": "Quiet indoor ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_27626", "media_path": "drama_03/clip_27626.mp4", "source_media_path": "clips/clip_27626.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Older man with grey hair, wearing a gold ring on his left ring finger", "attributes": "White collared shirt, dark suit jacket" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A black gooseneck microphone with a rectangular base featuring a button" } ], "visual_description": "Close-up of [PERSON_1]'s hand pressing the button on the base of [OBJECT_1].", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.4, 2.5 ], "references": [ "PERSON_1" ], "visual_description": "Profile shot of [PERSON_1] looking forward with a serious expression.", "camera": { "shot_type": "close-up", "angle": "side view", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.5, 3.5 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A group of men sitting attentively at desks", "attributes": "Formal business suits, ties, and glasses" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A large room with wooden desks arranged in rows, large windows with curtains in the background" } ], "visual_description": "Wide shot from behind [PERSON_1], showing [PERSON_2] seated at desks in [SCENE_1].", "camera": { "shot_type": "wide shot", "angle": "over-the-shoulder", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 3.5, 4.7 ], "references": [ "PERSON_1" ], "visual_description": "Close-up of [PERSON_1] speaking directly to the camera.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 1.5 ], "content": { "speaker": "PERSON_1", "line": "轮到我发言了", "description": "Calm, narrative voiceover." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.5, 2.5 ], "content": { "speaker": "PERSON_1", "line": "我拿着麦克风", "description": "Calm, narrative voiceover." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.5, 3.6 ], "content": { "speaker": "PERSON_1", "line": "我只说了一句话", "description": "Calm, narrative voiceover." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 3.6, 4.2 ], "content": { "speaker": "PERSON_1", "line": "我希望大家", "description": "Serious, authoritative tone." } } ], "scene_description": "An older man prepares to address an audience at a formal conference, delivering a serious message.", "global_style": "Cinematic, dramatic lighting, corporate setting.", "global_audio": "Quiet ambient room tone with clear, authoritative dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_7574", "media_path": "drama_03/clip_7574.mp4", "source_media_path": "clips/clip_7574.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with fair skin, sharp eyebrows, and a serious expression", "attributes": "Black hair tied in a topknot with loose strands framing his face, wearing a dark blue robe with red and gold cloud-like patterns" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Blurred background showing wooden architectural elements and warm lighting" } ], "visual_description": "A close-up shot of [PERSON_1] looking forward with a serious and attentive expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.1, 4.4 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with fair skin, smiling gently", "attributes": "Black hair tied up, wearing a small gold crown and a red robe with intricate gold patterns" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "An older woman with a neutral expression", "attributes": "Grey hair tied back with a hairpin, wearing a plain grey high-collared dress" }, "SCENE_1" ], "visual_description": "A close-up shot of [PERSON_2] smiling and speaking. [PERSON_3] is visible in the background, standing quietly.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.4, 5.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A close-up shot returning to [PERSON_1], who maintains a serious expression and slightly lowers his gaze.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 1.8 ], "content": { "speaker": "PERSON_2", "line": "在府里开了个诗会", "description": "Explaining a situation in a calm tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.8, 4.1 ], "content": { "speaker": "PERSON_2", "line": "我不舍拒绝他们这才晚来了一会", "description": "Speaking with a friendly and slightly apologetic tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.6, 4.7 ], "content": { "speaker": "PERSON_1", "line": "不过", "description": "Responding with a serious tone." } } ], "scene_description": "Two young men are having a conversation in a traditional setting, where one is explaining why he arrived late.", "global_style": "3D animated style with realistic character designs and traditional Chinese clothing.", "global_audio": "Clear dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_5461", "media_path": "drama_03/clip_5461.mp4", "source_media_path": "clips/clip_5461.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, fair skin, and a serious expression", "attributes": "Wearing a white button-up shirt adorned with a red rose pin on the right and a black rose pin on the left, and a thin silver necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dark, blurred background suggesting an outdoor environment at night with subtle lighting" } ], "visual_description": "[PERSON_1] is shown in a close-up shot, looking slightly off-camera with a serious and concerned expression as he speaks.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.3, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long black hair, fair skin, and red lipstick", "attributes": "Wearing a white coat over a grey turtleneck sweater" }, "SCENE_1", "PERSON_1" ], "visual_description": "The camera cuts to a close-up of [PERSON_2]. She looks slightly downwards, then raises her eyes to meet the gaze of [PERSON_1] as she responds calmly.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 2.0, 2.8 ], "content": { "speaker": "PERSON_1", "line": "心魔把你吃掉", "description": "Serious and concerned tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 4.5 ], "content": { "description": "Soft, dramatic background music." } } ], "scene_description": "A serious nighttime conversation where a man warns a woman not to let her inner demons consume her, and she acknowledges his warning.", "global_style": "Cinematic, dramatic lighting, shallow depth of field.", "global_audio": "Soft, dramatic background music accompanying the dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_17701", "media_path": "drama_03/clip_17701.mp4", "source_media_path": "clips/clip_17701.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with long black hair styled in a half-updo with a silver hairpiece, wearing a light blue, multi-layered ancient Chinese robe", "attributes": "clothing: Light blue ancient Chinese robe, hairstyle: Long black hair, half-updo with silver hairpiece, accessories: Silver hairpiece" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor set with wooden lattice windows, wooden pillars, and various filming equipment like lights and monitors" } ], "visual_description": "[PERSON_1] is seen from the chest up, speaking directly to someone off-camera. He has a slightly surprised expression.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.3, 3.3 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short black hair wearing a brown jacket over a dark shirt", "attributes": "clothing: Brown jacket, dark shirt, hairstyle: Short black hair, accessories: None" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman with dark hair tied back, wearing glasses, a white puffy vest over a grey hoodie", "attributes": "clothing: White puffy vest, grey hoodie, hairstyle: Dark hair tied back, accessories: Glasses" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "Three black monitors arranged side-by-side on a table, with the letters 'J S' written on the back of each" }, "SCENE_1" ], "visual_description": "The camera cuts to a wider angle showing [PERSON_2] and [PERSON_3] standing behind a table with [OBJECT_1]. They are looking towards [PERSON_1], who is standing on the right side of the frame.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.3, 5.5 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera returns to a close-up of [PERSON_1]. He continues speaking, using hand gestures to emphasize his points.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 2.0 ], "content": { "speaker": "PERSON_1", "line": "DNA检测系统", "description": "Spoken with a tone of realization or surprise." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.0, 3.3 ], "content": { "speaker": "PERSON_1", "line": "好家伙", "description": "An exclamation of surprise." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.3, 5.4 ], "content": { "speaker": "PERSON_1", "line": "之前还是萌娃下山寻找首富爹爹", "description": "Spoken in an explanatory and slightly amused tone." } } ], "scene_description": "An actor in an ancient costume is on a filming set, talking to the crew behind the monitors about the plot or script, expressing surprise at the storyline.", "global_style": "Behind-the-scenes footage, casual and documentary style.", "global_audio": "Clear dialogue with some faint background set noise." } }, { "dataset": "drama_03", "clip_id": "clip_24218", "media_path": "drama_03/clip_24218.mp4", "source_media_path": "clips/clip_24218.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark hair, wearing a grey suit over a mesh shirt and a large amber pendant necklace", "attributes": "clothing: Grey suit, mesh shirt, hairstyle: Short dark hair, accessories: Large amber pendant necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit hallway with warm lighting" } ], "visual_description": "[PERSON_1] walks forward in [SCENE_1], looking serious and speaking.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 3.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "Close-up of [PERSON_1] continuing to speak angrily.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.0, 4.4 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A man wearing a black suit and a white shirt, holding a camera with a flash", "attributes": "clothing: Black suit, white shirt, hairstyle: Short dark hair, accessories: Camera with flash, ID badge" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman wearing a beige jacket, holding a camera", "attributes": "clothing: Beige jacket, hairstyle: Long dark hair, accessories: Camera, ID badge" }, "SCENE_1" ], "visual_description": "[PERSON_3] and [PERSON_4] are taking photos with their cameras, flashes going off.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "SFX_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.4, 6.7 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "Return to the close-up of [PERSON_1] finishing his sentence.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.7, 7.4 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with long dark wavy hair, wearing a pink silk robe and a pearl necklace", "attributes": "clothing: Pink silk robe, hairstyle: Long dark wavy hair, accessories: Pearl necklace" }, "SCENE_1" ], "visual_description": "[PERSON_2] is kneeling on the floor, holding onto the leg of [PERSON_1], looking up at him with a distressed expression.", "camera": { "shot_type": "Medium shot", "angle": "High angle", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.4, 2.4 ], "content": { "speaker": "PERSON_1", "line": "这些人", "description": "Accusatory tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.4, 4.5 ], "content": { "speaker": "PERSON_1", "line": "他们不就是你叫来的吗", "description": "Angry and confrontational tone" } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.0, 3.0 ], "content": { "description": "Camera shutter and flash sounds" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.5, 7.1 ], "content": { "speaker": "PERSON_1", "line": "你刚才得意忘形的样子哪里像本陷害", "description": "Cold and mocking tone" } } ], "scene_description": "A man confronts a kneeling woman in a hallway, accusing her of staging a situation with photographers.", "global_style": "Dramatic, modern television drama aesthetic with warm, moody lighting.", "global_audio": "Tense background ambience with dialogue and camera sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_15663", "media_path": "drama_03/clip_15663.mp4", "source_media_path": "clips/clip_15663.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin and dark hair styled in an elaborate updo", "attributes": "Wearing a light purple traditional Chinese dress with silver embroidery, a silver headpiece with dangling ornaments, and a delicate necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with fair skin, dark hair, and a distinct red mark on his forehead", "attributes": "Wearing a black outfit with a fur collar and a black headpiece with gold accents" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Dark background with blurred warm lights, suggesting a nighttime setting with lanterns or candles" } ], "visual_description": "[PERSON_1] is the main focus, speaking with a serious expression. [PERSON_2] is partially visible on the left side of the frame, facing her.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.5, 5.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], who is looking at [PERSON_1] with a serious and attentive expression. [PERSON_1] is partially visible on the right side of the frame.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.0, 4.2 ], "content": { "speaker": "PERSON_1", "line": "愿望许下了就得抓紧实现", "description": "Assertive and determined tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.2, 5.0 ], "content": { "speaker": "PERSON_1", "line": "从现在起", "description": "Firm and commanding tone." } } ], "scene_description": "A dramatic conversation between a woman and a man in traditional attire, where the woman declares her intention to immediately fulfill a wish.", "global_style": "Cinematic, traditional Chinese fantasy aesthetic, dramatic lighting.", "global_audio": "Quiet ambient background with clear, prominent dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_19263", "media_path": "drama_03/clip_19263.mp4", "source_media_path": "clips/clip_19263.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Only hands and arms are visible", "attributes": "Black leather jacket" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A bundle of envelopes with stamps and an open letter with handwritten Chinese characters" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A desk with a red folder or clipboard in the blurred background" } ], "visual_description": "[PERSON_2] holds [OBJECT_1] in [SCENE_1]. The camera focuses on the handwritten text of the open letter on top of the stack.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.0, 5.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with dark hair tied in a ponytail", "attributes": "Grey sweater" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A room with a wooden table, a vase of flowers, and warm ambient lighting" } ], "visual_description": "[PERSON_1] is sitting at a table in [SCENE_2], writing on a piece of paper with a pen.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.9, 4.3 ], "content": { "speaker": "PERSON_1", "line": "我在学校学习很好", "description": "Voiceover reading a letter, calm and reassuring tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.3, 4.6 ], "content": { "speaker": "PERSON_1", "line": "学费", "description": "Voiceover continuing to read the letter, slightly concerned tone." } } ], "scene_description": "A person reads a handwritten letter from a young woman who is shown writing it, discussing her studies and tuition fees.", "global_style": "Cinematic, nostalgic, with a mix of cool tones in the first scene and warm tones in the second.", "global_audio": "Quiet ambient sound with a clear female voiceover." } }, { "dataset": "drama_03", "clip_id": "clip_21183", "media_path": "drama_03/clip_21183.mp4", "source_media_path": "clips/clip_21183.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with long black hair, fair skin, and sharp facial features", "attributes": "Wearing a black official hat with side flaps, a long red robe, and a decorative belt" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin, her black hair styled in an elegant updo with hairpins", "attributes": "Wearing a pink traditional dress with a yellow sash, visibly pregnant" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring a wooden lattice window with bamboo visible outside, a large wooden bookshelf filled with books, and a wooden chair" } ], "visual_description": "[PERSON_1] is seated in [SCENE_1]. He sighs and then raises his right hand, gesturing for someone to approach. [PERSON_2] walks into the frame from the left and stands beside him. [PERSON_1] gently holds her hands.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 1.0 ], "content": { "speaker": "PERSON_1", "line": "唉", "description": "A heavy sigh." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.0, 2.0 ], "content": { "speaker": "PERSON_1", "line": "过来", "description": "A gentle command." } } ], "scene_description": "A man in ancient attire sits in a study and calls a pregnant woman over to him, holding her hands affectionately.", "global_style": "3D animation, ancient Chinese historical setting, realistic character rendering.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_1030", "media_path": "drama_03/clip_1030.mp4", "source_media_path": "clips/clip_1030.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man in his 30s with short black hair and a serious facial expression", "attributes": "Wearing a light grey button-up shirt over a white t-shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit room with a blurred, neutral-colored background" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A standard black smartphone" } ], "visual_description": "[PERSON_1] is standing in [SCENE_1], holding [OBJECT_1] to his right ear. He maintains a serious, focused expression as he listens intently to the call, blinking occasionally and making subtle head movements.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 1.3 ], "content": { "speaker": "PERSON_2", "line": "意料之中", "description": "Calm, narrative tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.3, 2.7 ], "content": { "speaker": "PERSON_2", "line": "王律师的声音很冷静", "description": "Calm, narrative tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.7, 4.0 ], "content": { "speaker": "PERSON_2", "line": "那我现在就把我们准备好的", "description": "Decisive, professional tone." } } ], "scene_description": "A man listens seriously to a phone call where a female voice narrates his calm demeanor and confirms the sending of prepared documents to a corporate board.", "global_style": "Modern, serious, dramatic corporate aesthetic.", "global_audio": "Clear voiceover dialogue with a serious and professional tone." } }, { "dataset": "drama_03", "clip_id": "clip_10636", "media_path": "drama_03/clip_10636.mp4", "source_media_path": "clips/clip_10636.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.6 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with black hair tied up in a topknot", "attributes": "Wearing a dark blue robe with grey patterned lapels and a black headband" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with black hair tied up in a topknot", "attributes": "Wearing a dark blue robe with grey patterned lapels and a black headband" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor area with a stone wall and trees in the background" } ], "visual_description": "[PERSON_1] and [PERSON_2] are standing side-by-side, smiling broadly and clapping their hands. They are looking towards the left side of the frame.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "SFX_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.6, 2.9 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young woman with long black hair, partially tied up", "attributes": "Wearing a light grey and white patterned dress with white floral hair accessories" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A young man with black hair tied up", "attributes": "Wearing a white robe with light green accents and a silver headpiece" }, "SCENE_1", "PERSON_1", "PERSON_2" ], "visual_description": "The camera cuts to [PERSON_3] and [PERSON_4] standing together. [PERSON_3] is holding her pregnant belly with one hand. Both are smiling and looking towards the direction of [PERSON_1] and [PERSON_2]. [PERSON_3] then turns her gaze up towards [PERSON_4].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.9, 5.0 ], "references": [ "PERSON_3", "PERSON_4", "SCENE_1" ], "visual_description": "A close-up of [PERSON_3] as she looks affectionately at [PERSON_4] with a gentle smile.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.0, 5.0 ], "references": [ "PERSON_4", "SCENE_1", "PERSON_3" ], "visual_description": "A close-up of [PERSON_4] returning the affectionate gaze, smiling warmly back at [PERSON_3].", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 0.8 ], "content": { "description": "Sound of hands clapping." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Gentle, uplifting instrumental background music." } } ], "scene_description": "Two men enthusiastically applaud a couple, consisting of a pregnant woman and a man, who share a warm, affectionate look with each other.", "global_style": "Historical Chinese drama aesthetic with bright, natural outdoor lighting and elaborate traditional costumes.", "global_audio": "A mix of enthusiastic dialogue, clapping sound effects, and a gentle, emotional instrumental soundtrack." } }, { "dataset": "drama_03", "clip_id": "clip_24211", "media_path": "drama_03/clip_24211.mp4", "source_media_path": "clips/clip_24211.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with a fair complexion, large eyes, and long, dark, wavy hair parted in the middle", "attributes": "Wearing an off-the-shoulder, long-sleeved white top or dress" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A standard black smartphone with a visible camera module on the back" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit room with a blurred background featuring a green potted plant and a modern floor lamp" } ], "visual_description": "[PERSON_1] is sitting in [SCENE_1], looking down at [OBJECT_1] in her hand. Her expression shifts to one of shock and distress. She lowers [OBJECT_1], looks up with a resolute and anxious gaze, and begins to speak.", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "SFX_1", "DIALOGUE_1", "DIALOGUE_2" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 0.5 ], "content": { "description": "A short, high-pitched digital notification beep." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 2.5, 3.5 ], "content": { "speaker": "PERSON_1", "line": "不行", "description": "Spoken with sudden realization and anxiety." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.5, 4.9 ], "content": { "speaker": "PERSON_1", "line": "我要去找京城哥哥问清楚", "description": "Spoken with a determined and urgent tone." } } ], "scene_description": "A young woman receives concerning information on her phone, prompting her to make an urgent decision to confront someone for answers.", "global_style": "Modern dramatic style with soft, naturalistic lighting and a shallow depth of field focusing on the character's emotional reaction.", "global_audio": "Quiet indoor ambience with clear, prominent dialogue and a distinct digital sound effect." } }, { "dataset": "drama_03", "clip_id": "clip_17364", "media_path": "drama_03/clip_17364.mp4", "source_media_path": "clips/clip_17364.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Older male with a goatee, mustache, and a distressed expression", "attributes": "clothing: Dark green traditional Chinese robe with gold and patterned trim over a white inner layer., hairstyle: Hair pulled up into a topknot., accessories: Black and gold headpiece" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Indoor setting with wooden lattice screens and warm ambient lighting" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A small light green bowl filled with white rice" } ], "visual_description": "[PERSON_1] is sitting in [SCENE_1] with [OBJECT_1] on the table in front of him. He has a highly distressed, crying expression and is vocalizing his frustration.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 2.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Young female with a fair complexion and a playful smile", "attributes": "clothing: Light blue and white traditional Chinese dress with red tassels and embroidered details., hairstyle: Elaborate traditional updo with dangling hair ornaments., accessories: Hairpins, earrings, and a necklace" }, "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2] standing in [SCENE_1]. She has her hands clasped near her chin and is smiling playfully, observing the situation.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 2.2, 4.8 ], "references": [ "PERSON_1", "SCENE_1", "OBJECT_1" ], "visual_description": "The camera cuts back to [PERSON_1] in [SCENE_1]. He continues to cry exaggeratedly and then speaks pleadingly while looking forward.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 1.0 ], "content": { "description": "Exaggerated crying and whining sounds." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 3.4, 4.1 ], "content": { "speaker": "PERSON_1", "line": "求你了", "description": "Pleading and crying dramatically." } } ], "scene_description": "An older man is dramatically crying and pleading with a young woman, who seems amused by his exaggerated behavior.", "global_style": "Historical Chinese drama with a comedic and lighthearted tone, featuring bright and warm lighting.", "global_audio": "Exaggerated crying sounds and spoken dialogue with no prominent background music." } }, { "dataset": "drama_03", "clip_id": "clip_18927", "media_path": "drama_03/clip_18927.mp4", "source_media_path": "clips/clip_18927.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with short black hair", "attributes": "Grey suit jacket, white button-up shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit room with a blurred background" } ], "visual_description": "[PERSON_1] looks off-camera to his left and speaks while slightly adjusting his jacket with his hand.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.5, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with long black hair and bangs", "attributes": "White turtleneck sweater, cream-colored coat, large earrings" }, "SCENE_1" ], "visual_description": "[PERSON_2] reacts with a surprised expression, then speaks with a slightly disbelieving and teasing look.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 1.9 ], "content": { "speaker": "PERSON_1", "line": "是明天在我办公室", "description": "Casual and informative tone." } } ], "scene_description": "A brief conversation between a man and a woman where the man mentions a shooting location, prompting a surprised and teasing reaction from the woman.", "global_style": "Modern drama aesthetic with soft lighting and close-up shots focusing on character expressions.", "global_audio": "Clear dialogue with quiet ambient background noise." } }, { "dataset": "drama_03", "clip_id": "clip_17075", "media_path": "drama_03/clip_17075.mp4", "source_media_path": "clips/clip_17075.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark hair, wet skin, and a muscular physique", "attributes": "Shirtless, wet skin, dark hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room filled with steam, illuminated by warm, golden light", "attributes": "Steamy, warm lighting, golden hue" } ], "visual_description": "The camera focuses closely on the muscular, wet chest of [PERSON_1] in [SCENE_1]. The lighting is warm and golden, highlighting the water droplets on his skin.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "tilt up" }, "active_events": [ "DIALOGUE_1", "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.8, 5.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera continues to tilt up, revealing the face of [PERSON_1]. His eyes are closed, and he appears relaxed as steam swirls around him in [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "tilt up" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.9, 3.6 ], "content": { "speaker": "PERSON_2", "line": "肌硬不硬", "description": "Admiring and questioning tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.0, 2.0 ], "content": { "description": "A sharp intake of breath or sigh." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.6, 4.4 ], "content": { "speaker": "PERSON_2", "line": "看他那身材", "description": "Admiring tone." } } ], "scene_description": "A cinematic, slow-motion sequence featuring a shirtless man in a steamy, warmly lit environment, accompanied by an admiring off-screen female voiceover.", "global_style": "Cinematic, warm, golden, steamy, sensual.", "global_audio": "Ambient room tone with a prominent female voiceover and a breathing sound effect." } }, { "dataset": "drama_03", "clip_id": "clip_2042", "media_path": "drama_03/clip_2042.mp4", "source_media_path": "clips/clip_2042.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark, slightly wet hair, wearing a dark suit", "attributes": "black suit jacket, dark shirt, red tie" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short dark hair, wearing glasses and casual winter clothing", "attributes": "dark grey turtleneck sweater, brown trousers, gold-rimmed glasses" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A small, metallic lighter" } ], "visual_description": "[PERSON_2] holds [OBJECT_1] to light a cigarette for [PERSON_1], who is kneeling and leaning forward to the flame.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.3, 4.0 ], "references": [ "PERSON_2", "PERSON_1" ], "visual_description": "[PERSON_2] looks down at [PERSON_1] with a serious expression while speaking.", "camera": { "shot_type": "medium shot", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.0, 4.9 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious room with a light-colored sofa, a dark coffee table, and a large potted plant in the background" } ], "visual_description": "A wide view of [SCENE_1] showing [PERSON_1] kneeling on the floor. [PERSON_2] turns away from [PERSON_1] and begins to walk off.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.9, 5.0 ], "references": [ "PERSON_2" ], "visual_description": "[PERSON_2] walks past the camera, his back and shoulder filling the frame as he exits.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "pan" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 1.0 ], "content": { "speaker": "PERSON_2", "line": "抽完这根烟", "description": "Calm, authoritative tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.0, 2.0 ], "content": { "speaker": "PERSON_2", "line": "你就走吧", "description": "Dismissive, final tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Dramatic, tense instrumental background music." } } ], "scene_description": "A tense confrontation in a modern living room where a standing man lights a cigarette for a kneeling man, then coldly dismisses him.", "global_style": "Dark, moody, cinematic lighting with a dramatic and serious atmosphere.", "global_audio": "Tense, dramatic instrumental music playing throughout the scene." } }, { "dataset": "drama_03", "clip_id": "clip_21576", "media_path": "drama_03/clip_21576.mp4", "source_media_path": "clips/clip_21576.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with long dark hair, wearing a white coat over a beige top, and dangling earrings", "attributes": "long dark hair, white coat, beige top, dangling earrings" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "A man with short dark hair wearing a black coat", "attributes": "short dark hair, black coat" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor space with white walls, glass doors, and red accents", "attributes": "white walls, glass doors, red accents" } ], "visual_description": "[PERSON_1] stands looking concerned. [PERSON_5] is partially visible in the background.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.8, 2.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A middle-aged man with short dark hair, wearing a brown patterned traditional Chinese shirt, holding a string of prayer beads", "attributes": "short dark hair, brown patterned traditional shirt, prayer beads" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman with dark hair tied back, wearing a white dress with ruffled details", "attributes": "dark hair tied back, white ruffled dress, earrings" }, "SCENE_1" ], "visual_description": "[PERSON_2] speaks with a serious expression, holding prayer beads in his hand. The arm of [PERSON_3] is visible next to him.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.8, 5.5 ], "references": [ "PERSON_3", "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_3] stands looking down with a sad expression. [PERSON_1] is visible in the background.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.5, 6.7 ], "references": [ "PERSON_2", "PERSON_3", { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman with long dark hair, wearing a dark top, seen touching her face", "attributes": "long dark hair, dark top" }, "SCENE_1" ], "visual_description": "[PERSON_2] continues speaking. [PERSON_3] and [PERSON_4] are visible in the background, with [PERSON_4] touching her face.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 2.5 ], "content": { "speaker": "PERSON_2", "line": "皮膚极薄", "description": "Serious and descriptive tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.5, 4.6 ], "content": { "speaker": "PERSON_2", "line": "好似没有", "description": "Grave and concerned tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.6, 6.2 ], "content": { "speaker": "PERSON_2", "line": "我勋变皮肤科专家", "description": "Desperate and explanatory tone." } } ], "scene_description": "A tense conversation where a man describes a severe skin condition, while the people around him listen with concern and distress.", "global_style": "Dramatic and serious, typical of a modern drama.", "global_audio": "Dialogue-driven with no prominent background music." } }, { "dataset": "drama_03", "clip_id": "clip_13648", "media_path": "drama_03/clip_13648.mp4", "source_media_path": "clips/clip_13648.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair", "attributes": "black jacket, black t-shirt, silver chain necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long black hair tied back", "attributes": "beige patterned long-sleeve top, white pants, yellow shoulder bag" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor plaza in front of a modern building featuring large colorful posters on the windows, one of which reads 'LE PARK'" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A blue and black sports motorcycle" } ], "visual_description": "Wide shot showing [PERSON_1] sitting on [OBJECT_1] while talking to [PERSON_2] who is standing next to him in [SCENE_1].", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.5, 2.2 ], "references": [ "PERSON_2" ], "visual_description": "Medium close-up of [PERSON_2] looking slightly away and then speaking.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.2, 3.4 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "Medium close-up of [PERSON_1] looking at [PERSON_2] and speaking.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 3.4, 5.0 ], "references": [ "PERSON_2" ], "visual_description": "Medium close-up of [PERSON_2] looking away again and speaking.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 1.6 ], "content": { "speaker": "PERSON_1", "line": "我都推你们蛋糕店", "description": "Casual statement" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.6, 1.9 ], "content": { "speaker": "PERSON_2", "line": "你来干", "description": "Questioning tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.2, 3.0 ], "content": { "speaker": "PERSON_1", "line": "来揪了下班", "description": "Playful and affectionate tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 3.9, 4.6 ], "content": { "speaker": "PERSON_2", "line": "到时候", "description": "Dismissive or hesitant tone" } } ], "scene_description": "A man on a motorcycle and a woman standing next to him are having a brief conversation outdoors.", "global_style": "Modern urban drama aesthetic with natural lighting.", "global_audio": "Quiet outdoor ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_1163", "media_path": "drama_03/clip_1163.mp4", "source_media_path": "clips/clip_1163.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with long wavy brown hair, wearing a silver necklace with a large pendant", "attributes": "Red strapless evening dress, silver necklace, long wavy brown hair, makeup" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor street setting at night with glowing blue streetlights and dark silhouettes of trees and buildings", "attributes": "Nighttime, streetlights, outdoor" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], looking forward with a stern and slightly angry expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with short black hair, visible tears and water droplets on her face", "attributes": "Short black hair, wet face, crying expression" } ], "visual_description": "A close-up of [PERSON_2]'s face. She is crying, with tears and water droplets streaming down her cheeks.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 1.7 ], "content": { "speaker": "PERSON_3", "line": "林静是凌月的妹妹", "description": "Narrating in a serious tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.7, 3.2 ], "content": { "speaker": "PERSON_3", "line": "每一个虐文女主的背后", "description": "Narrating in a serious tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.4, 4.9 ], "content": { "speaker": "PERSON_3", "line": "个跟着她哥一起做见她", "description": "Narrating in a serious tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Melancholic and dramatic background music." } } ], "scene_description": "An animated sequence introducing a character named Lin Jing and describing the trope of an abused female lead.", "global_style": "Anime style, dramatic and emotional.", "global_audio": "Dramatic background music with a female voiceover narration." } }, { "dataset": "drama_03", "clip_id": "clip_1576", "media_path": "drama_03/clip_1576.mp4", "source_media_path": "clips/clip_1576.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with dark hair tied back, wearing full tactical gear", "attributes": "Camouflage uniform, tactical helmet with night vision goggles mounted on top, headset, tactical vest with various pouches and a small circular device" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A blurred background showing tree trunks and foliage, indicating a wooded area" } ], "visual_description": "[PERSON_1] is seen from the chest up in [SCENE_1]. She is looking slightly off-camera to her left, speaking. She briefly raises her right hand towards her face while talking.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.0, 6.5 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A middle-aged man with a weathered face, wearing full tactical gear", "attributes": "Camouflage uniform, tactical helmet with night vision goggles mounted on top, headset, tactical vest with a rectangular device mounted on the chest" }, "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2] in [SCENE_1], seen from the chest up. He is smiling broadly, looking slightly off-camera to his right, and speaking.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 3.6 ], "content": { "speaker": "PERSON_1", "line": "我看你好像挺照顾那个平头哥的", "description": "Observational and slightly questioning tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.6, 5.8 ], "content": { "speaker": "PERSON_2", "line": "平头哥谁给他起的外号", "description": "Amused and curious tone." } } ], "scene_description": "Two soldiers in tactical gear are having a brief conversation in a forest setting. The female soldier makes an observation about the male soldier's behavior towards someone nicknamed 'Ping Tou Ge', to which the male soldier responds with an amused question about the origin of the nickname.", "global_style": "Realistic, military drama style with a shallow depth of field focusing on the characters.", "global_audio": "Quiet outdoor ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_6075", "media_path": "drama_03/clip_6075.mp4", "source_media_path": "clips/clip_6075.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, wearing elaborate traditional Chinese makeup including a red mark on her forehead", "attributes": "White top with red embroidered trim, red skirt, complex updo hairstyle adorned with numerous red and gold hairpins and ornaments, wearing a beaded necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A warmly lit room with blurred traditional furniture and architectural elements in the background" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "Rectangular papers with Chinese characters printed on them, appearing aged or traditional" } ], "visual_description": "[PERSON_1] is sitting in [SCENE_1], holding [OBJECT_1]. She looks down at the papers, sighs, then looks up with a distressed expression and speaks.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1", "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.7, 5.0 ], "references": [ "PERSON_1", "SCENE_1", "OBJECT_1" ], "visual_description": "The camera angle changes to show [PERSON_1] from a slightly different perspective. She continues to look sad while holding [OBJECT_1].", "camera": { "shot_type": "medium shot", "angle": "slightly low angle", "movement": "static" }, "active_events": [ "SFX_2" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 1.0 ], "content": { "description": "Sound of papers rustling." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.5, 3.4 ], "content": { "speaker": "PERSON_1", "line": "我要什么时候才能回家啊", "description": "Sad, longing, and frustrated tone." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 4.0, 5.0 ], "content": { "description": "A distinct chime or ding sound effect." } } ], "scene_description": "A woman in traditional Chinese clothing expresses her longing to return home while holding a large stack of documents.", "global_style": "Historical Chinese drama aesthetic, warm and slightly melancholic tone.", "global_audio": "Quiet ambient room noise with clear dialogue and distinct sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_28546", "media_path": "drama_03/clip_28546.mp4", "source_media_path": "clips/clip_28546.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A small girl viewed from behind, running energetically", "attributes": "Wearing a pink and peach traditional Chinese dress with flowing ribbons, hair styled in double buns with floral ornaments" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A wide set of stone stairs leading up to a dark, open doorway", "attributes": "The stairs are heavily carved with large, detailed dragon motifs" } ], "visual_description": "[PERSON_1] runs quickly up the carved stone steps of [SCENE_1] towards a dark, open doorway. The camera follows her from behind, capturing the movement of her dress and ribbons.", "camera": { "shot_type": "medium shot", "angle": "low angle", "movement": "tracking" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.3, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with a pale complexion and a serious expression", "attributes": "Wearing dark traditional clothing with intricate gold embroidery, a red inner collar, and long dark hair" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A dimly lit room focused on a wooden desk", "attributes": "The desk is cluttered with stacks of documents, a writing brush, and an inkstone" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "Thick sheets of paper stacked on a desk", "attributes": "The papers have vertical lines of Chinese characters written on them" } ], "visual_description": "The scene cuts to [SCENE_2] where [PERSON_2] is seated at a desk. His hand flips through a stack of [OBJECT_1], lifting a page to reveal more text underneath. He looks down at the papers with a serious expression as he speaks.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_2", "DIALOGUE_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 1.5 ], "content": { "description": "Rapid, light footsteps on stone." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 1.5, 3.0 ], "content": { "description": "Rustling and flipping of thick paper." } } ], "scene_description": "A little girl runs up a grand staircase towards a building, followed by a cut to a man inside a study reviewing concerning documents about a food shortage.", "global_style": "3D animation with a traditional Chinese fantasy aesthetic, featuring detailed costumes and environments.", "global_audio": "A dramatic and slightly tense atmosphere, transitioning from the energetic sounds of running to the quiet, serious rustling of papers and spoken dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_17921", "media_path": "drama_03/clip_17921.mp4", "source_media_path": "clips/clip_17921.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with long white hair, fair skin, and a serious expression", "attributes": "Wearing a black robe with red collar and silver embroidery, and a silver headpiece" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with a round face and a slightly confused expression", "attributes": "Wearing a black patterned robe with a dark red collar and a black hat" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A small table covered with a grey patterned cloth" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A courtyard with traditional Chinese architecture, red pillars, and green bamboo leaves in the foreground" } ], "visual_description": "The camera looks through green bamboo leaves in the foreground, revealing [PERSON_1] sitting at [OBJECT_2] in [SCENE_1]. [PERSON_2] is standing behind him.", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 3.0 ], "references": [ "PERSON_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A small, folded piece of white cloth or paper" }, "SCENE_1" ], "visual_description": "The camera cuts to a closer view of [PERSON_1] sitting and looking down at [OBJECT_1] in his hands.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.0, 4.7 ], "references": [ "PERSON_2", { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man standing still", "attributes": "Wearing a black uniform" }, "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2] speaking with a questioning expression. [PERSON_3] is visible standing in the background.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.7, 6.4 ], "references": [ "PERSON_1", "OBJECT_1", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1], who is still holding [OBJECT_1]. He looks up slightly and speaks.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 3.3 ], "content": { "speaker": "PERSON_2", "line": "大人你从祥悟府找到密信了", "description": "Respectful reporting" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.3, 5.7 ], "content": { "speaker": "PERSON_2", "line": "怎么不直接回咱们自己家啊就隔一条街", "description": "Curious inquiry" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.7, 6.2 ], "content": { "speaker": "PERSON_1", "line": "你懂什么", "description": "Dismissive response" } } ], "scene_description": "A subordinate questions his lord about their current location after retrieving a secret letter, to which the lord responds dismissively.", "global_style": "Historical Chinese costume drama with vibrant colors and natural lighting.", "global_audio": "Clear dialogue with subtle outdoor ambient sounds." } }, { "dataset": "drama_03", "clip_id": "clip_23526", "media_path": "drama_03/clip_23526.mp4", "source_media_path": "clips/clip_23526.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with long black hair wearing a black robe with gold embroidery and a gold crown-like headpiece", "attributes": "black robe, gold embroidery, gold headpiece, long black hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A courtyard surrounded by a multi-story traditional Chinese wooden building with stairs and balconies", "attributes": "wooden building, stairs, balconies, traditional architecture" } ], "visual_description": "[PERSON_1] stands in [SCENE_1] and yells aggressively, gesturing with his head and looking furious.", "camera": { "shot_type": "medium shot", "angle": "slightly low angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.2, 3.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with long black hair wearing a black robe with gold embroidery and a black headpiece", "attributes": "black robe, gold embroidery, black headpiece, long black hair" }, "SCENE_1" ], "visual_description": "[PERSON_2] sits calmly at a table, looking slightly downward, seemingly unfazed by the outburst.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 3.2, 4.1 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with long black hair wearing a purple robe with black trim and a black headpiece", "attributes": "purple robe, black trim, black headpiece, long black hair, sword" }, "SCENE_1" ], "visual_description": "[PERSON_3] angrily draws his sword from its scabbard, stepping forward with a hostile expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.1, 4.7 ], "references": [ { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman wearing a pink dress with an elaborate hairstyle adorned with hairpins, holding a white handkerchief", "attributes": "pink dress, elaborate hairstyle, hairpins, white handkerchief" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "A woman wearing a light blue and grey dress with an elaborate hairstyle adorned with hairpins, holding a round fan", "attributes": "light blue dress, grey dress, elaborate hairstyle, hairpins, round fan" }, "SCENE_1" ], "visual_description": "[PERSON_4] and [PERSON_5] stand together, looking shocked and confused by the situation. [PERSON_4] holds a handkerchief to her chest.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 1.8 ], "content": { "speaker": "PERSON_1", "line": "都是垃圾", "description": "Loud, angry, insulting." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.8, 3.5 ], "content": { "description": "Metallic sound of a sword being drawn from its scabbard." } } ], "scene_description": "A tense confrontation occurs in a courtyard where one man angrily insults others, prompting another to draw his sword while bystanders react with shock.", "global_style": "Historical costume drama, vibrant colors, traditional aesthetic.", "global_audio": "Dramatic and tense atmosphere with clear dialogue and sharp sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_9336", "media_path": "drama_03/clip_9336.mp4", "source_media_path": "clips/clip_9336.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 6.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with dark hair tied back, wearing a light blue patterned pajama top", "attributes": "dark hair, tied back hair, light blue patterned pajama top" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A standard smartphone held in hand" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit room with soft lighting" } ], "visual_description": "[PERSON_1] is looking at [OBJECT_1] in [SCENE_1]. Chat bubbles are overlaid on the screen.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 6.5, 7.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with dark hair, wearing a light blue t-shirt", "attributes": "dark hair, light blue t-shirt" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A bedroom with blue bed sheets and pillows" } ], "visual_description": "[PERSON_2] is sleeping in [SCENE_2]. Chat bubbles remain overlaid on the screen.", "camera": { "shot_type": "medium close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 7.0 ], "content": { "description": "Melancholic background music with female vocals." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 4.9 ], "content": { "speaker": "PERSON_2", "line": "往後的五年你都要一個人待在國外你真的下定決心了", "description": "Serious and questioning tone." } } ], "scene_description": "A woman reads a serious text message about studying abroad alone for five years, while the sender of the message is shown sleeping.", "global_style": "Dramatic and melancholic.", "global_audio": "Quiet ambience with a melancholic song playing in the background." } }, { "dataset": "drama_03", "clip_id": "clip_15252", "media_path": "drama_03/clip_15252.mp4", "source_media_path": "clips/clip_15252.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin and black hair tied back", "attributes": "Wearing a light pink traditional-style top with purple trim and buttons, a purple skirt, pearl drop earrings, a necklace with a dark pendant, and a delicate hairpiece" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A multi-level wooden staircase with turned balusters and dark wood paneling on the walls" } ], "visual_description": "A high-angle view looking down at [PERSON_1] standing on [SCENE_1]. She is holding the handrail and looking up towards the camera.", "camera": { "shot_type": "high angle, full shot", "angle": "high", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 5.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A medium close-up of [PERSON_1] standing in [SCENE_1]. She looks slightly off-camera with a serious expression as she speaks.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.6, 1.7 ], "content": { "speaker": "PERSON_1", "line": "重要的東西都在那", "description": "Serious and informative tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.6, 4.1 ], "content": { "speaker": "PERSON_1", "line": "我們江家的地契", "description": "Emphasizing the importance of the item." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.1, 4.7 ], "content": { "speaker": "PERSON_1", "line": "肯定也在", "description": "Confident assertion." } } ], "scene_description": "A woman stands on a staircase and discusses the location of important family documents, specifically a land deed.", "global_style": "Period drama aesthetic with warm, slightly muted lighting and traditional costumes.", "global_audio": "Quiet ambient room tone with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_293", "media_path": "drama_03/clip_293.mp4", "source_media_path": "clips/clip_293.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.1 ], "references": [ { "ref_id": "SCENE_1", "type": "scene", "id_features": "Dark blue and purple clouds with a bright, fiery shape in the center and a bolt of lightning striking downwards" } ], "visual_description": "In [SCENE_1], a fiery shape resembling a creature appears in the dark, cloudy sky, accompanied by a strike of lightning.", "camera": { "shot_type": "wide", "angle": "low", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.1, 3.2 ], "references": [ { "ref_id": "SCENE_2", "type": "scene", "id_features": "A dimly lit area with stone floors covered in debris, dark walls, and a moody atmosphere" }, { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with long black hair, fair skin, wearing a silver hair ornament", "attributes": "White robes, long black hair, silver hair crown" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A figure wearing red robes, seen from a distance and out of focus", "attributes": "Red robes" } ], "visual_description": "In [SCENE_2], [PERSON_1] stands with his back to the camera, facing [PERSON_2] who is standing further away in the background.", "camera": { "shot_type": "medium", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.2, 4.7 ], "references": [ "SCENE_2", "PERSON_1" ], "visual_description": "A close-up profile of [PERSON_1]'s face in [SCENE_2], focusing on his ear, jawline, and hair.", "camera": { "shot_type": "close-up", "angle": "side", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 1.0 ], "content": { "description": "A comical farting or squelching sound." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.1, 3.5 ], "content": { "speaker": "PERSON_1", "line": "小五月", "description": "Serious, slightly melancholic tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.5, 4.1 ], "content": { "speaker": "PERSON_1", "line": "你是不是", "description": "Questioning, emotional tone." } } ], "scene_description": "The video begins with a brief, comical shot of a fiery cloud and lightning, before abruptly transitioning to a dramatic 3D animated scene where a man in white confronts another person in a dark, ruined setting.", "global_style": "A mix of a stylized 2D/VFX opening followed by high-quality 3D animation with dark, moody lighting and realistic textures.", "global_audio": "Starts with a comical sound effect, then shifts to clear, dramatic dialogue with no prominent background music." } }, { "dataset": "drama_03", "clip_id": "clip_472", "media_path": "drama_03/clip_472.mp4", "source_media_path": "clips/clip_472.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, long black hair styled with hairpins, wearing a flowing red dress with a wide belt and a white circular waist ornament", "attributes": "long black hair, hairpins, red Hanfu dress, wide belt, white circular waist ornament, red boots" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A clear blue sky filled with soft, white clouds", "attributes": "blue sky, white clouds" } ], "visual_description": "[PERSON_1] stands against [SCENE_1], laughing with her head tilted back and hands clasped in front of her waist.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 2.8 ], "references": [ "PERSON_1" ], "visual_description": "An extreme close-up of [PERSON_1]'s eye as a tear forms and rolls down her cheek.", "camera": { "shot_type": "extreme close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.8, 4.3 ], "references": [ "PERSON_1" ], "visual_description": "A close-up of [PERSON_1]'s smiling mouth, with a tear dropping past her chin.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.3, 5.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A close-up of [PERSON_1]'s feet wearing red boots, slowly levitating off the ground against [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "low angle", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.7, 2.8 ], "content": { "speaker": "PERSON_1", "line": "师兄生气", "description": "Laughing and speaking in a cheerful, slightly mocking tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.8, 4.0 ], "content": { "speaker": "PERSON_1", "line": "我怎么心情这么好", "description": "Speaking happily, followed by a light laugh." } } ], "scene_description": "A 3D animated female character in traditional red clothing laughs about her senior brother being angry, expressing a surprisingly good mood while shedding a tear and levitating.", "global_style": "3D animation, fantasy, traditional Chinese aesthetic.", "global_audio": "Clear voice acting with no distinct background music." } }, { "dataset": "drama_03", "clip_id": "clip_13350", "media_path": "drama_03/clip_13350.mp4", "source_media_path": "clips/clip_13350.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man viewed from behind, wearing a dark green robe", "attributes": "clothing: Dark green traditional robe., hairstyle: Hair tied up in a topknot with a hairpiece., accessories: None visible" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A nighttime outdoor setting with traditional wooden architecture, stone pathways, and glowing paper lanterns" } ], "visual_description": "[PERSON_1] walks away from the camera, his back turned, moving through [SCENE_1].", "camera": { "shot_type": "medium_shot", "angle": "eye_level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 3.3 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with a confident smile, wearing light-colored traditional clothing and elaborate hair accessories", "attributes": "clothing: Light blue and white traditional layered robes., hairstyle: Elaborate updo with silver hairpins and dangling ornaments., accessories: Silver earrings, holding a sword" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A young woman wearing warm-toned traditional clothing, holding a black rectangular object", "attributes": "clothing: Yellow and white traditional layered robes., hairstyle: Hair styled up with pink floral accessories., accessories: Holding a black rectangular object" }, { "ref_id": "PERSON_GROUP_1", "type": "person", "id_features": "A group of people, mostly women, wearing matching light purple and pink robes", "attributes": "clothing: Light purple and pink traditional robes., hairstyle: Various traditional updos., accessories: None distinct" }, "SCENE_1" ], "visual_description": "A high-angle wide shot reveals [PERSON_2] and [PERSON_3] standing on a raised stone platform in [SCENE_1]. Below them, [PERSON_GROUP_1] is gathered, looking up at the two women.", "camera": { "shot_type": "wide_shot", "angle": "high_angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.3, 6.1 ], "references": [ "PERSON_2", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A traditional sword with a dark, textured scabbard and a decorative hilt" }, "SCENE_1" ], "visual_description": "A close-up focuses on [PERSON_2], who rests [OBJECT_1] casually over her shoulder and smiles with a confident expression.", "camera": { "shot_type": "close_up", "angle": "eye_level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 6.1, 7.7 ], "references": [ "PERSON_2", "PERSON_3", "OBJECT_1", { "ref_id": "OBJECT_2", "type": "object", "id_features": "A flat, black rectangular object, possibly a ledger or a clapperboard" }, "SCENE_1" ], "visual_description": "A medium shot shows [PERSON_2] and [PERSON_3] standing together. [PERSON_3] holds [OBJECT_2] in her hands while looking towards [PERSON_2].", "camera": { "shot_type": "medium_shot", "angle": "eye_level", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 3.0 ], "content": { "speaker": "PERSON_GROUP_1", "line": "咦——", "description": "A collective, drawn-out sound of playful jeering or surprise from the crowd." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.0, 4.0 ], "content": { "speaker": null, "line": "哼", "description": "A short, dismissive scoff from an off-screen male voice." } } ], "scene_description": "In a nighttime courtyard setting, a confident woman holding a sword stands on a platform with a companion, facing a crowd that reacts to them with playful jeering.", "global_style": "Historical Chinese drama aesthetic, characterized by traditional costumes, wooden architecture, and atmospheric lantern lighting.", "global_audio": "The audio consists of vocal reactions from the characters, including a collective crowd noise and a distinct scoff, with no background music." } }, { "dataset": "drama_03", "clip_id": "clip_30334", "media_path": "drama_03/clip_30334.mp4", "source_media_path": "clips/clip_30334.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with black hair, wearing a light grey double-breasted suit jacket, a light blue shirt, and a grey patterned tie", "attributes": "black hair, light grey double-breasted suit, light blue shirt, grey patterned tie" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An office with a desk, a black leather chair, indoor plants, and a window in the background" } ], "visual_description": "[PERSON_1] is sitting in a black leather chair at a desk in [SCENE_1]. He looks slightly off-camera to his left and speaks.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.8, 5.1 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with black hair, wearing a dark blue suit jacket and a black button-down shirt", "attributes": "black hair, dark blue suit, black shirt" }, "SCENE_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A grey clipboard held by a person" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A couple of books held underneath a clipboard" }, "PERSON_1" ], "visual_description": "[PERSON_2] is standing in [SCENE_1], holding [OBJECT_1] and [OBJECT_2] in his hands. He speaks while looking towards the direction of [PERSON_1].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.2, 2.3 ], "content": { "speaker": "PERSON_1", "line": "俗话说", "description": "Thoughtful tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.3, 4.8 ], "content": { "speaker": "PERSON_2", "line": "要想抓住一个女人的心要先抓住她的胃", "description": "Explaining tone" } } ], "scene_description": "Two men are having a conversation in an office setting, discussing a common saying about relationships.", "global_style": "Professional, well-lit corporate office environment.", "global_audio": "Clear dialogue with quiet ambient room noise." } }, { "dataset": "drama_03", "clip_id": "clip_3287", "media_path": "drama_03/clip_3287.mp4", "source_media_path": "clips/clip_3287.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A middle-aged man with short black hair, wearing glasses", "attributes": "Brown plaid three-piece suit, white shirt, striped tie, glasses" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A middle-aged woman with her hair styled up in an elegant updo", "attributes": "Light green long-sleeved dress with a mandarin collar and decorative buttons, pearl earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A well-lit room with a blurred background, featuring warm lighting and what appears to be a living room or upscale lobby environment" } ], "visual_description": "[PERSON_1] stands facing [PERSON_2], whose back is to the camera. [PERSON_1] smiles warmly and speaks to her.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 4.4 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], showing her face as she listens to [PERSON_1], whose shoulder is visible in the foreground. She maintains a calm, neutral expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.4, 4.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1], who continues speaking to [PERSON_2] with a pleasant smile.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.0, 3.0 ], "content": { "description": "A sparkling, magical chime sound effect." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.7, 3.5 ], "content": { "speaker": "PERSON_1", "line": "你今日的穿着", "description": "Complimentary tone." } } ], "scene_description": "A man and a woman are having a polite and complimentary conversation indoors. The man praises the woman's outfit.", "global_style": "Bright, elegant, and polished visual aesthetic typical of a modern drama.", "global_audio": "Clear dialogue with a subtle, magical sound effect added for emphasis." } }, { "dataset": "drama_03", "clip_id": "clip_2000", "media_path": "drama_03/clip_2000.mp4", "source_media_path": "clips/clip_2000.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A middle-aged man with short dark hair, wearing glasses", "attributes": "Dark blue double-breasted coat, dark turtleneck sweater, silver-rimmed glasses" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A very dark background with minimal lighting" } ], "visual_description": "[PERSON_1] is seen in profile, looking to the left and speaking with a serious expression in [SCENE_1].", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.0, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man lying on his back", "attributes": "Black and white striped suit" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A man standing", "attributes": "Dark suit" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A room with a white counter, a large red abstract sculpture, and a digital screen displaying a cityscape" } ], "visual_description": "[PERSON_2] is lying on his back on a white counter in [SCENE_2], gesturing with his hand while speaking. [PERSON_3] stands behind the counter looking down at him.", "camera": { "shot_type": "Wide shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.6, 4.4 ], "content": { "speaker": "PERSON_1", "line": "既然他不懂规矩就教教他规矩", "description": "Stern and commanding tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.4, 5.0 ], "content": { "speaker": "PERSON_2", "line": "您的意思是", "description": "Questioning, slightly strained tone." } } ], "scene_description": "A man gives a stern order to teach someone a lesson, followed by a cut to another man lying on a counter, seemingly reacting to the situation.", "global_style": "Dramatic, modern, slightly tense.", "global_audio": "Dialogue with no prominent background music." } }, { "dataset": "drama_03", "clip_id": "clip_9097", "media_path": "drama_03/clip_9097.mp4", "source_media_path": "clips/clip_9097.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, a fair complexion, and a serious, slightly sad expression", "attributes": "beige jacket, white shirt, black hair" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman with long dark hair, standing still in the background", "attributes": "light green top, brown skirt, long hair" } ], "visual_description": "A close-up shot of [PERSON_1] looking down with a somber expression. In the blurred background, [PERSON_3] is visible standing still.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.9, 3.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short black hair, wearing glasses, with a serious and sympathetic facial expression", "attributes": "glasses, brown leather jacket, black shirt, black pants" } ], "visual_description": "A close-up shot of [PERSON_2] speaking. He looks slightly downward, maintaining a serious and sympathetic expression.", "camera": { "shot_type": "close-up", "angle": "slightly high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.8, 5.0 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A bright white hallway with repeating arched structures and a highly reflective black floor" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A standard black manual wheelchair with large rear wheels" } ], "visual_description": "A wide shot showing [PERSON_1] sitting in [OBJECT_1] while [PERSON_2] stands beside him in [SCENE_1]. The reflective floor mirrors their figures. A stylized title graphic appears over the scene.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.1, 2.4 ], "content": { "speaker": "PERSON_2", "line": "让你的双腿", "description": "Continuing with a serious tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.4, 3.3 ], "content": { "speaker": "PERSON_2", "line": "无法真正地恢复", "description": "Delivering unfortunate news with a sympathetic but firm tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Subtle, dramatic background music." } } ], "scene_description": "A doctor or specialist informs a young man in a wheelchair that his legs will not fully recover despite nerve repair treatments.", "global_style": "Modern, clinical, and slightly dramatic with a cool color palette and futuristic architectural elements.", "global_audio": "Clear dialogue with a quiet, dramatic musical underscore." } }, { "dataset": "drama_03", "clip_id": "clip_13173", "media_path": "drama_03/clip_13173.mp4", "source_media_path": "clips/clip_13173.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short dark hair, wearing a formal suit", "attributes": "black suit jacket, black trousers, striped dress shirt, dark tie, black dress shoes" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dirt road lined with green fields and traditional brick houses with tiled roofs, mountains in the background" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A brown, hard-shell rolling suitcase with an extended handle" } ], "visual_description": "[PERSON_1] walks confidently down [SCENE_1] towards the camera, pulling [OBJECT_1] behind him.", "camera": { "shot_type": "full shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.8, 3.5 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short dark hair, smiling broadly", "attributes": "black suit jacket, black dress shirt, red boutonniere on the lapel" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "An open area decorated with red lanterns, a wooden archway, and seating for guests" } ], "visual_description": "[PERSON_1] and [PERSON_2] stand side-by-side at [SCENE_2]. [PERSON_1] smiles and pats [PERSON_2] on the shoulder.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.5, 4.5 ], "references": [ "PERSON_1", "SCENE_2" ], "visual_description": "[PERSON_1] walks briskly through [SCENE_2], gesturing with his hand as if directing guests or helping out.", "camera": { "shot_type": "medium full shot", "angle": "eye level", "movement": "pan" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.5, 6.3 ], "references": [ "PERSON_1", { "ref_id": "SCENE_3", "type": "scene", "id_features": "A room with white walls, wooden window frames, and wooden furniture" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A large red paper cutout of the 'Double Happiness' character" } ], "visual_description": "[PERSON_1] stands in [SCENE_3], carefully attaching [OBJECT_2] to the wall.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_4", "MUSIC_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.3, 7.7 ], "references": [ "PERSON_1", { "ref_id": "SCENE_4", "type": "scene", "id_features": "A nighttime setting with round tables full of food, surrounded by guests and illuminated by string lights" } ], "visual_description": "[PERSON_1] sits at a crowded table in [SCENE_4], looking down and picking up food with his chopsticks.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_5", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 1.8 ], "content": { "speaker": "PERSON_1", "line": "回老家参加发小婚礼", "description": "Narrative voiceover explaining the situation." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.8, 2.8 ], "content": { "speaker": "PERSON_1", "line": "忙得脚不沾地", "description": "Narrative voiceover describing how busy he is." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.8, 5.2 ], "content": { "speaker": "PERSON_1", "line": "当伴郎招呼客人帮忙布置", "description": "Narrative voiceover listing his duties." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 5.2, 6.3 ], "content": { "speaker": "PERSON_1", "line": "连手机都没空看", "description": "Narrative voiceover emphasizing his lack of free time." } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 6.3, 7.3 ], "content": { "speaker": "PERSON_1", "line": "晚上刚做下八口饭", "description": "Narrative voiceover describing finally getting to eat." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 7.0 ], "content": { "description": "Lighthearted, upbeat background music." } } ], "scene_description": "A man returns to his rural hometown to serve as a groomsman for his childhood friend's wedding. The video highlights his busy day, from arriving with his luggage to helping with decorations, greeting guests, and finally sitting down for a meal at the evening banquet.", "global_style": "Bright, lively, and realistic, capturing the festive and bustling atmosphere of a traditional rural Chinese wedding.", "global_audio": "A continuous upbeat and cheerful background music track accompanies a first-person narrative voiceover." } }, { "dataset": "drama_03", "clip_id": "clip_22709", "media_path": "drama_03/clip_22709.mp4", "source_media_path": "clips/clip_22709.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Older man, bald on top with glasses", "attributes": "tan blazer, black shirt, patterned tie, glasses" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Young woman with long dark hair", "attributes": "white blouse with a pink bow, pink headband" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Office space with desks, computers, and a filing cabinet" } ], "visual_description": "[PERSON_1] and [PERSON_2] walk into [SCENE_1]. [PERSON_1] leans forward, looking around the office with an angry expression. [PERSON_2] follows closely behind him.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 3.0 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "Young woman with long dark hair tied back", "attributes": "light blue button-down shirt, white top, earrings" }, "SCENE_1" ], "visual_description": "[PERSON_3] is shown hiding under a desk in [SCENE_1], looking worried and whispering to herself.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.0, 4.0 ], "references": [ { "ref_id": "PERSON_4", "type": "person", "id_features": "Young man with short dark hair", "attributes": "light blue jacket, white t-shirt, beige pants, watch" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A black smartphone displaying a dial pad" }, "SCENE_1" ], "visual_description": "[PERSON_4] is squatting on the floor in [SCENE_1], holding [OBJECT_1] in his hands and looking at the screen.", "camera": { "shot_type": "medium shot", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.0, 5.0 ], "references": [ "PERSON_4", "OBJECT_1" ], "visual_description": "A close-up of [OBJECT_1] held by [PERSON_4]. The screen shows a dial pad with a phone number entered. [PERSON_4]'s finger presses the green call button.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1", "SFX_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Tense, suspenseful background music." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.7, 1.8 ], "content": { "speaker": "PERSON_3", "line": "糟了", "description": "Whispered in a panicked tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 4.0, 5.0 ], "content": { "description": "A beep sound from the phone as the call button is pressed." } } ], "scene_description": "In an office setting, a boss and his assistant enter looking for someone. Two employees are shown hiding under desks, with one of them nervously dialing a number on his phone.", "global_style": "Dramatic and suspenseful, with cool, slightly desaturated lighting typical of a tense office drama.", "global_audio": "The audio consists of tense background music, a whispered line of dialogue, and a phone sound effect." } }, { "dataset": "drama_03", "clip_id": "clip_28571", "media_path": "drama_03/clip_28571.mp4", "source_media_path": "clips/clip_28571.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young girl with large eyes, wearing a peach and white traditional Chinese dress with floral patterns and a bell accessory", "attributes": "Black hair styled in double buns with floral hairpins, peach and white Hanfu, pink shoes with pearl decorations, white socks with bow patterns" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A simple, dark wooden stool" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden furniture, including a desk, a stool, and a bookshelf filled with books. Warm, soft lighting" } ], "visual_description": "[PERSON_1] sits down on [OBJECT_1] in [SCENE_1]. She looks slightly downwards.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1", "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.8, 3.7 ], "references": [ "PERSON_1" ], "visual_description": "A close-up view of [PERSON_1]'s feet, showing her pink shoes and white socks. The pearl hem of her dress is visible above.", "camera": { "shot_type": "Close-up", "angle": "Low angle", "movement": "Static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.7, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A person whose lower half is visible, wearing a white robe with a patterned belt", "attributes": "White robe, patterned belt with a metal buckle" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A polished wooden desk" }, "SCENE_1" ], "visual_description": "[PERSON_2] walks into the frame and stands near [OBJECT_2]. Only the lower half of [PERSON_2] is visible.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1", "SFX_2" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Gentle, traditional instrumental background music." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 1.0 ], "content": { "description": "A soft jingling sound of a bell." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 3.5, 5.0 ], "content": { "description": "Footsteps walking on a wooden floor." } } ], "scene_description": "A little girl in traditional attire sits on a stool, followed by a person in a white robe entering the room.", "global_style": "3D animation, traditional Chinese aesthetic, warm and soft lighting.", "global_audio": "Gentle traditional instrumental music." } }, { "dataset": "drama_03", "clip_id": "clip_10014", "media_path": "drama_03/clip_10014.mp4", "source_media_path": "clips/clip_10014.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, dark eyes, and long black hair styled in twin braids", "attributes": "Wearing a light green traditional-style top with white lace detailing, panda motifs, and a black beaded necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair and fair skin", "attributes": "Wearing a light blue collared shirt with silver star-shaped pins on the collar points, and a matching tie" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit indoor environment with blurred background elements suggesting a furnished room" } ], "visual_description": "[PERSON_1] is in sharp focus in the foreground, looking slightly downwards with a concerned expression. She then begins to speak. [PERSON_2] is visible in the background, out of focus.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.5, 4.7 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "The camera cuts to [PERSON_2], who is now in sharp focus. He has his arms crossed and is looking towards [PERSON_1] with a serious expression, listening to her.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 5.0 ], "content": { "description": "Tense, dramatic instrumental background music." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 3.1, 3.9 ], "content": { "speaker": "PERSON_1", "line": "但我不知道是哪一个", "description": "Uncertain and slightly anxious tone." } } ], "scene_description": "A tense moment between a young woman and a young man, where the woman expresses uncertainty about something.", "global_style": "Cinematic with shallow depth of field, focusing on character expressions, warm color grading.", "global_audio": "Dramatic instrumental music setting a serious mood." } }, { "dataset": "drama_03", "clip_id": "clip_24523", "media_path": "drama_03/clip_24523.mp4", "source_media_path": "clips/clip_24523.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, wearing a red traditional dress with blue and gold embroidery. She has a red mark on her forehead and wears a colorful beaded necklace", "attributes": "Red traditional wedding dress, elaborate gold hair accessories, red forehead mark, beaded necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room decorated in rich red tones, featuring a bed with red linens and traditional patterns" } ], "visual_description": "[PERSON_1] is lying down on a red bed in [SCENE_1], looking upwards and speaking.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.4, 4.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with a serious expression, wearing a red traditional robe with gold patterns. His hair is styled up with a gold crown", "attributes": "Red traditional robe, gold crown hairpiece" }, "SCENE_1" ], "visual_description": "[PERSON_2] is looking downwards with a serious expression in [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.1, 2.6 ], "content": { "speaker": "PERSON_1", "line": "久闻狮子殿下武艺高强", "description": "Playful but calm statement." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.6, 4.1 ], "content": { "speaker": "PERSON_1", "line": "久战沙场", "description": "Continuing the statement with a steady tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.1, 4.5 ], "content": { "speaker": "PERSON_1", "line": "没忍住", "description": "Admitting her action with a hint of mischief." } } ], "scene_description": "In a traditional Chinese wedding bedchamber, a bride lies on the bed and playfully admits to her groom that she tested his martial arts skills because of his formidable reputation.", "global_style": "Historical Chinese drama with a rich red color palette and a romantic, slightly tense atmosphere.", "global_audio": "Quiet ambient background with clear, close-mic dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_11982", "media_path": "drama_03/clip_11982.mp4", "source_media_path": "clips/clip_11982.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with fair skin, wearing a red robe with gold shoulder armor, and a black headpiece with red tassels", "attributes": "red robe, gold shoulder armor, black headpiece, red tassels, long black hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden furniture, lit candles on a stand, and a bonsai tree with yellow flowers" } ], "visual_description": "[PERSON_1] is seated at a wooden table in [SCENE_1]. He is looking slightly to the right, speaking with a serious expression. His right hand rests on the table.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.5, 4.0 ], "content": { "speaker": "PERSON_1", "line": "求神还三拜九叩", "description": "Speaking with a calm but authoritative tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.0, 4.3 ], "content": { "speaker": "PERSON_1", "line": "赵福桑", "description": "Calling out a name." } } ], "scene_description": "A man in traditional Chinese clothing sits in a candlelit room and speaks.", "global_style": "Historical drama, traditional Chinese aesthetic, warm lighting.", "global_audio": "Quiet ambient sound with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_12751", "media_path": "drama_03/clip_12751.mp4", "source_media_path": "clips/clip_12751.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with pale skin, long black hair, and striking facial features", "attributes": "Elaborate golden crown with blue jewels, iridescent pastel dress with butterfly and fairy motifs, delicate necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A courtyard or open space filled with a crowd of onlookers dressed in traditional or fantasy attire" } ], "visual_description": "[PERSON_1] stands confidently in [SCENE_1], speaking with a determined expression while a crowd watches from behind.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.2, 6.2 ], "references": [ "PERSON_1", { "ref_id": "SCENE_2", "type": "scene", "id_features": "Dark, swirling clouds illuminated by fiery red lightning and glowing energy" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A massive, dark, textured hand with sharp claws reaching down from the clouds" } ], "visual_description": "[PERSON_1] levitates above a glowing magic circle, then transforms into a massive pillar of golden fire, shooting upwards into [SCENE_2] towards [OBJECT_1].", "camera": { "shot_type": "wide shot", "angle": "low angle", "movement": "tilt up" }, "active_events": [ "SFX_1", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.2, 7.4 ], "references": [ "PERSON_1", "OBJECT_1", "SCENE_2" ], "visual_description": "A wider view reveals [OBJECT_1] reaching down from the sky towards [PERSON_1], who is now hovering above a platform, appearing small in comparison to the giant hand.", "camera": { "shot_type": "extreme wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_2", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 2.1 ], "content": { "speaker": "PERSON_1", "line": "老娘去会会这所谓的魔神", "description": "Confident and defiant declaration." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.5, 6.0 ], "content": { "description": "Roaring fire and a powerful magical whoosh." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 6.0, 8.0 ], "content": { "description": "Deep, ominous rumbling." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 8.0 ], "content": { "description": "Epic, dramatic orchestral background music." } } ], "scene_description": "A powerful female character boldly confronts a massive demonic entity in the sky, ascending as a pillar of fire to meet it.", "global_style": "High fantasy, CGI animation, epic, dramatic, visually spectacular.", "global_audio": "Epic orchestral music accompanied by intense magical and environmental sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_18916", "media_path": "drama_03/clip_18916.mp4", "source_media_path": "clips/clip_18916.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with short black hair, fair skin, and a serious expression", "attributes": "Wearing a grey blazer over an unbuttoned white shirt, dark trousers, and a wristwatch. A white bandage is taped to his stomach" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with long black hair, seen mostly from the back and side profile", "attributes": "Wearing a light-colored cardigan" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with low lighting, featuring a light-colored sofa" } ], "visual_description": "[PERSON_2] rests her hand on [PERSON_1]'s exposed chest. [PERSON_1] looks down and begins to button his white shirt, covering the bandage on his abdomen. As [PERSON_2] speaks, [PERSON_1] pauses his action and looks up at her with a slightly surprised expression.", "camera": { "shot_type": "medium_shot", "angle": "eye_level", "movement": "static" }, "active_events": [ "EVENT_1", "EVENT_2" ] } ], "events": [ { "event_id": "EVENT_1", "type": "sfx", "time_range": [ 0.5, 1.5 ], "content": { "description": "A soft sigh or exhalation." } }, { "event_id": "EVENT_2", "type": "dialogue", "time_range": [ 3.0, 3.9 ], "content": { "speaker": "PERSON_2", "line": "你能让我拍张照吗", "description": "Asking a question in a calm, slightly hesitant tone." } } ], "scene_description": "In a dimly lit room, a woman asks to take a picture of a man as he buttons his shirt over a bandaged wound.", "global_style": "Modern drama, intimate and slightly tense atmosphere with low-key lighting.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_20700", "media_path": "drama_03/clip_20700.mp4", "source_media_path": "clips/clip_20700.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man wearing a dark blue and green robe with gold embroidery, with his hair tied up using a silver ornament", "attributes": "dark blue and green robe, gold embroidery, silver hair ornament, black hair" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A man wearing a dark purple robe with intricate black and silver patterns, and a dark, ornate crown", "attributes": "dark purple robe, intricate patterns, dark ornate crown, long black hair" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "An older man with white hair, wearing a white robe and a white headpiece", "attributes": "white robe, white hair, white headpiece" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman wearing a light blue and white dress with long black hair", "attributes": "light blue and white dress, long black hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A stone-paved courtyard with a circular pattern on the ground, large stone stairs in the background, and a massive bronze cauldron", "attributes": "stone paving, circular ground pattern, stone stairs, bronze cauldron" } ], "visual_description": "In [SCENE_1], [PERSON_1] is kneeling on the ground, facing [PERSON_3] who is seated in the center. [PERSON_2] is seated to the left, and [PERSON_4] is standing to the right, all looking towards [PERSON_1].", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.1, 5.8 ], "references": [ "PERSON_1", "PERSON_4" ], "visual_description": "[PERSON_1] bows down deeply, touching his forehead to the ground. The lower part of [PERSON_4]'s dress is visible in the background.", "camera": { "shot_type": "medium shot", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.8, 8.0 ], "references": [ "PERSON_2" ], "visual_description": "[PERSON_2] is seated with his eyes closed, looking solemn and contemplative.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 6.2 ], "content": { "speaker": "PERSON_1", "line": "师尊师尊你信我我真的从未想过要害小师妹性命真的没有求你信我这一次", "description": "Desperate and emotional pleading." } } ], "scene_description": "A disciple kneels before his master and peers, desperately pleading his innocence against accusations of attempting to harm his junior martial sister.", "global_style": "Chinese fantasy xianxia drama with elaborate historical costumes and grand architectural settings.", "global_audio": "Emotional dialogue accompanied by subtle, dramatic background music." } }, { "dataset": "drama_03", "clip_id": "clip_31150", "media_path": "drama_03/clip_31150.mp4", "source_media_path": "clips/clip_31150.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Older male with short black hair", "attributes": "White long-sleeve shirt, grey button-up vest, purple patterned tie, wristwatch, grey trousers" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Modern interior with a white sofa, dark marble table, and light marble accent wall" } ], "visual_description": "[PERSON_1] is sitting on a white sofa in [SCENE_1], looking up towards the right side of the frame. He speaks with an angry expression and points his right index finger forward.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.0, 4.9 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Younger male with short black hair", "attributes": "Brown double-breasted suit jacket, black turtleneck sweater, brown trousers" }, "SCENE_1" ], "visual_description": "[PERSON_2] stands in [SCENE_1], facing left and looking down with a distressed and confused expression while speaking.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.9, 5.7 ], "references": [ "PERSON_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A feather duster with brown and white feathers and a green and red handle" }, "SCENE_1" ], "visual_description": "The right hand of [PERSON_1] quickly grabs [OBJECT_1] from a dark marble table.", "camera": { "shot_type": "Close-up", "angle": "High angle", "movement": "Static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 3.2 ], "content": { "speaker": "PERSON_1", "line": "你问我你和苏慕选怎么在一起的", "description": "Angry and accusatory tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.2, 4.6 ], "content": { "speaker": "PERSON_2", "line": "爸我失忆了", "description": "Confused and defensive tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 4.0, 5.0 ], "content": { "description": "Sound of an object being snatched from a hard surface." } } ], "scene_description": "A tense confrontation between a father and his son, where the father angrily questions the son about a relationship, and the son claims to have amnesia, prompting the father to grab a feather duster.", "global_style": "Modern drama with a tense and slightly comedic undertone.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_22838", "media_path": "drama_03/clip_22838.mp4", "source_media_path": "clips/clip_22838.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long black hair, wearing a light blue trench coat over a white top, and a silver necklace", "attributes": "clothing: Light blue trench coat, white top, hairstyle: Long black hair, accessories: Silver necklace, earrings" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A middle-aged woman with her hair tied back, wearing a brown blazer over a black turtleneck, and a pearl necklace", "attributes": "clothing: Brown blazer, black turtleneck, brown skirt, hairstyle: Hair tied back, accessories: Pearl necklace, earrings" } ], "visual_description": "[PERSON_1] is looking forward and speaking with a smile. The shoulder of [PERSON_2] is partially visible in the foreground.", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.7, 3.9 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "[PERSON_2] smiles, speaks, and then turns to walk away to the right. The shoulder of [PERSON_1] is partially visible in the foreground.", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Pan right" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.9, 5.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man with short black hair, wearing a beige and brown striped sweater", "attributes": "clothing: Beige and brown striped sweater, light green pants, hairstyle: Short black hair, accessories: None" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A modern office space with red walls, glass partitions, indoor plants, and a display shelf with books" }, "PERSON_2" ], "visual_description": "Viewed through a glass shelf with books, [PERSON_1] and [PERSON_3] are standing together in [SCENE_1], looking towards the direction where [PERSON_2] walked away.", "camera": { "shot_type": "Wide shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 2.4 ], "content": { "speaker": "PERSON_1", "line": "谢谢你上总监", "description": "Polite and grateful tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.4, 2.8 ], "content": { "speaker": "PERSON_2", "line": "我先走了", "description": "Casual and dismissive tone." } } ], "scene_description": "A brief interaction in an office where a young woman thanks a director, who then takes her leave.", "global_style": "Bright, modern corporate drama aesthetic.", "global_audio": "Clear dialogue with subtle ambient room noise." } }, { "dataset": "drama_03", "clip_id": "clip_12864", "media_path": "drama_03/clip_12864.mp4", "source_media_path": "clips/clip_12864.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.6 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, wearing a white veil that covers the lower half of her face", "attributes": "Light pink traditional dress, elaborate silver and pearl hair ornaments with dangling tassels" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with dark hair and a serious expression", "attributes": "Greyish-purple patterned robe with a high collar, dark hair tied up with a silver crown ornament" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit outdoor area with blurred architectural elements in the background" } ], "visual_description": "Viewed from over the shoulder of [PERSON_2], [PERSON_1] stands quietly, looking towards him in [SCENE_1].", "camera": { "shot_type": "Over-the-shoulder shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.6, 2.2 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] turns his head slightly, looking attentive as he hears a voice calling him.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.2, 4.2 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "PERSON_3", "type": "person", "id_features": "A pregnant woman whose face is mostly unseen, identified by her prominent belly", "attributes": "Purple dress with intricate floral embroidery and a decorative waist belt" }, "SCENE_1" ], "visual_description": "[PERSON_1] watches as [PERSON_3] walks into the frame from the right, passing between [PERSON_1] and [PERSON_2].", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.2, 5.0 ], "references": [ "PERSON_2", "PERSON_3" ], "visual_description": "[PERSON_2] places his hand gently and protectively on the pregnant belly of [PERSON_3].", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.9, 3.1 ], "content": { "speaker": "PERSON_3", "line": "将军", "description": "Calling out affectionately." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.7, 4.6 ], "content": { "speaker": "PERSON_2", "line": "你大着肚子不方便", "description": "Expressing care and concern." } } ], "scene_description": "A pregnant woman approaches a man addressed as General, interrupting a quiet moment between him and a veiled woman. The man shows tender concern for the pregnant woman.", "global_style": "Historical Chinese drama aesthetic with soft lighting, elegant traditional costumes, and a romantic, slightly melancholic tone.", "global_audio": "Soft, emotional background music playing throughout the scene." } }, { "dataset": "drama_03", "clip_id": "clip_20393", "media_path": "drama_03/clip_20393.mp4", "source_media_path": "clips/clip_20393.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, wearing formal attire", "attributes": "white tuxedo jacket with black lapels, white dress shirt, black bow tie, black trousers" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A red folder or document holder" } ], "visual_description": "[PERSON_1] is sitting and looking down intently at [OBJECT_2] in his hands.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 4.9 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long wavy brown hair, wearing glasses and a black dress", "attributes": "glasses, black long-sleeved mini dress with lace sleeves and a chest cutout, earrings, watch" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious room with high ceilings, large windows showing greenery outside, white walls, a white sofa, a marble coffee table with flowers, and a modern armchair" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A clear drinking glass filled with a dark liquid" }, "OBJECT_2" ], "visual_description": "In [SCENE_1], [PERSON_1] is seated in an armchair holding [OBJECT_2]. [PERSON_2] stands up from a squatting position near the coffee table, picks up [OBJECT_1], and walks over to [PERSON_1].", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.9, 7.0 ], "references": [ "PERSON_1", "PERSON_2", "OBJECT_1" ], "visual_description": "[PERSON_2] stands in front of [PERSON_1] and offers him [OBJECT_1]. The hand of [PERSON_1] reaches up and takes [OBJECT_1] from her.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "tilt down" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 7.0 ], "content": { "description": "Upbeat, slightly comedic instrumental background music." } } ], "scene_description": "A woman in a black dress brings a glass of dark liquid to a man in a white tuxedo who is reviewing a document in a modern living room.", "global_style": "Bright, modern, and polished.", "global_audio": "Upbeat instrumental music plays throughout the scene." } }, { "dataset": "drama_03", "clip_id": "clip_4744", "media_path": "drama_03/clip_4744.mp4", "source_media_path": "clips/clip_4744.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with black hair tied back, wearing pearl earrings and a grey textured top", "attributes": "clothing: grey textured top, hairstyle: black hair tied back, accessories: pearl earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor environment with a plain wall and curtains in the background" } ], "visual_description": "[PERSON_1] looks off-screen with a concerned and slightly confused expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.5, 4.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short hair and a beard, wearing a brown leather jacket over a patterned shirt and a gold chain", "attributes": "clothing: brown leather jacket, patterned shirt, hairstyle: short hair, beard, accessories: gold chain" }, "SCENE_1" ], "visual_description": "[PERSON_2] looks off-screen and speaks with a serious expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.1, 2.7 ], "content": { "speaker": "PERSON_2", "line": "什么高利贷", "description": "Defensive tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.7, 4.0 ], "content": { "speaker": "PERSON_2", "line": "我们可是正规公司", "description": "Assertive tone." } } ], "scene_description": "A man defends his company's legitimacy to a concerned woman.", "global_style": "Realistic, dramatic lighting.", "global_audio": "Quiet indoor ambience." } }, { "dataset": "drama_03", "clip_id": "clip_23236", "media_path": "drama_03/clip_23236.mp4", "source_media_path": "clips/clip_23236.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with an authoritative demeanor, wearing traditional attire", "attributes": "Pink and purple traditional dress, elaborate gold headpiece, hair styled up" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with a serious, slightly downcast expression", "attributes": "Pink traditional dress with red accents, gold hair accessories, red mark on her forehead" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An ornate room with elaborate decorations", "attributes": "Large golden dragon reliefs carved into the wall behind a dark wooden desk" } ], "visual_description": "[PERSON_1] is seated at a desk in [SCENE_1], speaking with an authoritative expression. The back of [PERSON_2] is visible in the blurred foreground.", "camera": { "shot_type": "medium_shot", "angle": "eye_level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.3, 3.4 ], "references": [ "PERSON_2" ], "visual_description": "A close-up of [PERSON_2] looking slightly downwards with a serious expression while listening.", "camera": { "shot_type": "close_up", "angle": "eye_level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.4, 5.7 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "An older man with a beard, appearing respectful but firm", "attributes": "Dark armor with prominent gold dragon motifs, hair tied up in a topknot" } ], "visual_description": "[PERSON_3] stands in the hall, looking forward and speaking respectfully.", "camera": { "shot_type": "medium_shot", "angle": "eye_level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 3.3 ], "content": { "speaker": "PERSON_1", "line": "长宁郡主,岂是你可以随意污蔑的吗", "description": "Stern and authoritative reprimand." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.5, 5.3 ], "content": { "speaker": "PERSON_3", "line": "不敢妄言", "description": "Respectful but firm response." } } ], "scene_description": "A tense confrontation in a grand hall where a noblewoman reprimands a military officer for alleged slander, to which he respectfully defends his words.", "global_style": "Historical Chinese costume drama with rich, ornate set designs and elaborate traditional clothing.", "global_audio": "Clear dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_17049", "media_path": "drama_03/clip_17049.mp4", "source_media_path": "clips/clip_17049.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, styled neatly", "attributes": "Wearing a dark grey three-piece suit, a white dress shirt, and a dark patterned tie" } ], "visual_description": "[PERSON_1] looks forward, speaks, and then turns to his right, preparing to walk away.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 2.1 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long dark hair", "attributes": "Wearing a light blue long-sleeved button-down shirt and a white skirt" } ], "visual_description": "The hands of [PERSON_2] reach out and grab the arm of [PERSON_1], stopping his movement.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.1, 3.8 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A modern interior with large windows letting in bright sunlight, creating a strong backlight", "attributes": "Brightly lit, modern architecture" } ], "visual_description": "[PERSON_1] stops walking and stands still as [PERSON_2] holds onto his arm. They are standing in [SCENE_1] with bright sunlight streaming in from the windows behind them.", "camera": { "shot_type": "medium shot", "angle": "low angle", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 3.8, 6.0 ], "references": [ "PERSON_1" ], "visual_description": "A profile view of [PERSON_1]'s face. He looks down slightly, then raises his eyes as he listens.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 1.8 ], "content": { "speaker": "PERSON_1", "line": "我来买", "description": "Assertive and decisive tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.8, 4.6 ], "content": { "speaker": "PERSON_2", "line": "等一下", "description": "Urgent and slightly panicked tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.6, 5.8 ], "content": { "speaker": "PERSON_2", "line": "我爸妈就在那边坐着", "description": "Explanatory and anxious tone." } } ], "scene_description": "A man offers to pay the bill and attempts to leave, but a woman urgently grabs his arm to stop him, explaining that her parents are sitting nearby.", "global_style": "Modern urban drama with cinematic lighting, featuring shallow depth of field and strong backlighting.", "global_audio": "Quiet ambient background with clear, prominent dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_28606", "media_path": "drama_03/clip_28606.mp4", "source_media_path": "clips/clip_28606.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A pale hand with visible knuckles" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A small, round, metallic-looking object, possibly a coin or token" } ], "visual_description": "An extreme close-up focuses on [PERSON_1]'s hand holding and manipulating [OBJECT_1] in dim, cool-toned lighting.", "camera": { "shot_type": "extreme close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 3.4 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A 3D animated young girl with large brown eyes, black hair with straight bangs, and a fair complexion", "attributes": "traditional orange and peach dress, floral hair accessories" } ], "visual_description": "A close-up reveals the face of [PERSON_2], who has a slightly surprised and attentive expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "slight zoom in" }, "active_events": [ "SFX_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.4, 6.3 ], "references": [ "PERSON_2" ], "visual_description": "An extreme close-up shows the ear of [PERSON_2].", "camera": { "shot_type": "extreme close-up", "angle": "side", "movement": "static" }, "active_events": [ "SFX_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 6.3, 8.0 ], "references": [ "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A traditional Chinese-style building with wooden doors, a tiled roof, and a stone ledge" } ], "visual_description": "A wider shot shows [PERSON_2] sitting on a ledge outside [SCENE_1]. She has her hands clasped together and is looking down thoughtfully.", "camera": { "shot_type": "full shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 3.0 ], "content": { "description": "Metallic clinking sound of a small object being handled." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 3.0, 6.0 ], "content": { "description": "A subtle, low-frequency ambient transition sound." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 6.6, 7.7 ], "content": { "speaker": "PERSON_2", "line": "好多人在挨", "description": "A young girl's voice speaking with a tone of concern and sadness." } } ], "scene_description": "A mysterious hand handles a small object, followed by a transition to a young animated girl who appears to be listening intently before expressing concern about people starving.", "global_style": "High-quality 3D animation with a mix of dark, moody lighting in the beginning and warm, natural lighting in the later scene.", "global_audio": "Quiet ambient sounds punctuated by specific sound effects and a single line of dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_19598", "media_path": "drama_03/clip_19598.mp4", "source_media_path": "clips/clip_19598.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A plump man with a mustache and goatee, wearing his hair in a topknot secured with a gold pin", "attributes": "Red robe with floral patterns, large green gemstone ring on his right hand" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with wooden lattice windows and red pillars, typical of ancient Chinese architecture" } ], "visual_description": "[PERSON_1] is standing in [SCENE_1]. He gestures with his right hand while speaking, then clasps his hands together with a smug, laughing expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 4.3 ], "content": { "speaker": "PERSON_1", "line": "不用咱们动手灾民们自己就会闹起来到时候", "description": "Confident, scheming, and slightly mocking tone." } } ], "scene_description": "A man in traditional Chinese attire confidently explains a scheme, anticipating that refugees will cause trouble without his direct involvement.", "global_style": "3D animation with a historical Chinese aesthetic, featuring realistic lighting and detailed character design.", "global_audio": "Clear spoken dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_23154", "media_path": "drama_03/clip_23154.mp4", "source_media_path": "clips/clip_23154.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with fair skin, wearing an elaborate gold headdress adorned with pearls and red beads, and pearl drop earrings", "attributes": "clothing: Red patterned robe with a thick brown fur collar., hairstyle: Updo with elaborate hairpins and a large gold crown-like headdress., accessories: Gold headdress with pearls and red beads, pearl earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden lattice doors or windows in the background, slightly out of focus" } ], "visual_description": "[PERSON_1] is shown in a medium close-up, looking slightly off-camera with an angry and resentful expression as she speaks. The background [SCENE_1] is blurred.", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.1, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man wearing a traditional official's hat and a purple robe", "attributes": "clothing: Purple robe with intricate embroidery on the front., hairstyle: Concealed under the hat., accessories: Black hat with a gold emblem on the front" }, "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_2] is shown in a medium close-up, looking towards [PERSON_1] (off-screen) with a serious and reassuring expression as he speaks. The edge of [PERSON_1]'s fur collar is visible on the left side of the frame.", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 4.4 ], "content": { "speaker": "PERSON_1", "line": "好一个长宁郡主竟偏要和本宫对着干", "description": "Angry and resentful tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.4, 5.0 ], "content": { "speaker": "PERSON_2", "line": "娘娘放心", "description": "Reassuring and respectful tone." } } ], "scene_description": "A scene from a historical Chinese drama where a noblewoman expresses her anger towards a rival, and her subordinate reassures her.", "global_style": "Historical Chinese drama, rich colors, traditional costumes, soft lighting.", "global_audio": "Clear dialogue with no prominent background music." } }, { "dataset": "drama_03", "clip_id": "clip_4083", "media_path": "drama_03/clip_4083.mp4", "source_media_path": "clips/clip_4083.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair", "attributes": "Wearing a black silk robe with gold piping and an 'M' embroidered on the pocket" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long, wavy dark hair", "attributes": "Wearing a deep red silk robe" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A bedroom with warm, ambient lighting, featuring a bed with a beige quilted blanket and a modern wall sconce" } ], "visual_description": "[PERSON_1] and [PERSON_2] are sitting on a bed in [SCENE_1]. [PERSON_1] points a finger at [PERSON_2] while speaking to her.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.8, 3.2 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "A close-up of [PERSON_2] looking down thoughtfully, then speaking with a serious and slightly emotional expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.2, 5.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "A close-up of [PERSON_1] looking surprised and slightly confused as he listens to [PERSON_2], whose shoulder is visible in the foreground.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 1.0 ], "content": { "speaker": "PERSON_1", "line": "你知道错了没有", "description": "Accusing and confrontational tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.0, 2.0 ], "content": { "speaker": "PERSON_2", "line": "真的假的", "description": "Disbelieving and quiet tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.0, 3.0 ], "content": { "speaker": "PERSON_2", "line": "七年啊", "description": "Emotional and reflective tone." } } ], "scene_description": "A tense and emotional conversation between a man and a woman sitting in bed, where the man accuses the woman, and she responds with disbelief about the length of their relationship.", "global_style": "Dramatic, intimate, with warm and moody lighting.", "global_audio": "Quiet room ambiance with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_13196", "media_path": "drama_03/clip_13196.mp4", "source_media_path": "clips/clip_13196.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "An older woman with grey hair styled in a bun, wearing a light beige traditional-style long-sleeved shirt with frog buttons, and grey striped trousers", "attributes": "clothing: Light beige traditional-style shirt, grey striped trousers, hairstyle: Grey hair in a bun, accessories: Hair stick" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A gathering area with round tables covered in bright red tablecloths. There are glasses containing yellow liquid and chopsticks on the tables. Other attendees are visible in the background" } ], "visual_description": "[PERSON_1] is sitting at a table in [SCENE_1]. She looks shocked and speaks animatedly, gesturing with her right hand while her left hand rests on her lap. She leans slightly forward as she talks.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 2.3 ], "content": { "speaker": "PERSON_1", "line": "我的天造孽啊", "description": "Exclaiming in shock and dismay." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.3, 3.3 ], "content": { "speaker": "PERSON_1", "line": "这孩子看着老", "description": "Speaking with a tone of disbelief." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.7, 4.6 ], "content": { "speaker": "PERSON_1", "line": "怎么干出这种事", "description": "Questioning with disappointment and confusion." } } ], "scene_description": "An older woman sitting at a banquet table expresses shock and disappointment about someone's unexpected actions.", "global_style": "Realistic, bright outdoor daytime lighting, casual social setting.", "global_audio": "Ambient background noise of a gathering with people talking." } }, { "dataset": "drama_03", "clip_id": "clip_22373", "media_path": "drama_03/clip_22373.mp4", "source_media_path": "clips/clip_22373.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A middle-aged man with a goatee and mustache, wearing a black cloak and a decorative metallic headpiece", "attributes": "Black cloak, decorative headpiece, facial hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit outdoor area with architectural elements visible in the background" } ], "visual_description": "[PERSON_1] is seen speaking with a confident expression in [SCENE_1].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.3, 3.9 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with his hair tied up in a topknot with a hairpiece, wearing a dark patterned robe with red accents", "attributes": "Dark patterned robe, red accents, hair tied up, hairpiece" } ], "visual_description": "A close-up of [PERSON_2]'s hand clenching tightly into a fist.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.9, 4.7 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] turns his head slightly, smirking as he speaks in [SCENE_1].", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.8, 1.7 ], "content": { "speaker": "PERSON_1", "line": "南玉做东", "description": "Confident and ambitious tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.5, 3.0 ], "content": { "description": "Sound of a hand clenching into a fist, leather creaking." } } ], "scene_description": "Two men are having a tense conversation, with one expressing grand ambitions and the other reacting with sarcastic amusement.", "global_style": "Historical Chinese drama with dark, moody lighting.", "global_audio": "Quiet ambient background with clear dialogue and distinct sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_13904", "media_path": "drama_03/clip_13904.mp4", "source_media_path": "clips/clip_13904.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, large eyes, and red makeup around her eyes and cheeks", "attributes": "Wearing a traditional Chinese dress in pastel pink, yellow, and light blue. Her hair is styled in an elaborate updo adorned with gold hairpins, dangling pearls, and a large pink flower" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A courtyard or pavilion with traditional architecture, featuring a bridge and buildings in the background, and floral decorations indoors" } ], "visual_description": "[PERSON_1] is kneeling on the floor in [SCENE_1], looking upwards with a shocked, fearful, and pleading expression.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 1.1, 3.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with sharp facial features, dark eyebrows, and a stern expression", "attributes": "Wearing dark armor with gold dragon scale patterns on the shoulders and a red sash across his chest. His long dark hair is partially tied up in a topknot" }, "SCENE_1" ], "visual_description": "[PERSON_2] stands with a stern and commanding posture, looking slightly downwards as he speaks.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.2, 5.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] is shown again, but her expression has drastically changed to a wide, maniacal smile as she speaks defiantly.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.6, 4.0 ], "content": { "speaker": "PERSON_2", "line": "来人拖下去打入天牢", "description": "Authoritative and cold command." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.0, 4.7 ], "content": { "speaker": "PERSON_1", "line": "成王败寇", "description": "Maniacal and defiant statement." } } ], "scene_description": "A dramatic confrontation in an ancient palace where a man orders a kneeling woman to be imprisoned, prompting her to react with a crazed, defiant laugh.", "global_style": "3D animated fantasy with a historical Chinese aesthetic, featuring detailed character models and vibrant lighting.", "global_audio": "Dramatic dialogue with no prominent background music." } }, { "dataset": "drama_03", "clip_id": "clip_9144", "media_path": "drama_03/clip_9144.mp4", "source_media_path": "clips/clip_9144.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark, slightly messy hair, wearing a dark suit", "attributes": "Black suit jacket, black shirt, brown patterned tie" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit indoor space with a notice board or framed document on the wall in the background" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with her hair tied back, wearing a light blue uniform", "attributes": "Light blue medical or nurse uniform with a collar, a name tag on the left chest, and a logo patch" } ], "visual_description": "[PERSON_1] is shown from the chest up, looking slightly off-camera towards [PERSON_2]. He has a slight, confident smile on his face as he speaks. The background [SCENE_1] is out of focus.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.2, 5.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], shown from the chest up. She is looking intently at [PERSON_1], who is now off-camera but whose shoulder is visible in the foreground. She maintains a serious, unwavering expression.", "camera": { "shot_type": "Over-the-shoulder shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 1.8 ], "content": { "speaker": "PERSON_1", "line": "好啊", "description": "Confident and slightly mocking tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.8, 3.4 ], "content": { "speaker": "PERSON_1", "line": "既然你這麼想玩", "description": "Challenging tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.4, 4.0 ], "content": { "speaker": "PERSON_1", "line": "我陪你玩", "description": "Threatening and assertive tone." } } ], "scene_description": "A tense confrontation between a man in a suit and a woman in a medical uniform, where the man accepts a challenge.", "global_style": "Dramatic lighting with cool tones, creating a serious and slightly ominous atmosphere.", "global_audio": "Quiet ambient room noise with clear, prominent dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_3067", "media_path": "drama_03/clip_3067.mp4", "source_media_path": "clips/clip_3067.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark hair, lying unconscious or asleep", "attributes": "Bare-chested, covered with a patterned blanket" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring a wooden bed frame with blue curtains and traditional decor" } ], "visual_description": "[PERSON_1] is lying asleep in [SCENE_1], covered by a blanket.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with dark hair styled in braids", "attributes": "Wearing a traditional white outfit, holding a folded red garment" }, "SCENE_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A piece of bright red clothing, folded and held by the woman" } ], "visual_description": "[PERSON_2] is standing in [SCENE_1], holding [OBJECT_1] and looking towards the camera while speaking.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 3.2 ], "content": { "speaker": "PERSON_2", "line": "希望国公爷以后", "description": "Sincere and slightly melancholic tone." } } ], "scene_description": "A woman stands in a traditional bedroom, holding a red garment, and expresses her good wishes for the future to a man sleeping in the bed.", "global_style": "Traditional Chinese historical drama aesthetic with soft lighting.", "global_audio": "Quiet room ambience with clear spoken dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_10572", "media_path": "drama_03/clip_10572.mp4", "source_media_path": "clips/clip_10572.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man wearing a bright red robe, sitting cross-legged on the ground", "attributes": "Bright red robe, hair tied up" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A traditional wooden stringed instrument, likely a guqin" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dirt clearing in front of a massive, closed wooden gate with metal studs" } ], "visual_description": "[PERSON_1] sits on the ground playing [OBJECT_1] in front of a large gate in [SCENE_1]. Soldiers with spears stand in the blurred foreground.", "camera": { "shot_type": "long shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.3, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with long hair, wearing dark armor with shoulder pads and a long dark cape", "attributes": "Dark armor, long hair, dark cape" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A person kneeling, wearing a dark patterned tunic over red clothing", "attributes": "Dark patterned tunic, red undergarments" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A dimly lit room with a large window, a desk with objects on it, dark curtains, and a patterned rug" } ], "visual_description": "In [SCENE_2], [PERSON_2] stands behind a desk while [PERSON_3] kneels on a rug before him. [PERSON_2] turns around, his cape swishing, and looks down at [PERSON_3].", "camera": { "shot_type": "medium full shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "SFX_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.0, 5.0 ], "content": { "description": "Fabric swishing, footsteps, and heavy breathing" } } ], "scene_description": "A transition from a man playing an instrument outside a fortress gate to a commander inside a room reacting to a kneeling subordinate.", "global_style": "Historical drama, cinematic lighting, muted color palette.", "global_audio": "Vocal grunts and foley sounds of movement." } }, { "dataset": "drama_03", "clip_id": "clip_15154", "media_path": "drama_03/clip_15154.mp4", "source_media_path": "clips/clip_15154.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, a slight cut on his lip, wearing a blue denim jacket over a black shirt", "attributes": "blue denim jacket, black shirt, short black hair, cut on lip" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Partially visible person, back to the camera, wearing dark clothing", "attributes": "dark clothing" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A hallway with a wooden door bearing the number '1802' and a wall sconce" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], pointing his finger aggressively at [PERSON_2]. He has a fierce expression and appears to be yelling. He holds his other arm near his chest.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 2.8, 4.5 ], "content": { "speaker": "PERSON_1", "line": "能让你们从江市消失", "description": "Angry and threatening tone." } } ], "scene_description": "A tense confrontation in a hallway where a man threatens another person.", "global_style": "Dramatic, slightly dark lighting.", "global_audio": "Dialogue with no prominent background music." } }, { "dataset": "drama_03", "clip_id": "clip_20969", "media_path": "drama_03/clip_20969.mp4", "source_media_path": "clips/clip_20969.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long black hair, wearing makeup", "attributes": "black jacket, black top with pearl buttons, pearl necklace, silver hoop earrings" } ], "visual_description": "[PERSON_1] stands with her arms crossed, looking off-camera to the right with a slightly annoyed and impatient expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 0.9, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short dark hair, seen primarily from behind", "attributes": "dark green suit jacket, dark pants, dark shoes with light soles" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An interior space featuring a dark brown wooden door with a black handle" } ], "visual_description": "Viewed from behind, [PERSON_2] is pushing against a dark brown door in [SCENE_1] with both hands spread wide. He suddenly drops to his knees while still keeping his hands pressed against the door.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_1", "DIALOGUE_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.0, 2.0 ], "content": { "description": "Sound of a door being pushed or hitting a frame." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 3.0, 4.0 ], "content": { "speaker": "PERSON_2", "line": "哎呦", "description": "An exclamation of pain, surprise, or exertion." } } ], "scene_description": "A woman displays an annoyed expression, followed by a man who appears to be struggling to keep a door closed before falling to his knees in exhaustion or defeat.", "global_style": "Modern indoor setting with soft, slightly dramatic lighting.", "global_audio": "Quiet ambient background with a distinct physical impact sound and a vocal exclamation." } }, { "dataset": "drama_03", "clip_id": "clip_8097", "media_path": "drama_03/clip_8097.mp4", "source_media_path": "clips/clip_8097.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Middle-aged man with short black hair, wearing a black suit, black shirt, and a patterned tie", "attributes": "black suit, black shirt, patterned tie, short black hair" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A smartphone with a gold-colored casing" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring a bright yellow, possibly fabric, backdrop" } ], "visual_description": "[PERSON_1] is standing in [SCENE_1], looking down intently at [OBJECT_1] held in both hands.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.5, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Young woman with long black hair tied back, wearing a grey top, red and white striped tie, black blazer, and red leather skirt", "attributes": "grey top, red and white striped tie, black blazer, red leather skirt, long black hair" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A smartphone with a black casing" }, { "ref_id": "OBJECT_3", "type": "object", "id_features": "A smartphone enclosed in a transparent protective case" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A room with blurred background elements and a hint of green lighting" } ], "visual_description": "[PERSON_2] is standing in [SCENE_2], holding [OBJECT_2] in her right hand and [OBJECT_3] in her left hand. She looks down at the phones with a slight smile.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_2" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.0, 2.0 ], "content": { "description": "A digital notification chime." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 3.0, 4.0 ], "content": { "description": "A digital notification chime." } } ], "scene_description": "A man and a woman are shown in separate locations, both checking their smartphones and receiving notifications.", "global_style": "Modern, well-lit indoor settings with distinct color palettes for each character.", "global_audio": "Quiet background with distinct digital notification sounds." } }, { "dataset": "drama_03", "clip_id": "clip_347", "media_path": "drama_03/clip_347.mp4", "source_media_path": "clips/clip_347.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.6 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Young man with dark hair, thick eyebrows, and large eyes", "attributes": "Wearing a white robe with a dark belt and a small hairpiece" } ], "visual_description": "Close-up of [PERSON_1]'s face as he looks down with a shocked and concerned expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.6, 3.9 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Young woman with dark hair, pale skin, and delicate features", "attributes": "Dark hair" }, "PERSON_1" ], "visual_description": "Close-up of [PERSON_2]'s face looking up towards [PERSON_1]. She then slowly closes her eyes.", "camera": { "shot_type": "close-up", "angle": "high-angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.9, 5.0 ], "references": [ "PERSON_1", { "ref_id": "SCENE_1", "type": "scene", "id_features": "Room with wooden sliding doors, teal curtains, and traditional architecture" } ], "visual_description": "[PERSON_1] runs out of [SCENE_1] in a panic, looking back over his shoulder.", "camera": { "shot_type": "wide", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 0.8, 3.6 ], "content": { "speaker": "PERSON_1", "line": "你雷千不妨", "description": "Urgent and worried tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 4.0, 5.0 ], "content": { "description": "Sound of hurried footsteps." } } ], "scene_description": "A dramatic moment where a man expresses concern for a woman, followed by him running away in a panic.", "global_style": "3D animated fantasy style with traditional Chinese elements.", "global_audio": "Dramatic dialogue followed by the sound of running." } }, { "dataset": "drama_03", "clip_id": "clip_13033", "media_path": "drama_03/clip_13033.mp4", "source_media_path": "clips/clip_13033.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with messy dark hair, looking slightly downwards with a serious expression", "attributes": "messy dark hair, white collared shirt, light-colored textured jacket" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor space with moody, low-key lighting" } ], "visual_description": "[PERSON_1] is shown in a close-up, looking slightly downwards and away from the camera with a serious, contemplative expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.9, 3.3 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with dark hair styled in two messy buns, holding a smartphone", "attributes": "dark hair in two buns, dark green jacket, light green shirt" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A modern smartphone displaying a contact profile screen" }, "SCENE_1", "PERSON_1" ], "visual_description": "The view cuts to [PERSON_2] holding [OBJECT_1] in her hand. She is looking towards where [PERSON_1] would be standing, speaking to him.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.3, 5.4 ], "references": [ "PERSON_2", "OBJECT_1", "SCENE_1" ], "visual_description": "A bright purple and white flash transitions the scene. [PERSON_2] is now holding [OBJECT_1] up, displaying the screen directly to the camera.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.1, 1.5 ], "content": { "speaker": "PERSON_2", "line": "我呢", "description": "Casual, slightly questioning tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.5, 2.5 ], "content": { "speaker": "PERSON_2", "line": "已经帮你报警了", "description": "Confident and direct statement." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.8, 3.5 ], "content": { "description": "A bright, whooshing flash sound effect accompanying the visual transition." } } ], "scene_description": "A tense interaction between a man and a woman, where the woman reveals she has already called the police on his behalf, ending with a dramatic cliffhanger.", "global_style": "Cinematic and moody, featuring low-key lighting and a stylized flash transition.", "global_audio": "Quiet ambient background focusing on clear dialogue, punctuated by a dramatic transition sound effect." } }, { "dataset": "drama_03", "clip_id": "clip_119", "media_path": "drama_03/clip_119.mp4", "source_media_path": "clips/clip_119.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Fair skin, prominent nose, and glossy pink lips", "attributes": "clothing: Not visible, hairstyle: Not visible, accessories: None visible" } ], "visual_description": "An extreme close-up focuses on the lower half of [PERSON_1]'s face. Her glossy lips part and move as she speaks.", "camera": { "shot_type": "extreme close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.5, 4.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Only a hand is visible, showing fair skin and slender fingers", "attributes": "clothing: White and silver garment with an ornate cuff featuring large, bright blue gemstones., hairstyle: Not visible, accessories: Silver cuff with blue gems" } ], "visual_description": "The camera cuts to a close-up of [PERSON_2]'s hand tightly gripping a piece of light-colored fabric, revealing the detailed blue gemstone cuff on the wrist.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 2.5 ], "content": { "speaker": "PERSON_1", "line": "我会收好你的", "description": "Soft, seductive, and slightly menacing tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 3.0, 4.0 ], "content": { "description": "Sound of fabric rustling and tightening as a hand grips it firmly." } } ], "scene_description": "A seductive and tense moment where a female character speaks intimately, prompting a physical reaction of tension from another character who grips their clothing.", "global_style": "High-quality 3D animation with a fantasy aesthetic, featuring detailed textures, soft lighting on the face, and intricate costume designs.", "global_audio": "A quiet atmosphere dominated by a close, intimate voice line followed by a subtle foley sound of fabric." } }, { "dataset": "drama_03", "clip_id": "clip_18079", "media_path": "drama_03/clip_18079.mp4", "source_media_path": "clips/clip_18079.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with fair skin, red lipstick, and a sorrowful expression", "attributes": "clothing: Light blue traditional Chinese dress with floral embroidery., hairstyle: Elaborate updo., accessories: Silver and pearl hairpieces with dangling ornaments, silver necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit interior space with blurred warm lights in the background, suggesting a grand hall or room" } ], "visual_description": "A close-up shot of [PERSON_1] looking downwards with a sorrowful expression. She slightly raises her gaze towards the end of the shot.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 1.3, 5.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with a serious and resolute facial expression", "attributes": "clothing: Dark robe with intricate gold wave-like patterns., hairstyle: Long dark hair half-tied up., accessories: Gold crown-like headpiece with long dangling gold chains" }, "SCENE_1" ], "visual_description": "An over-the-shoulder medium shot focusing on [PERSON_2]. He is looking directly ahead and speaking with a stern expression. The shoulder and back of [PERSON_1] are visible in the blurred foreground.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.1, 4.3 ], "content": { "speaker": "PERSON_2", "line": "我柳家只有休妻没有", "description": "Stern and resolute declaration." } } ], "scene_description": "A tense confrontation between a man and a woman in a historical setting, where the man firmly states his family's rules regarding marriage separation.", "global_style": "Historical Chinese fantasy drama with elaborate costumes and soft, warm lighting.", "global_audio": "Quiet ambient background with clear dialogue." } }, { "dataset": "drama_03", "clip_id": "clip_21291", "media_path": "drama_03/clip_21291.mp4", "source_media_path": "clips/clip_21291.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.6 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with fair skin and long dark hair tied up in a topknot with some loose strands", "attributes": "Wearing a light-colored, textured, cross-collared robe with a wide, multi-layered belt in brown, red, and grey tones. He has a small braided cord accessory on his chest" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A blurred outdoor background suggesting a courtyard or garden with traditional architecture and greenery" } ], "visual_description": "[PERSON_1] is standing outdoors, looking slightly off-camera with a serious expression as he speaks.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.6, 4.8 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A closer view of [PERSON_1] as he delivers a more intense statement, his eyes narrowing slightly.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.8, 5.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin, delicate features, and long dark hair", "attributes": "Wearing elaborate gold and pearl hair accessories, a white lacy dress with intricate embroidery, and a pearl necklace" }, "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] is shown looking towards [PERSON_1] with an expression of shock and concern.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 3.0 ], "content": { "speaker": "PERSON_1", "line": "何止认识", "description": "Serious and slightly bitter tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.5, 5.0 ], "content": { "description": "A dramatic, low-frequency swoosh followed by a tense musical sting that sustains." } } ], "scene_description": "A dramatic confrontation where a man reveals a deep-seated enmity to a surprised woman.", "global_style": "Chinese period drama aesthetic, likely Xianxia or Wuxia, featuring elaborate traditional costumes, soft lighting, and a shallow depth of field.", "global_audio": "Quiet ambient background punctuated by dramatic dialogue and a tense musical sting." } }, { "dataset": "drama_03", "clip_id": "clip_1431", "media_path": "drama_03/clip_1431.mp4", "source_media_path": "clips/clip_1431.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.8 ], "references": [], "visual_description": "A brief reflection in a dark, glossy surface shows a person in tactical gear holding a camera.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.8, 2.3 ], "references": [ { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dark room featuring wood-paneled walls, patterned curtains over a window, and a desk" }, { "ref_id": "PERSON_1", "type": "person", "id_features": "A soldier wearing a camouflage uniform, a tactical vest, and a helmet with flipped-up night vision goggles", "attributes": "camouflage uniform, tactical vest, helmet, night vision goggles" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A soldier wearing a camouflage uniform and tactical gear, holding a rifle", "attributes": "camouflage uniform, tactical gear, rifle" } ], "visual_description": "Inside [SCENE_1], [PERSON_2] crouches near the window, aiming a rifle to secure the area. In the background, [PERSON_1] stands near a desk.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.3, 5.0 ], "references": [ "SCENE_1", "PERSON_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A black, rectangular safe or electronic device situated on a desk" } ], "visual_description": "[PERSON_1] stands at the desk in [SCENE_1], using both hands to carefully operate [OBJECT_1].", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 4.0 ], "content": { "description": "Low, ominous ambient drone music." } } ], "scene_description": "Soldiers in tactical gear conduct an operation inside a dimly lit room, with one securing the perimeter at the window while another interacts with a device on a desk.", "global_style": "Dark, gritty, tactical, cinematic.", "global_audio": "Ominous ambient drone." } }, { "dataset": "drama_03", "clip_id": "clip_11107", "media_path": "drama_03/clip_11107.mp4", "source_media_path": "clips/clip_11107.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with a fair complexion, wearing an elaborate traditional Chinese dress", "attributes": "White and pink dress with floral embroidery, elaborate hairstyle with silver and pearl hairpins, long black hair tied with dark ribbons" } ], "visual_description": "[PERSON_1] stands looking slightly downward, then raises her eyes with a calm, somewhat melancholic expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.4, 4.5 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with a stern expression, dressed in dark, regal clothing", "attributes": "Black cloak with a fur collar over a red inner garment, ornate gold crown, long black hair" } ], "visual_description": "[PERSON_2] stands indoors in front of a decorative wooden screen, looking straight ahead with a serious and commanding demeanor.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.5, 5.0 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman speaking to someone off-camera, dressed in simpler, everyday traditional clothes", "attributes": "Brown and beige wrap dress, simple hairstyle, carrying a woven basket" } ], "visual_description": "[PERSON_3] is seen speaking animatedly, holding a woven basket. A white paper umbrella with a red detail is partially visible in the background.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.4, 3.5 ], "content": { "speaker": "PERSON_3", "line": "他是太子殿下的恩人", "description": "Gossiping, informative tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.5, 4.8 ], "content": { "speaker": "PERSON_3", "line": "此次跟隨太子殿下回去", "description": "Continuing the gossip with a matter-of-fact tone" } } ], "scene_description": "A brief sequence from a historical drama where a character gossips about a young woman being the benefactor of the Crown Prince and accompanying him back.", "global_style": "Historical Chinese drama aesthetic, featuring elaborate traditional costumes, soft lighting, and a dramatic, serious tone.", "global_audio": "Clear spoken dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_03", "clip_id": "clip_31484", "media_path": "drama_03/clip_31484.mp4", "source_media_path": "clips/clip_31484.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "An older woman with a neutral expression, wearing an elaborate headdress and a layered blue and purple robe with intricate patterns", "attributes": "elaborate gold headdress, blue and purple layered robe, intricate patterns" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious room with wooden lattice windows, decorative plants including pink blossom trees, patterned carpets, and low wooden tables" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], looking forward with a neutral expression. The camera focuses on her upper body.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 3.5 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A younger woman with her hair styled up, wearing a gold headdress and a bright red robe with gold embroidery", "attributes": "gold headdress, red robe, gold embroidery" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman seen from behind, wearing a white robe and hair ornaments", "attributes": "white robe, hair ornaments" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A white pedestal plate holding several red apples" }, "SCENE_1" ], "visual_description": "[PERSON_2] sits at a low table with [OBJECT_1] in [SCENE_1]. She looks slightly downwards and then raises her eyes. [PERSON_4] is partially visible in the foreground.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 3.5, 6.4 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman wearing a light pink robe and a headdress", "attributes": "pink robe, headdress" }, "PERSON_4", { "ref_id": "PERSON_5", "type": "person", "id_features": "A man sitting in the background wearing a grey or light blue robe", "attributes": "grey robe" }, "SCENE_1" ], "visual_description": "A wide view of [SCENE_1]. [PERSON_1] walks towards [PERSON_3], who is standing. [PERSON_2] and [PERSON_4] are seated at tables in the foreground. [PERSON_5] is seated at a table in the background.", "camera": { "shot_type": "wide shot", "angle": "high angle", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 1.0 ], "content": { "description": "A sharp, resonant chime or bell sound effect." } } ], "scene_description": "A group of people in traditional attire are gathered in an ornate room. One woman walks towards another while others remain seated at low tables.", "global_style": "Historical drama, traditional Chinese aesthetic, bright lighting, rich colors.", "global_audio": "Quiet ambient sound with an initial chime sound effect." } }, { "dataset": "drama_04", "clip_id": "clip_82554", "media_path": "drama_04/clip_82554.mp4", "source_media_path": "clips/clip_82554.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with short dark hair, wearing a white top with a prominent black bow collar", "attributes": "clothing: white top with black bow collar, hairstyle: short dark hair, accessories: hair clip" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long dark hair tied half-up, wearing a white high-necked top with decorative buttons", "attributes": "clothing: white high-necked top, hairstyle: long dark hair, half-up, accessories: gold earrings" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man with medium-length wavy brown hair, wearing a beige coat over a black shirt", "attributes": "clothing: beige coat, black shirt, hairstyle: medium-length wavy brown hair, accessories: none" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor space with large windows letting in natural light, filled with various colorful flowers in vases" } ], "visual_description": "[PERSON_2] stands with her arm around [PERSON_1], talking to her. [PERSON_3] stands next to them, looking on. They are in [SCENE_1].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.4, 6.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "Over-the-shoulder shot from [PERSON_1]'s perspective, focusing on [PERSON_2]'s face as she continues speaking confidently.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.7, 9.1 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_1] and [PERSON_2] look at each other and smile warmly.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.1, 10.0 ], "references": [ "PERSON_3", "SCENE_1" ], "visual_description": "[PERSON_3] smiles gently with his eyes closed.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.5, 3.8 ], "content": { "speaker": "PERSON_2", "line": "我哥除了我的手", "description": "Confident statement" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.8, 5.5 ], "content": { "speaker": "PERSON_2", "line": "别的女人的手", "description": "Emphasizing a point" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.5, 6.4 ], "content": { "speaker": "PERSON_2", "line": "是不会碰的", "description": "Concluding with certainty" } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Soft, romantic background music" } } ], "scene_description": "Three people are gathered in a bright flower shop. One woman confidently tells another that her brother will not touch any other woman's hand except hers, leading to smiles all around.", "global_style": "Bright, romantic, soft lighting, warm tones.", "global_audio": "Soft background music with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_81391", "media_path": "drama_04/clip_81391.mp4", "source_media_path": "clips/clip_81391.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "An older woman with short, dark hair, a fair complexion, and a concerned facial expression", "attributes": "Wearing a light grey, long-sleeved button-up shirt, dark trousers, and dark slip-on shoes" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring a wooden door frame, a wooden wardrobe, a small wooden desk with a white bowl on it, and light-colored walls" } ], "visual_description": "[PERSON_1] leans into [SCENE_1] through an open doorway. She holds onto the door frame with one hand and gestures slightly with her other hand while speaking with an earnest expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.0, 8.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short dark hair, a clean-shaven face, and a serious, upright posture", "attributes": "Wearing a green military-style uniform consisting of a button-up shirt and trousers, a brown leather belt, and black dress shoes" }, "SCENE_1" ], "visual_description": "The view cuts to [PERSON_2] standing upright in the middle of [SCENE_1], facing the doorway. He maintains a rigid posture, listens attentively, and then responds with a firm and reassuring demeanor.", "camera": { "shot_type": "Medium full shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 8.7, 10.0 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young woman with long black hair styled in two braids, resting with her eyes closed", "attributes": "Wearing a yellow long-sleeved button-up shirt and white trousers" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A bed covered with a light-colored, slightly wrinkled sheet and a white pillow" } ], "visual_description": "The scene transitions to [PERSON_3] lying flat on her back on [SCENE_2]. Her eyes are closed, her hands rest peacefully by her sides, and she appears completely relaxed.", "camera": { "shot_type": "Medium shot", "angle": "High angle", "movement": "Static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 3.1 ], "content": { "speaker": "PERSON_1", "line": "有时候脾气倔你多担待", "description": "Earnest and slightly pleading tone, expressing a mother's concern." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.1, 5.5 ], "content": { "speaker": "PERSON_3", "line": "陆征回答得很坚定", "description": "Calm, reflective narrative tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.5, 8.8 ], "content": { "speaker": "PERSON_2", "line": "妈您放心小碗很好我会照顾好她", "description": "Firm, respectful, and reassuring tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.8, 9.7 ], "content": { "speaker": "PERSON_3", "line": "我心里那点不安", "description": "Relieved and peaceful narrative tone." } } ], "scene_description": "A mother speaks to her son-in-law, asking him to be patient with her daughter's stubbornness. The son-in-law responds with a firm promise to take good care of her, which brings a sense of deep relief and peace to the daughter, who is reflecting on the exchange.", "global_style": "Nostalgic and realistic, featuring a muted color palette and vintage clothing that suggests a mid-to-late 20th-century setting.", "global_audio": "Clear, upfront dialogue and voiceover narration with a quiet, subtle room ambience." } }, { "dataset": "drama_04", "clip_id": "clip_72643", "media_path": "drama_04/clip_72643.mp4", "source_media_path": "clips/clip_72643.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair and a fair complexion", "attributes": "Wearing a grey silk pajama shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A bedroom featuring a bed with a white tufted headboard, grey patterned pillows, and grey silk sheets" } ], "visual_description": "[PERSON_1] is sleeping peacefully in [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.0, 3.0 ], "references": [ { "ref_id": "SCENE_2", "type": "scene", "id_features": "A dark blue night sky with a bright full moon, partially obscured by the dark silhouettes of tree leaves in the foreground" } ], "visual_description": "A view of [SCENE_2], showing the moon glowing through the leaves.", "camera": { "shot_type": "medium shot", "angle": "low angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.0, 4.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long, wavy black hair", "attributes": "Wearing a beige silk slip dress with lace trim and a matching sheer robe" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A standard white interior door with a silver handle" }, "SCENE_1" ], "visual_description": "[PERSON_2] slowly opens [OBJECT_1] and steps into [SCENE_1], looking towards the bed.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1", "SFX_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.8, 6.2 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A brief shot of [PERSON_1] continuing to sleep in [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.2, 9.4 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] approaches the bed in [SCENE_1], looking down at [PERSON_1] with a soft expression.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "pan down" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 8.0 ], "content": { "description": "Soft, emotional piano melody playing in the background." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.5, 3.5 ], "content": { "description": "Sound of a door latch clicking and the door creaking open." } } ], "scene_description": "A woman quietly enters a dimly lit bedroom at night to check on a sleeping man.", "global_style": "Cinematic, moody lighting, romantic and quiet atmosphere.", "global_audio": "Soft piano music with ambient room sounds." } }, { "dataset": "drama_04", "clip_id": "clip_71126", "media_path": "drama_04/clip_71126.mp4", "source_media_path": "clips/clip_71126.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Middle-aged man with short black hair and a wrinkled face", "attributes": "Wearing a dark green short-sleeved t-shirt and blue jeans" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "Small, translucent river shrimp", "attributes": "None" } ], "visual_description": "[PERSON_1] is seen in a close-up, stuffing [OBJECT_1] into his mouth and chewing it with an exaggerated expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.5, 6.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Woman with fair skin", "attributes": "Wearing a dark blue sheer long-sleeved blouse, grey trousers, and a gold bracelet" } ], "visual_description": "The camera cuts to a close-up of [PERSON_2] lying motionless on the floor.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.8, 10.3 ], "references": [ "PERSON_1" ], "visual_description": "[PERSON_1] is shown again in a close-up, looking directly forward with a serious expression. A digital interface with garbled text is overlaid on the screen.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 10.3, 11.4 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "OBJECT_2", "type": "object", "id_features": "White bowl containing food", "attributes": "None" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Brightly lit room with white walls, a wooden table, and chairs", "attributes": "None" } ], "visual_description": "A wide shot reveals [PERSON_1] sitting on a chair at a table, eating from [OBJECT_2] with chopsticks. In the foreground, [PERSON_2] remains lying on the floor.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 4.2 ], "content": { "speaker": "NARRATOR", "line": "就把一只河虾塞进嘴里吃得津津有味还故意发出咀嚼的声", "description": "Narrating the man's actions." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 4.0 ], "content": { "description": "Loud chewing and crunching sounds." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.2, 7.0 ], "content": { "speaker": "NARRATOR", "line": "音完全无视了地上痛苦挣扎的张翠芳", "description": "Narrating the woman's situation." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.0, 9.9 ], "content": { "speaker": "NARRATOR", "line": "弹幕上终于有人看不下去了纷纷指责赵志刚没人", "description": "Narrating the audience's reaction." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 10.3, 11.1 ], "content": { "speaker": "NARRATOR", "line": "主播都晕倒了", "description": "Concluding the narration." } } ], "scene_description": "A man callously eats a meal while ignoring a woman lying seemingly unconscious on the floor nearby, prompting outrage from unseen viewers.", "global_style": "Dramatic and slightly surreal, with a mix of close-ups and a revealing wide shot.", "global_audio": "A continuous voiceover narration with exaggerated chewing sound effects in the beginning." } }, { "dataset": "drama_04", "clip_id": "clip_41098", "media_path": "drama_04/clip_41098.mp4", "source_media_path": "clips/clip_41098.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with a concerned expression", "attributes": "Wearing a light green and white traditional outfit with floral embroidery, hair styled up with floral accessories" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman appearing drunk and playful", "attributes": "Wearing a flowing pink and white traditional robe, hair styled up with elegant hairpins" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A dark blue, round-bottomed bottle" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden furniture and lit candles in the background" } ], "visual_description": "[PERSON_1] looks concerned and reaches out her hand towards [PERSON_2], who is partially visible in the foreground holding [OBJECT_1].", "camera": { "shot_type": "over-the-shoulder shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 9.8 ], "references": [ "PERSON_1", "PERSON_2", "OBJECT_1", "SCENE_1" ], "visual_description": "The focus shifts to [PERSON_2], who is holding [OBJECT_1]. She appears intoxicated, swaying slightly and adjusting her garment. [PERSON_1]'s hand is visible reaching out to her. [PERSON_2] leans forward, resting her chin on her hand that holds [OBJECT_1], and speaks to [PERSON_1].", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "DIALOGUE_4" ] }, { "shot_id": "SHOT_3", "time_range": [ 9.8, 10.8 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The focus returns to [PERSON_1], who looks down slightly and responds to [PERSON_2].", "camera": { "shot_type": "over-the-shoulder shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_5" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.6, 1.4 ], "content": { "speaker": "PERSON_1", "line": "别喝了", "description": "Concerned and urging tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.7, 9.6 ], "content": { "speaker": "PERSON_2", "line": "我们先玩个游戏", "description": "Playful, intoxicated tone." } } ], "scene_description": "A concerned companion tries to stop an intoxicated woman from drinking more, but the intoxicated woman playfully suggests playing a game instead.", "global_style": "Historical Chinese drama aesthetic with soft warm lighting and elegant traditional costumes.", "global_audio": "Quiet ambient room sound with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_18221", "media_path": "drama_04/clip_18221.mp4", "source_media_path": "clips/clip_18221.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with fair skin, sharp eyebrows, and dark eyes", "attributes": "Wearing a white robe with blue crane embroidery, a black scholar's hat, and a jade belt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with a wooden desk, calligraphy brushes, rolled scrolls, and a landscape painting hanging on the wall", "attributes": "Well-lit, traditional decor" } ], "visual_description": "[PERSON_1] is sitting at a desk in [SCENE_1], looking down at something. He then slowly raises his head to look forward.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 4.5, 7.5 ], "references": [ "PERSON_1" ], "visual_description": "A close-up of [PERSON_1]'s face as he speaks with a serious expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.5, 9.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin, large eyes, and red lips", "attributes": "Wearing elaborate red and gold hair accessories, dangling earrings, and a red dress" } ], "visual_description": "A close-up of half of [PERSON_2]'s face as she speaks with a slight, innocent smile.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 4.7, 8.1 ], "content": { "speaker": "PERSON_1", "line": "你早上是故意的", "description": "Serious and questioning tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 8.1, 8.9 ], "content": { "speaker": "PERSON_2", "line": "夫君在说什么", "description": "Innocent, feigning ignorance." } } ], "scene_description": "A tense conversation between a husband and wife in a traditional Chinese setting, where the husband accuses the wife of doing something on purpose, and she feigns ignorance.", "global_style": "3D animation with a traditional Chinese historical aesthetic, realistic lighting, and detailed character models.", "global_audio": "Quiet ambient sound with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_23010", "media_path": "drama_04/clip_23010.mp4", "source_media_path": "clips/clip_23010.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with a clean-shaven face, wearing traditional Chinese attire", "attributes": "White robes with light blue accents and circular patterns on the shoulders, dark hair styled up with a silver ornamental headpiece" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "An older man with a mustache and goatee, looking serious", "attributes": "Dark, patterned robes, hair tied up in a topknot with a braided band" } ], "visual_description": "[PERSON_1] is shown in a close-up, speaking and gesturing slightly with his head. He is looking off-camera to his right, towards [PERSON_2].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.4, 6.8 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with a slightly fuller build, focused on his food", "attributes": "Brownish, earth-toned clothing, hair tied back" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with traditional Chinese decor, featuring a round dining table laden with dishes, warm ambient lighting from lanterns", "attributes": "Round table, food dishes, teacups, warm lighting, traditional architecture" } ], "visual_description": "The camera cuts to a wider shot showing [PERSON_1], [PERSON_2], and [PERSON_3] sitting around a table in [SCENE_1]. [PERSON_1] continues to speak, gesturing with his hands. [PERSON_2] listens attentively, while [PERSON_3] is actively eating from a bowl.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.8, 10.0 ], "references": [ "PERSON_2", "PERSON_1" ], "visual_description": "A close-up of [PERSON_2] looking down thoughtfully, then slightly raising his gaze as he is addressed by [PERSON_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.0, 3.2 ], "content": { "speaker": "PERSON_1", "line": "这船的两侧还有预留排", "description": "Explaining a technical detail with a calm and informative tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.9, 6.2 ], "content": { "speaker": "PERSON_1", "line": "用于存放油柜重", "description": "Continuing the explanation, listing items." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 9.0, 9.2 ], "content": { "speaker": "PERSON_1", "line": "家主", "description": "Addressing someone directly with a respectful but firm tone." } } ], "scene_description": "Three men are gathered around a dining table in a traditional setting, discussing the design and specifications of a ship.", "global_style": "Historical Chinese drama with high production value, featuring detailed costumes and warm, atmospheric lighting.", "global_audio": "Clear dialogue with subtle ambient room noise." } }, { "dataset": "drama_04", "clip_id": "clip_26433", "media_path": "drama_04/clip_26433.mp4", "source_media_path": "clips/clip_26433.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.6 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with a fair complexion, sharp facial features, and long black hair", "attributes": "Wearing a dark blue traditional robe with gold embroidery and a black hairpiece" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit interior space with stone pillars and light streaming in from a damaged roof" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], looking directly forward with a serious and resolute expression.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.6, 5.6 ], "references": [ "PERSON_1", { "ref_id": "SCENE_2", "type": "scene", "id_features": "A desolate landscape in front of a large, dark stone fortress, filled with an army" }, { "ref_id": "ANIMAL_1", "type": "animal", "id_features": "Large, bear-like creatures with dark fur and glowing fire on their bodies" } ], "visual_description": "A wide view of [SCENE_2] showing [PERSON_1] standing alone, surrounded by a massive army of soldiers and large, fiery [ANIMAL_1].", "camera": { "shot_type": "wide shot", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.6, 6.8 ], "references": [ "PERSON_1" ], "visual_description": "A tight close-up of [PERSON_1]'s face, showing cuts and blood, with an intense, angry expression as he speaks.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] }, { "shot_id": "SHOT_4", "time_range": [ 6.8, 8.1 ], "references": [ { "ref_id": "ANIMAL_2", "type": "animal", "id_features": "A grey pigeon with red feet" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A small, rolled-up piece of light-colored paper" } ], "visual_description": "A close-up of hands attaching a small rolled-up [OBJECT_1] to the leg of [ANIMAL_2].", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_4", "DIALOGUE_5" ] }, { "shot_id": "SHOT_5", "time_range": [ 8.1, 9.4 ], "references": [ "ANIMAL_2" ], "visual_description": "[ANIMAL_2] takes flight against a cloudy sky.", "camera": { "shot_type": "medium shot", "angle": "low angle", "movement": "tracking" }, "active_events": [ "DIALOGUE_5", "SFX_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 2.6 ], "content": { "speaker": "PERSON_1", "line": "早已磨灭我对他们的最后一丝幻想", "description": "Serious and resolute tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.9, 4.4 ], "content": { "speaker": "PERSON_1", "line": "年前我率军出战", "description": "Narrative tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.4, 5.7 ], "content": { "speaker": "PERSON_1", "line": "被妖族大军包围", "description": "Intense narrative tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 5.7, 8.1 ], "content": { "speaker": "PERSON_1", "line": "我向当时已是镇妖司司主的父亲", "description": "Angry and desperate tone." } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 8.1, 9.1 ], "content": { "speaker": "PERSON_1", "line": "连发十道求援令", "description": "Urgent and resentful tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.0, 5.0 ], "content": { "description": "Sounds of a battlefield, including roaring beasts and army clamor." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 8.0, 9.0 ], "content": { "description": "Flapping wings of a bird taking off." } } ], "scene_description": "A warrior recounts a past betrayal where he was abandoned by his father during a massive battle against a demon army, leading to his current state of disillusionment.", "global_style": "Dark fantasy, dramatic, cinematic with high contrast lighting and intense visual effects.", "global_audio": "Dramatic and tense background music accompanying the intense narration and battlefield sound effects." } }, { "dataset": "drama_04", "clip_id": "clip_100256", "media_path": "drama_04/clip_100256.mp4", "source_media_path": "clips/clip_100256.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long dark hair, wearing a white jacket with pearl embellishments and a white lace collar, and dangling earrings", "attributes": "long dark hair, white jacket, pearl embellishments, white lace collar, dangling earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit indoor space with a solid, muted greyish-green wall in the background", "attributes": "indoor, dimly lit, greyish-green wall, plain background" } ], "visual_description": "[PERSON_1] looks directly forward with a serious and slightly threatening expression while speaking.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.8, 3.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long wavy brown hair, wearing a beige trench coat over a grey top and a striped collared shirt, and pearl earrings", "attributes": "long wavy brown hair, beige trench coat, grey top, striped collared shirt, pearl earrings" }, "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], who looks slightly confused and defensive as she responds.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.2, 5.9 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1], who continues speaking with a firm and accusatory tone.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.9, 8.6 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2] again, who is listening intently, her expression turning more concerned and serious.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_5", "time_range": [ 8.6, 10.4 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1] as she delivers a revealing statement, maintaining intense eye contact.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 2.3 ], "content": { "speaker": "PERSON_1", "line": "你觉得我会放过你吗", "description": "Threatening and serious tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.3, 4.4 ], "content": { "speaker": "PERSON_2", "line": "这跟我有什么关系", "description": "Defensive and confused tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.4, 7.0 ], "content": { "speaker": "PERSON_1", "line": "因为这些是李泽培为了给你出头", "description": "Accusatory and explanatory tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 7.4, 9.9 ], "content": { "speaker": "PERSON_1", "line": "的你知不知道其实李泽培", "description": "Dramatic and revealing tone" } } ], "scene_description": "A tense confrontation between two women, where one accuses the other and reveals a hidden identity regarding a man named Li Zepei.", "global_style": "Modern drama, cinematic lighting with a slightly cool and moody color palette.", "global_audio": "Clear dialogue with no prominent background music or ambient noise." } }, { "dataset": "drama_04", "clip_id": "clip_24685", "media_path": "drama_04/clip_24685.mp4", "source_media_path": "clips/clip_24685.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with a red mark on her forehead and red smudges on her cheeks, wearing elaborate traditional clothing", "attributes": "clothing: Blue traditional dress with gold embroidery and a white collar., hairstyle: Elaborate updo with multiple gold hairpins and ornaments., accessories: Gold hairpins, dangling earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with traditional Chinese decor, featuring a red round table" } ], "visual_description": "[PERSON_1] speaks animatedly with an angry expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.5, 3.4 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with a serious expression, sitting at a table", "attributes": "clothing: Black robe with feather-like details on the shoulders., hairstyle: Hair pulled back into a topknot with a hairpiece., accessories: Dark hairpiece" }, "SCENE_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A red round table with a white teapot, white teacups, and a plate of oranges" } ], "visual_description": "[PERSON_2] sits at [OBJECT_1], listening with a serious and slightly frowning expression.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.4, 5.3 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young woman with a gentle expression, sitting at a table", "attributes": "clothing: Pale yellow and white traditional dress with floral embroidery., hairstyle: Long dark hair, half-up with gold ornaments., accessories: Gold hair ornaments, simple necklace, dangling earrings" }, "SCENE_1", "OBJECT_1" ], "visual_description": "[PERSON_3] sits at [OBJECT_1], smiling slightly while holding a teacup.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.3, 8.1 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] continues speaking with a furious and vindictive look, gesturing slightly with her hand.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_5", "time_range": [ 8.1, 10.0 ], "references": [ "PERSON_2", "SCENE_1", "OBJECT_1" ], "visual_description": "[PERSON_2] remains seated at [OBJECT_1], looking slightly downward as he listens.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.8, 3.6 ], "content": { "speaker": "PERSON_1", "line": "那蛇兽定要狠狠地撕咬他们", "description": "Angry and vindictive tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.6, 5.6 ], "content": { "speaker": "PERSON_1", "line": "让他和那个小野种", "description": "Spiteful and malicious tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.6, 7.6 ], "content": { "speaker": "PERSON_1", "line": "死无葬身之地", "description": "Furious and threatening tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 7.9, 9.7 ], "content": { "speaker": "PERSON_3", "line": "月死了风哥哥", "description": "Calm, reporting tone." } } ], "scene_description": "A tense conversation takes place among three individuals in a traditional setting. One woman expresses intense anger and wishes harm upon others, while another woman calmly reports a death to the man present.", "global_style": "Traditional Chinese historical or fantasy drama aesthetic, characterized by elaborate costumes, ornate hairpieces, and classical interior design.", "global_audio": "Clear dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_04", "clip_id": "clip_87870", "media_path": "drama_04/clip_87870.mp4", "source_media_path": "clips/clip_87870.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 6.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, clean-shaven, with a serious expression", "attributes": "Wearing a dark blue suit, a crisp white shirt, and a dark red tie" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with warm lighting, featuring a large wooden desk, wooden chairs, a calligraphy scroll on the wall, and traditional wooden window frames" } ], "visual_description": "[PERSON_1] is sitting behind a large wooden desk in [SCENE_1], looking directly forward with a serious demeanor. The setting is formal and traditional.", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 6.8, 8.1 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts to a medium close-up of [PERSON_1] as he speaks. He maintains a serious expression, slightly moving his head for emphasis.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 8.1, 10.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A plump man with a goatee, wearing a red bandana on his head", "attributes": "Wearing a brown leather jacket over a pink graphic t-shirt, a red bandana, and a beaded necklace" }, "SCENE_1" ], "visual_description": "The camera angle changes to show both [PERSON_1] and [PERSON_2] sitting across from each other at the desk in [SCENE_1]. [PERSON_2] is speaking and gesturing slightly, while [PERSON_1] listens attentively.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.8, 6.4 ], "content": { "speaker": "PERSON_1", "line": "四大家族谁不知道除了他们还有赌王船王那几", "description": "Serious and informative tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 6.4, 9.8 ], "content": { "speaker": "PERSON_2", "line": "家那些啊只是某些势力想让你看到的", "description": "Dismissive and revealing tone." } } ], "scene_description": "Two men are having a serious conversation in a traditional study room, discussing powerful families and hidden forces.", "global_style": "Cinematic, dramatic lighting, traditional Chinese aesthetic.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_59825", "media_path": "drama_04/clip_59825.mp4", "source_media_path": "clips/clip_59825.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 7.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long black hair, wearing a grey sleeveless turtleneck top and a black leather pencil skirt", "attributes": "long black hair, grey sleeveless turtleneck top, black leather pencil skirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A well-lit modern living room with a grey sofa, a black coffee table, and white built-in cabinets", "attributes": "grey sofa, black coffee table, white cabinets, modern decor" } ], "visual_description": "[PERSON_1] stands in the middle of [SCENE_1]. She maintains a serious expression and looks directly forward. The camera remains static on her.", "camera": { "shot_type": "medium-full shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_2", "time_range": [ 7.7, 10.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "An older woman with short curly black hair, wearing a blue floral short-sleeved dress", "attributes": "short curly black hair, blue floral dress" }, "SCENE_1" ], "visual_description": "[PERSON_2] stands in [SCENE_1], gesturing with her right hand while speaking. She looks slightly off-camera with an assertive expression.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 3.3 ], "content": { "speaker": "PERSON_2", "line": "小姑娘家家的说话也太难听了", "description": "Complaining tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.3, 4.9 ], "content": { "speaker": "PERSON_2", "line": "什么跟踪不跟踪的", "description": "Dismissive tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.9, 7.8 ], "content": { "speaker": "PERSON_2", "line": "这房子你不就是想跟我儿子结婚才买的吗", "description": "Accusatory tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 7.8, 9.5 ], "content": { "speaker": "PERSON_2", "line": "还藏着掖着走拿出来", "description": "Demanding tone" } } ], "scene_description": "An older woman confronts a young woman in a modern living room, accusing her of buying a house with the intention of marrying her son.", "global_style": "Realistic, modern, dramatic.", "global_audio": "Clear dialogue with no background music." } }, { "dataset": "drama_04", "clip_id": "clip_72873", "media_path": "drama_04/clip_72873.mp4", "source_media_path": "clips/clip_72873.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Middle-aged man with short black hair, wearing glasses", "attributes": "Grey suit jacket, white button-up shirt, black trousers" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Young woman with black hair tied back", "attributes": "Light blue cardigan, floral patterned blouse with a bow tie" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "Man with short black hair, wearing glasses", "attributes": "Brown jacket, striped shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with a wooden desk, stacks of paper, a washbasin on a stand in the background, and windows with green curtains" } ], "visual_description": "[PERSON_1] stands behind a desk in [SCENE_1], gesturing with his hand as he speaks to [PERSON_2], whose back is to the camera. [PERSON_3] is partially visible in the foreground on the right.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.4, 4.8 ], "references": [ "PERSON_3", "SCENE_1" ], "visual_description": "A close-up of [PERSON_3] looking slightly surprised or confused.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 4.8, 9.1 ], "references": [ "PERSON_2", "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_2] looks earnestly forward, speaking with determination. The shoulder of [PERSON_1] is visible in the foreground.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.1, 9.7 ], "references": [ "PERSON_1", "PERSON_2", "PERSON_3", "SCENE_1" ], "visual_description": "[PERSON_1] stands behind the desk, looking at [PERSON_2] after she finishes speaking.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 4.3 ], "content": { "speaker": "PERSON_1", "line": "你这英语怎么说的跟广播里一模一样", "description": "Impressed and slightly surprised tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.3, 8.7 ], "content": { "speaker": "PERSON_2", "line": "校长我想进医中我想考大学请您告诉我该怎么做", "description": "Earnest, determined, and respectful tone." } } ], "scene_description": "A young woman earnestly asks a school principal for guidance on how to enter a specific middle school and eventually go to college, after he praises her English pronunciation.", "global_style": "Realistic, period drama style with warm, slightly muted lighting.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_21115", "media_path": "drama_04/clip_21115.mp4", "source_media_path": "clips/clip_21115.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 9.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Young female with short white hair, large brown deer antlers, and a yellow flower hair accessory", "attributes": "Wearing a beige tribal-style halter top with brown patterns and a matching skirt" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Muscular male with short grey hair and brown deer antlers", "attributes": "Shirtless, wearing a brown and white fur pelt over his right shoulder" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit cave with rocky brown walls" } ], "visual_description": "[PERSON_1] stands in the foreground, speaking with an angry and emotional expression. She gestures with her hands and briefly wipes her eye as if holding back tears. [PERSON_2] stands behind her to the right, maintaining a stoic expression. They are located in [SCENE_1].", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3", "DIALOGUE_4", "DIALOGUE_5", "DIALOGUE_6" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 1.6 ], "content": { "speaker": "PERSON_1", "line": "可那么多次", "description": "Angry and frustrated tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.6, 3.0 ], "content": { "speaker": "PERSON_1", "line": "你把我当傻子吗", "description": "Accusatory tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.0, 4.0 ], "content": { "speaker": "PERSON_1", "line": "明知道我最讨厌", "description": "Emotional and upset tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 4.8, 6.5 ], "content": { "speaker": "PERSON_1", "line": "你还要和她", "description": "Voice breaking slightly with emotion" } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 6.5, 8.3 ], "content": { "speaker": "PERSON_1", "line": "既然你这么喜欢她", "description": "Resolute and bitter tone" } }, { "event_id": "DIALOGUE_6", "type": "dialogue", "time_range": [ 8.3, 9.3 ], "content": { "speaker": "PERSON_1", "line": "那我今日就休了你", "description": "Firm and decisive tone" } } ], "scene_description": "A female character with deer antlers angrily confronts a male character, expressing feelings of betrayal regarding another woman and declaring a separation.", "global_style": "2D anime-style animation with a fantasy tribal aesthetic.", "global_audio": "Emotional voice acting with no prominent background music." } }, { "dataset": "drama_04", "clip_id": "clip_26695", "media_path": "drama_04/clip_26695.mp4", "source_media_path": "clips/clip_26695.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 9.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, red lips, and a complex traditional updo adorned with flowers and pearls", "attributes": "Purple embroidered robe, yellow ornate collar piece, pearl strings, elaborate floral hairpieces" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Out of focus background with wooden frames and blue panels" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], speaking with a serious and slightly sorrowful expression. She looks forward, then lowers her eyes briefly before looking back up.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3", "DIALOGUE_4", "DIALOGUE_5", "DIALOGUE_6" ] } ], "events": [ { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 5.4, 6.6 ], "content": { "speaker": "PERSON_1", "line": "原谅我", "description": "Apologetic tone" } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 6.6, 7.8 ], "content": { "speaker": "PERSON_1", "line": "只有这样", "description": "Explaining tone" } }, { "event_id": "DIALOGUE_6", "type": "dialogue", "time_range": [ 7.8, 9.0 ], "content": { "speaker": "PERSON_1", "line": "我才能确保你的安全", "description": "Protective and firm tone" } } ], "scene_description": "A woman in traditional attire delivers a dramatic monologue, expressing her resolve to protect someone named Duoyi.", "global_style": "Cinematic, dramatic lighting, traditional Chinese aesthetic.", "global_audio": "Quiet background, clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_59538", "media_path": "drama_04/clip_59538.mp4", "source_media_path": "clips/clip_59538.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with her hair tied up in a bun, wearing a black and white patterned jacket with large black lapels over a black top", "attributes": "Hair in a bun, black and white patterned jacket, black lapels, black top" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with dark hair tied back, wearing a light yellow button-up cardigan over a dark grey top", "attributes": "Dark hair tied back, light yellow cardigan, dark grey top" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Blurred background showing greenery and a building structure, indicating an outdoor environment" } ], "visual_description": "[PERSON_1] is seen from the front, looking anxious and speaking urgently to [PERSON_2], whose shoulder and the back of her head are visible in the foreground.", "camera": { "shot_type": "medium close-up, over-the-shoulder", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.9, 7.8 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], seen from the front, answering [PERSON_1]'s question with a slightly hesitant expression. [PERSON_1]'s shoulder is visible in the foreground.", "camera": { "shot_type": "medium close-up, over-the-shoulder", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "DIALOGUE_4", "DIALOGUE_5", "DIALOGUE_6" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.8, 9.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1], who looks down with a serious and concerned expression after hearing the answer.", "camera": { "shot_type": "medium close-up, over-the-shoulder", "angle": "eye-level", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 1.6 ], "content": { "speaker": "PERSON_1", "line": "都离开了", "description": "Urgent and anxious tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.6, 3.8 ], "content": { "speaker": "PERSON_1", "line": "他们去哪儿了快告诉我", "description": "Demanding and desperate tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.8, 5.7 ], "content": { "speaker": "PERSON_2", "line": "我听容先生打电话说", "description": "Hesitant and informative tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 5.7, 6.8 ], "content": { "speaker": "PERSON_2", "line": "好像是去了", "description": "Continuing explanation" } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 6.9, 7.6 ], "content": { "speaker": "PERSON_2", "line": "安山的那家", "description": "Providing specific location details" } }, { "event_id": "DIALOGUE_6", "type": "dialogue", "time_range": [ 7.6, 8.4 ], "content": { "speaker": "PERSON_2", "line": "精神病院了", "description": "Revealing shocking information" } } ], "scene_description": "A tense conversation between two women where one urgently asks for someone's whereabouts and the other reveals they went to a psychiatric hospital.", "global_style": "Dramatic television show style with close-up over-the-shoulder shots to emphasize dialogue and reactions.", "global_audio": "Dialogue-focused with no prominent background music or sound effects." } }, { "dataset": "drama_04", "clip_id": "clip_38446", "media_path": "drama_04/clip_38446.mp4", "source_media_path": "clips/clip_38446.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.6 ], "references": [ { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with dark walls, recessed ceiling lights, a beige sofa, a small coffee table, mannequins displaying dresses, and a makeup vanity with a round lighted mirror", "attributes": "dark walls, recessed lighting, beige sofa, coffee table, mannequins, makeup vanity with lighted mirror" }, { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with short black hair, wearing a black suit jacket over a black shirt, accessorized with a silver brooch", "attributes": "short black hair, black suit jacket, black shirt, silver brooch" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with dark hair styled in an elegant updo, wearing a shiny gold off-the-shoulder dress, dangling earrings, and a delicate necklace", "attributes": "dark hair in an updo, gold off-the-shoulder dress, dangling earrings, necklace" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A man with short dark hair, wearing a plain white shirt", "attributes": "short dark hair, white shirt" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "A woman with long dark hair, wearing a white long-sleeved top and light blue jeans", "attributes": "long dark hair, white long-sleeved top, light blue jeans" }, { "ref_id": "PERSON_6", "type": "person", "id_features": "A man wearing a black t-shirt, white shorts, and white sneakers", "attributes": "black t-shirt, white shorts, white sneakers" } ], "visual_description": "A wide shot of [SCENE_1]. [PERSON_1] stands on the left holding a script. [PERSON_2] and [PERSON_5] are sitting on the sofa. On the right, [PERSON_4] is seated at the vanity while [PERSON_6] styles his hair.", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.6, 2.8 ], "references": [ "PERSON_1" ], "visual_description": "A close-up shot of [PERSON_1] speaking directly to the group.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.8, 5.5 ], "references": [ "PERSON_2" ], "visual_description": "A close-up shot of [PERSON_2] looking down and reading a script.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 5.5, 7.8 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman with long, dark, wavy hair, wearing a white button-up shirt with ruffled details and a simple necklace", "attributes": "long dark wavy hair, white button-up shirt, necklace" } ], "visual_description": "A close-up shot of [PERSON_3] speaking with a confident and reassuring expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_5", "time_range": [ 7.8, 9.3 ], "references": [ "PERSON_4", "PERSON_6" ], "visual_description": "A close-up shot of [PERSON_4] turning his head to look back over his shoulder while [PERSON_6]'s hand is visible adjusting his hair.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_6", "time_range": [ 9.3, 10.4 ], "references": [ "PERSON_2" ], "visual_description": "A close-up shot of [PERSON_2] looking up from her script and speaking with a questioning expression.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 6.2 ], "content": { "speaker": "PERSON_1", "line": "净装完安排了唯读时间大家有空速读一下剧本", "description": "Informative and authoritative tone, giving instructions to the cast." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 6.2, 9.5 ], "content": { "speaker": "PERSON_3", "line": "放心我们家简行已经把所有台词都背下来了", "description": "Confident and reassuring tone, boasting about an actor's preparation." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 9.5, 10.2 ], "content": { "speaker": "PERSON_2", "line": "林小姐不是", "description": "Questioning and slightly confused tone." } } ], "scene_description": "In a studio dressing room, a director informs the cast about an upcoming script reading. An agent confidently claims her actor has already memorized his lines, prompting a confused question from an actress about the agent's actual role.", "global_style": "Modern, sleek, and slightly moody aesthetic with dark interiors contrasted by bright spotlighting.", "global_audio": "Clear dialogue with quiet, ambient room tone." } }, { "dataset": "drama_04", "clip_id": "clip_93551", "media_path": "drama_04/clip_93551.mp4", "source_media_path": "clips/clip_93551.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young girl with large, expressive brown eyes, rosy cheeks, and a sweet smile", "attributes": "Hair styled in two buns tied with pink ribbons, wearing a traditional Chinese-style outfit in light pink and blue" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A large, pale, smooth oval object resembling a giant egg or shell" } ], "visual_description": "[PERSON_1] is looking down, then looks up with a bright smile, presenting [OBJECT_1] in her hands.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "EVENT_1", "EVENT_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 5.2, 7.5 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A handsome adult male with sharp facial features, dark eyebrows, and a serious expression", "attributes": "Wearing a black robe with intricate gold dragon embroidery, and a gold crown-like headpiece" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An interior space with traditional Chinese architectural elements, including wooden screens, red lanterns, and a table laden with food" } ], "visual_description": "[PERSON_2] is sitting at a table in [SCENE_1], looking surprised and slightly confused as he speaks.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "EVENT_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.5, 10.0 ], "references": [ "PERSON_1", "OBJECT_1" ], "visual_description": "[PERSON_1] is shown again, smiling happily as she speaks, holding [OBJECT_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "EVENT_4" ] } ], "events": [ { "event_id": "EVENT_1", "type": "dialogue", "time_range": [ 0.6, 3.7 ], "content": { "speaker": "PERSON_2", "line": "谁的饭菜敢比皇宫还好", "description": "Questioning and slightly arrogant tone." } }, { "event_id": "EVENT_2", "type": "dialogue", "time_range": [ 3.7, 5.4 ], "content": { "speaker": "PERSON_1", "line": "爹爹你看", "description": "Cheerful and excited tone." } }, { "event_id": "EVENT_3", "type": "dialogue", "time_range": [ 5.4, 8.2 ], "content": { "speaker": "PERSON_2", "line": "你从哪儿找来这么大鸡蛋壳", "description": "Confused and surprised tone." } }, { "event_id": "EVENT_4", "type": "dialogue", "time_range": [ 8.2, 9.8 ], "content": { "speaker": "PERSON_1", "line": "爹爹这是我的壳", "description": "Innocent and happy tone." } } ], "scene_description": "A young girl presents a giant eggshell to her father, who is dressed as an emperor. He is surprised by the object, and she innocently claims it is her shell.", "global_style": "3D animated, vibrant colors, traditional Chinese fantasy aesthetic with highly expressive character designs.", "global_audio": "Clear dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_04", "clip_id": "clip_71785", "media_path": "drama_04/clip_71785.mp4", "source_media_path": "clips/clip_71785.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, long dark hair, and a red mark on her forehead", "attributes": "clothing: Light pink outer robe over a white inner garment with light blue floral patterns., hairstyle: Long dark hair partially tied up with a wooden hairpin., accessories: Butterfly-shaped dangling earrings, wooden hairpin" } ], "visual_description": "A close-up shot of the side of [PERSON_1]'s head, focusing on her ear, dark hair, and a butterfly-shaped dangling earring.", "camera": { "shot_type": "close-up", "angle": "side angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 3.5 ], "references": [ "PERSON_1", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A blurred background showing hints of foliage, flowers, and glowing lanterns" } ], "visual_description": "An extreme close-up of [PERSON_1]'s eye, with glowing lanterns reflected in her pupil.", "camera": { "shot_type": "extreme close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.5, 6.8 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "An over-the-shoulder shot focusing on the back of [PERSON_1]'s head, highlighting her wooden hairpin. The background [SCENE_1] is blurred.", "camera": { "shot_type": "over-the-shoulder", "angle": "rear angle", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 6.8, 8.2 ], "references": [ "PERSON_1" ], "visual_description": "A close-up shot of [PERSON_1]'s lips as she begins to speak.", "camera": { "shot_type": "close-up", "angle": "front angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 8.2, 10.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A medium shot of [PERSON_1] facing forward, speaking with a gentle expression. She is set against the blurred background of [SCENE_1].", "camera": { "shot_type": "medium shot", "angle": "front angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 2.4, 7.1 ], "content": { "speaker": "PERSON_1", "line": "其实我刚才席间所说也并不全是假话", "description": "Speaking in a calm, reflective tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 7.1, 9.8 ], "content": { "speaker": "PERSON_1", "line": "只不过往往还未等足半个时辰", "description": "Continuing her thought with a slightly melancholic tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 9.0 ], "content": { "description": "Soft, atmospheric background music." } } ], "scene_description": "A young woman in traditional attire reflects on a previous conversation, speaking softly in a serene, atmospheric setting.", "global_style": "3D animation with a realistic, cinematic style, featuring shallow depth of field and soft lighting.", "global_audio": "Quiet and intimate, with soft background music complementing the spoken dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_90083", "media_path": "drama_04/clip_90083.mp4", "source_media_path": "clips/clip_90083.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long brown hair tied half up, wearing silver hoop earrings and a delicate necklace", "attributes": "Black blazer with a large white lapel, black lace inner top" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit background, possibly a hotel corridor or upscale lobby, with warm golden tones" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A silver smartphone with a clear protective case" } ], "visual_description": "[PERSON_1] is standing in [SCENE_1], holding [OBJECT_1] with both hands. She looks intently at the screen, her expression shifting to one of slight concern or surprise.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 5.9, 10.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man seen from behind with short dark hair", "attributes": "Brown suit jacket" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A man seen from behind with short dark hair", "attributes": "Dark blue or black suit jacket" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A man seen from behind, partially obscuring the camera view", "attributes": "Dark suit jacket" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "A man seen from behind, standing still", "attributes": "Light beige or white zip-up hoodie over a dark shirt, dark pants" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A room with a grey sofa, a large flat-screen TV mounted on a white marble-patterned wall panel, wooden shelves, and a window with sheer white curtains" } ], "visual_description": "In [SCENE_2], [PERSON_2], [PERSON_3], and [PERSON_4] walk into the room from the foreground, their backs to the camera. They approach [PERSON_5], who is standing near the window in the background, facing away from them. The camera follows the men in suits as they move forward.", "camera": { "shot_type": "Wide shot", "angle": "Eye level", "movement": "Tracking forward" }, "active_events": [] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.0, 4.0 ], "content": { "description": "A series of digital notification or processing sounds." } } ], "scene_description": "A woman receives a concerning message on her phone, followed by a scene where a group of men in suits approach another man standing by a window in a modern apartment.", "global_style": "Modern, dramatic, with a mix of warm and cool lighting.", "global_audio": "Ambient room noise with a distinct digital notification sound effect." } }, { "dataset": "drama_04", "clip_id": "clip_77117", "media_path": "drama_04/clip_77117.mp4", "source_media_path": "clips/clip_77117.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, large brown eyes, and a red decorative mark on her forehead", "attributes": "Wearing traditional Chinese Hanfu in light peach and green colors, with elaborate golden hairpins and floral hair accessories" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Partially visible male figure", "attributes": "Wearing yellow and gold traditional clothing" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A translucent, golden-colored digital screen floating in mid-air with Chinese characters and numbers", "attributes": "Glowing, digital, floating" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden architectural elements, decorative panels, and warm lighting", "attributes": "Traditional, ornate, warm-toned" } ], "visual_description": "[PERSON_1] stands with her arms crossed, looking at [OBJECT_1] which displays the number 139.90. [PERSON_2] is partially visible seated on the left. The setting is [SCENE_1].", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.0, 7.5 ], "references": [ "PERSON_1", "OBJECT_1", "SCENE_1" ], "visual_description": "The camera focuses on [OBJECT_1] as the text changes and golden coins fall around it. [PERSON_1] is visible on the right side of the frame, listening.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Slight zoom in" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.5, 8.8 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "An extreme close-up of [PERSON_1]'s face. She is smiling broadly while tears of joy fall from her eyes.", "camera": { "shot_type": "Extreme close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_4" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.8, 10.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] clasps her hands together in a prayer-like gesture, looking upwards with a joyful and grateful expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 3.0 ], "content": { "speaker": "PERSON_1", "line": "代主能奖励受几斤不", "description": "Inquiring and hopeful tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.0, 6.5 ], "content": { "speaker": "PERSON_2", "line": "可以你每赢发财一把受益公斤", "description": "Calm and authoritative tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 6.7, 7.3 ], "content": { "speaker": "PERSON_2", "line": "公斤封", "description": "Informative tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.0, 7.0 ], "content": { "description": "Sound of digital interface chiming and coins clinking." } } ], "scene_description": "A woman in traditional attire interacts with a holographic system, asking if she can lose weight as a reward for playing a game. The system agrees, offering weight loss for winning, which brings the woman to tears of joy.", "global_style": "3D animation with a blend of traditional Chinese aesthetics and futuristic holographic elements.", "global_audio": "Clear dialogue with digital sound effects accompanying the holographic interface." } }, { "dataset": "drama_04", "clip_id": "clip_1278", "media_path": "drama_04/clip_1278.mp4", "source_media_path": "clips/clip_1278.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark, slightly messy hair, wearing a black leather jacket over a white undershirt, and a silver chain necklace", "attributes": "black leather jacket, white undershirt, silver chain necklace, dark hair" } ], "visual_description": "A close-up shot of [PERSON_1] looking slightly off-camera with a serious expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 4.2 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long dark wavy hair, wearing a loose white button-down shirt and shorts", "attributes": "white button-down shirt, shorts, long dark hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit street at night, featuring a building with a metal gate, a red sign with Chinese characters, and potted plants", "attributes": "nighttime, metal gate, red sign, potted plants, street lighting" } ], "visual_description": "A wide shot showing [PERSON_2] standing on the left side of the frame, facing [PERSON_1] who is standing by a metal gate on the right in [SCENE_1].", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.2, 8.6 ], "references": [ "PERSON_1", "SCENE_1", "PERSON_2" ], "visual_description": "A medium close-up of [PERSON_1] standing by the doorway, speaking and looking towards [PERSON_2] who is off-screen.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.6, 10.0 ], "references": [ "PERSON_2", "PERSON_1" ], "visual_description": "A close-up shot of [PERSON_2] looking towards [PERSON_1] off-screen with a thoughtful and slightly disappointed expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Soft, atmospheric background music playing throughout the scene." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 3.0, 5.4 ], "content": { "speaker": "PERSON_1", "line": "淌水店是我阿婆开的", "description": "Informative tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 5.4, 7.0 ], "content": { "speaker": "PERSON_1", "line": "你买来什么", "description": "Questioning tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.0, 7.6 ], "content": { "speaker": "PERSON_1", "line": "和我没关系", "description": "Dismissive and slightly cold tone." } } ], "scene_description": "A nighttime encounter between a young man and a young woman outside a building. The man clarifies his connection to a local shop and acts dismissive towards the woman's actions.", "global_style": "Cinematic, moody lighting with a slightly cool color palette, typical of a modern urban drama.", "global_audio": "Quiet nighttime ambiance with soft, emotional background music." } }, { "dataset": "drama_04", "clip_id": "clip_42169", "media_path": "drama_04/clip_42169.mp4", "source_media_path": "clips/clip_42169.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long black hair, wearing a black strapless dress and a pearl necklace with a bow design", "attributes": "clothing: Black strapless dress, hairstyle: Long black wavy hair, accessories: Pearl necklace with a bow" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor environment with modern decor, featuring a dark sofa and light-colored walls with shelving" } ], "visual_description": "[PERSON_1] sits on a dark sofa, looking slightly upwards with a concerned expression while speaking.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.8, 3.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short black hair, wearing a grey suit jacket over a white collared shirt", "attributes": "clothing: Grey suit jacket, white shirt, hairstyle: Short black hair parted to the side, accessories: None" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A small, rectangular blue device, possibly a card reader or POS machine" }, "SCENE_1" ], "visual_description": "[PERSON_2] holds [OBJECT_1] in his hands, looking down at it briefly before looking up to speak respectfully.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.8, 5.9 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with messy black hair and glasses, wearing a brown suit, black shirt, and red tie", "attributes": "clothing: Brown suit, black shirt, red tie, hairstyle: Messy black hair, accessories: Glasses, gold watch" }, "SCENE_1" ], "visual_description": "[PERSON_3] looks slightly downwards with a serious expression, listening to the ongoing conversation.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.9, 7.8 ], "references": [ { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman with long wavy hair, wearing a white dress with a sweetheart neckline and pearl buttons", "attributes": "clothing: White dress with pearl buttons, hairstyle: Long wavy hair, accessories: Necklace, earrings" }, "SCENE_1" ], "visual_description": "[PERSON_4] stands and listens attentively, looking slightly to the side.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_5", "time_range": [ 7.8, 10.0 ], "references": [ "PERSON_3", "SCENE_1" ], "visual_description": "[PERSON_3] looks forward and speaks with an expression of disbelief and curiosity.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 2.4 ], "content": { "speaker": "PERSON_1", "line": "你们要抓我呀", "description": "Nervous and questioning tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.4, 7.5 ], "content": { "speaker": "PERSON_2", "line": "不是数额太大您的身份太尊贵我们要加强人手保护好", "description": "Respectful and reassuring tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.5, 9.6 ], "content": { "speaker": "PERSON_3", "line": "您数额太大他有多少钱", "description": "Incredulous and curious tone." } } ], "scene_description": "A dramatic interaction where a woman fears arrest, but is instead treated with extreme reverence due to her immense wealth, much to the shock of an onlooker.", "global_style": "Modern, dramatic, high-contrast lighting typical of a short drama.", "global_audio": "Clear dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_04", "clip_id": "clip_86753", "media_path": "drama_04/clip_86753.mp4", "source_media_path": "clips/clip_86753.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, dark eyes, and long black hair", "attributes": "Wearing a light-colored, flowing Hanfu-style dress. Her hair is partially tied up in a traditional style" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A natural environment with a body of water in the background, surrounded by trees and foliage. Warm, golden sunlight creates a hazy, ethereal atmosphere", "attributes": "Trees, leaves, water, sunlight, haze" } ], "visual_description": "[PERSON_1] is sitting outdoors in [SCENE_1], looking slightly to the right with a calm expression. The background is softly blurred with sunlight filtering through the leaves.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.5, 10.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] is lying down in [SCENE_1] with her eyes closed, appearing to rest or sleep. Warm sunlight illuminates her face. Various system reward icons and text appear sequentially on the screen.", "camera": { "shot_type": "Close-up", "angle": "Low angle", "movement": "Static" }, "active_events": [ "DIALOGUE_3", "DIALOGUE_4", "DIALOGUE_5", "DIALOGUE_6", "DIALOGUE_7" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.2, 2.8 ], "content": { "speaker": "PERSON_2", "line": "三十分之五", "description": "Neutral, automated system voice." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.8, 4.1 ], "content": { "speaker": "PERSON_2", "line": "继续保持", "description": "Neutral, automated system voice." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 4.1, 5.6 ], "content": { "speaker": "PERSON_2", "line": "奖励预览", "description": "Neutral, automated system voice." } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 5.9, 7.2 ], "content": { "speaker": "PERSON_2", "line": "乘二", "description": "Neutral, automated system voice." } }, { "event_id": "DIALOGUE_6", "type": "dialogue", "time_range": [ 7.2, 9.7 ], "content": { "speaker": "PERSON_2", "line": "大米乘五零金银子乘十", "description": "Neutral, automated system voice." } } ], "scene_description": "A young woman in ancient attire is resting in a serene outdoor setting while a system interface displays her survival days and upcoming rewards.", "global_style": "Cinematic, ethereal, ancient Chinese fantasy aesthetic with warm, golden lighting and soft focus.", "global_audio": "A calm, automated female voiceover narrating system messages." } }, { "dataset": "drama_04", "clip_id": "clip_39509", "media_path": "drama_04/clip_39509.mp4", "source_media_path": "clips/clip_39509.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A bald man with prominent scars on his forehead, thick dark eyebrows, a long mustache, and a pointed goatee. He has a stern and intense expression", "attributes": "Wearing a grey, textured robe" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A muddy, wet ground at night with a dark, cloudy sky and faint silhouettes of mountains in the background" } ], "visual_description": "[PERSON_1] looks slightly to the side with a sharp, intimidating gaze while speaking.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.2, 4.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "An elderly woman with deep wrinkles, dirt smudged on her face, and messy, greying hair tied back loosely. She has wide, fearful eyes", "attributes": "Wearing a worn, patched, and dirty blue garment" }, "SCENE_1" ], "visual_description": "[PERSON_2] looks up with an expression of sheer terror and shock.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 4.2, 5.6 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] maintains his stern, unwavering stare.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 5.6, 8.6 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] lowers her head, looking down submissively and pleadingly as she speaks, clutching her hands near her chest.", "camera": { "shot_type": "close-up", "angle": "high-angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_5", "time_range": [ 8.6, 10.0 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A middle-aged man lying on his side, looking distressed and exhausted", "attributes": "Wearing a dirty yellowish-brown tunic and a headband, with his arms bound by thick ropes" }, "SCENE_1" ], "visual_description": "[PERSON_3] is shown lying on the wet, muddy ground, bound tightly with ropes, looking helpless.", "camera": { "shot_type": "medium shot", "angle": "high-angle", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.4, 8.5 ], "content": { "speaker": "PERSON_2", "line": "我说的都是真的", "description": "Desperate pleading tone." } } ], "scene_description": "A tense interrogation scene where a menacing man threatens a terrified old woman, while another man lies bound on the muddy ground nearby.", "global_style": "Dark, gritty 3D animation with realistic textures, dramatic lighting, and a somber color palette.", "global_audio": "Quiet ambient night sounds with subtle, tense background noise." } }, { "dataset": "drama_04", "clip_id": "clip_47008", "media_path": "drama_04/clip_47008.mp4", "source_media_path": "clips/clip_47008.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Middle-aged man with a distressed expression, hair tied in a topknot", "attributes": "Wears dark robes, including a patterned vest in the first scene and a plain dark robe with a white inner collar in the second" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Dimly lit environment with indistinct background" } ], "visual_description": "[PERSON_1] is kneeling on the ground in [SCENE_1], looking highly distressed. He speaks while bowing his head towards the ground.", "camera": { "shot_type": "medium shot", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 7.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Young woman with a serious expression", "attributes": "Hair styled up with silver ornaments, wearing a red and white outfit with gold embroidery" }, "SCENE_1" ], "visual_description": "[PERSON_2] stands in [SCENE_1], looking downwards with a serious and slightly sympathetic expression.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 7.7, 9.9 ], "references": [ "PERSON_1", { "ref_id": "SCENE_2", "type": "scene", "id_features": "Stone steps leading up to a traditional building with wooden doors and decorative elements" } ], "visual_description": "In [SCENE_2], [PERSON_1] is kneeling and looking up with a pleading expression, speaking earnestly with his hands clasped together.", "camera": { "shot_type": "medium close-up", "angle": "slightly high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.9, 10.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_3", "type": "person", "id_features": "Man with an impassive expression, hair tied up", "attributes": "Wears a black robe with white trim" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "Man standing attentively", "attributes": "Wears a teal and blue outfit with a black hat" }, "SCENE_2" ], "visual_description": "A wider view of [SCENE_2] shows [PERSON_1] kneeling on the stone steps, bowing his head all the way to the ground. [PERSON_3] stands above him on the landing, looking down impassively. [PERSON_4] stands to the side, observing.", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.8, 3.1 ], "content": { "speaker": "PERSON_1", "line": "放过老奴", "description": "Desperate pleading." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.1, 8.1 ], "content": { "speaker": "PERSON_1", "line": "孟族馆还请您高抬贵手放过瑶儿吧", "description": "Earnest and emotional begging." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 8.1, 8.6 ], "content": { "speaker": "PERSON_1", "line": "我给你磕头", "description": "Submissive pleading." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 8.5, 9.5 ], "content": { "description": "Thud sound of a head hitting the stone ground." } } ], "scene_description": "A man is shown desperately begging for mercy in two different settings, pleading with authority figures to spare him and someone named Yao'er.", "global_style": "Historical drama with dramatic lighting and traditional costumes.", "global_audio": "Emotional dialogue with subtle ambient background noise." } }, { "dataset": "drama_04", "clip_id": "clip_83641", "media_path": "drama_04/clip_83641.mp4", "source_media_path": "clips/clip_83641.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with dark hair styled in a side braid, wearing a white lace capelet, a pearl necklace, pearl drop earrings, a white flower hair accessory, and a light green jade bracelet on her left wrist", "attributes": "white lace capelet, pearl necklace, pearl earrings, white flower hair accessory, side braid, jade bracelet" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A dark red, polished wooden frame with curved edges, possibly part of a mirror or piece of furniture", "attributes": "dark red, polished wood, curved" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor background featuring a fabric drape with a large, ornate floral pattern in muted gold, brown, and cream tones", "attributes": "floral pattern, fabric drape, muted colors" } ], "visual_description": "A close-up focuses on the left hand of [PERSON_1] tightly gripping the edge of [OBJECT_1]. The background consists of the floral fabric of [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.4, 9.7 ], "references": [ "PERSON_1", "OBJECT_1", "SCENE_1" ], "visual_description": "The camera cuts to a medium shot revealing [PERSON_1] standing behind [OBJECT_1]. She maintains a cold, intense expression as she speaks. A sudden bright visual flash effect occurs over the scene towards the end of the shot.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 3.5 ], "content": { "speaker": "PERSON_1", "line": "既然你这么放不开他,那,就一块去死吧", "description": "Cold, angry, and threatening tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 6.5, 8.0 ], "content": { "description": "A dramatic, echoing sound effect accompanying a visual flash." } } ], "scene_description": "A woman delivers a cold and threatening ultimatum, gripping a wooden frame with intense emotion.", "global_style": "Dramatic and tense, with a vintage or period-piece aesthetic characterized by the costume and set design.", "global_audio": "Quiet ambient background focusing entirely on the character's dialogue, punctuated by a dramatic sound effect." } }, { "dataset": "drama_04", "clip_id": "clip_32287", "media_path": "drama_04/clip_32287.mp4", "source_media_path": "clips/clip_32287.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin and dark eyes", "attributes": "Wearing a light green traditional Chinese dress over a white top, a pearl necklace, and her black hair is styled in an updo adorned with silver hairpins, with a long strand falling over her right shoulder" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring a wooden lattice screen with a blue background and a lit candle", "attributes": "Traditional Chinese interior, warm and soft lighting" } ], "visual_description": "[PERSON_1] is seen from the chest up, speaking thoughtfully while looking slightly downward and then forward. The background is slightly blurred, showing parts of [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.0, 9.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with fair skin, sharp facial features, and dark eyes", "attributes": "Wearing a layered white traditional Chinese robe. His long black hair is partially tied up, with strands framing his face" }, "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], who is listening intently. He maintains a serious expression, then speaks briefly. After speaking, he turns his head slightly to his left. [SCENE_1] is visible in the background with a lattice screen and a candle.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 7.2 ], "content": { "speaker": "PERSON_1", "line": "若非發現巨大金礦那就是通過貿易大樑除了墨北肯定還有更大的貿易對象", "description": "Analytical and serious tone, explaining a deduction." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 7.2, 7.9 ], "content": { "speaker": "PERSON_2", "line": "有點意思", "description": "Intrigued and calm tone." } } ], "scene_description": "Two characters in a historical setting are discussing economic and trade strategies, deducing the existence of a large trading partner.", "global_style": "Historical Chinese drama aesthetic, featuring elegant traditional costumes, soft lighting, and a serious, contemplative mood.", "global_audio": "Quiet ambient room tone with clear, prominent dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_22172", "media_path": "drama_04/clip_22172.mp4", "source_media_path": "clips/clip_22172.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair and a serious expression", "attributes": "white turtleneck, light grey jacket" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A standard black smartphone" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Dark interior of a vehicle, illuminated slightly by outside lights" } ], "visual_description": "A close-up profile shot of [PERSON_1] holding [OBJECT_1] to his ear inside [SCENE_1]. He has a serious expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.3, 6.0 ], "references": [ "PERSON_1", "OBJECT_1", "SCENE_1" ], "visual_description": "A medium shot from the passenger side showing [PERSON_1] lowering [OBJECT_1] from his ear. He stares blankly forward, deep in thought.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.0, 8.7 ], "references": [ "PERSON_1", { "ref_id": "OBJECT_2", "type": "object", "id_features": "The exterior side mirror of a dark-colored car, reflecting the driver's face" }, "SCENE_1" ], "visual_description": "A close-up shot focusing on [OBJECT_2] outside the car. The mirror clearly reflects the face of [PERSON_1], who is looking intently.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1", "SFX_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.7, 10.0 ], "references": [ "PERSON_1", "OBJECT_2" ], "visual_description": "The previous shot of [OBJECT_2] fades out with a bright, stylized light effect as text appears on the screen.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Dramatic and suspenseful instrumental background music." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 6.0, 8.0 ], "content": { "description": "A deep, resonant sound effect emphasizing the dramatic moment." } } ], "scene_description": "A man sits alone in his car at night, finishing a phone call with a serious expression, ending on a cliffhanger.", "global_style": "Dark, moody, cinematic lighting with a suspenseful tone.", "global_audio": "Suspenseful background music." } }, { "dataset": "drama_04", "clip_id": "clip_89856", "media_path": "drama_04/clip_89856.mp4", "source_media_path": "clips/clip_89856.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.6 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long black hair styled half-up, wearing pearl earrings", "attributes": "Floral jacket, white blouse with a large bow, blue jeans" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Outdoor area with red doors and festive decorations visible in the background", "attributes": "Outdoor, daytime, red doors, decorations" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], looking slightly disappointed and speaking to someone off-camera.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.6, 3.5 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair", "attributes": "Green jacket with a fur collar, brown shirt, tie, lanyard" }, "SCENE_1" ], "visual_description": "[PERSON_2] looks off-camera with a serious and slightly confused expression.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.5, 8.2 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] continues speaking, gesturing with her hands, and looking off-camera.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.2, 9.5 ], "references": [ "PERSON_1", { "ref_id": "PERSON_3", "type": "person", "id_features": "A young woman with black hair wearing a white headband", "attributes": "Green jacket with a fur collar, white blouse" }, "SCENE_1" ], "visual_description": "[PERSON_1] turns her head to the side to call out to someone, continuing to speak. [PERSON_3] is briefly visible in the background.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] }, { "shot_id": "SHOT_5", "time_range": [ 9.5, 10.7 ], "references": [ { "ref_id": "PERSON_4", "type": "person", "id_features": "An older woman with curly black hair styled up, wearing gold earrings", "attributes": "Green jacket with a fur collar, white turtleneck" }, "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_4] turns her head sharply, looking surprised and offended. [PERSON_2] is visible in the background.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_5" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.0, 2.0 ], "content": { "description": "A comedic, cartoonish sound effect indicating confusion or surprise." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.8, 3.8 ], "content": { "speaker": "PERSON_1", "line": "这怎么要走啊", "description": "Questioning tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.8, 5.8 ], "content": { "speaker": "PERSON_1", "line": "我看见正高潮呢", "description": "Complaining tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 5.8, 9.8 ], "content": { "speaker": "PERSON_1", "line": "妈他刚说你年轻的时候唱歌跑调", "description": "Instigating, tattletale tone" } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 9.8, 10.1 ], "content": { "speaker": "PERSON_4", "line": "什么", "description": "Surprised and offended tone" } } ], "scene_description": "A comedic interaction where a young woman complains about someone leaving, then stirs up trouble by telling an older woman that the man insulted her singing.", "global_style": "Bright, clear, television drama style with comedic elements.", "global_audio": "Clear dialogue with a comedic sound effect." } }, { "dataset": "drama_04", "clip_id": "clip_7846", "media_path": "drama_04/clip_7846.mp4", "source_media_path": "clips/clip_7846.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair", "attributes": "Black suit, black shirt, patterned tie, black shoes" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A white sports car with butterfly doors", "attributes": "White exterior, butterfly doors" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A street or parking area with trees and parked cars in the background", "attributes": "Outdoor, daytime, paved ground" } ], "visual_description": "[PERSON_1] exits [OBJECT_1], stands up, and gestures with his hand, inviting someone to enter the car.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.0, 7.1 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long brown hair styled in two braids", "attributes": "Black blazer, white collared shirt, black top, black shorts, black knee-high socks, black chunky shoes, black choker necklace" }, "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] stands and looks towards [PERSON_1].", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.1, 10.0 ], "references": [ "PERSON_1", "PERSON_2", "OBJECT_1", "SCENE_1" ], "visual_description": "[PERSON_2] walks towards [OBJECT_1] and sits down inside while [PERSON_1] holds the door open.", "camera": { "shot_type": "Full shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Upbeat background music." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 3.5, 3.6 ], "content": { "speaker": "PERSON_1", "line": "上车", "description": "Inviting tone." } } ], "scene_description": "A man gets out of a sports car and invites a woman to get in. She walks over and enters the car.", "global_style": "Modern, casual, slightly dramatic.", "global_audio": "Upbeat background music with a brief line of dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_62986", "media_path": "drama_04/clip_62986.mp4", "source_media_path": "clips/clip_62986.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young girl with her hair styled in buns tied with green ribbons, wearing a green patterned top", "attributes": "clothing: Green patterned top, hairstyle: Hair buns with green ribbons, accessories: Green ribbons" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman wearing a white top with colorful embroidered sleeves", "attributes": "clothing: White top with colorful embroidered sleeves, hairstyle: Not fully visible, accessories: None visible" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A rustic outdoor area with wooden structures, fences, and dirt ground" } ], "visual_description": "[PERSON_2] is holding and comforting a crying [PERSON_1].", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.2, 4.8 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with long dark hair, wearing a purple and grey outfit with a fur piece on his left shoulder", "attributes": "clothing: Purple and grey outfit, fur shoulder piece, hairstyle: Long dark hair tied half up, accessories: Fur shoulder piece" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman wearing a light pink dress, with her hair styled up and decorated with pink flower accessories", "attributes": "clothing: Light pink dress, hairstyle: Updo, accessories: Pink flower hair accessories, dangling earrings" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "A man wearing a brown vest over a grey shirt, with a blue headband", "attributes": "clothing: Brown vest, grey shirt, hairstyle: Tied up, accessories: Blue headband" }, { "ref_id": "PERSON_6", "type": "person", "id_features": "A woman wearing a white top and a light blue skirt, kneeling on the ground", "attributes": "clothing: White top, light blue skirt, hairstyle: Tied up with a white ribbon, accessories: White hair ribbon" }, "SCENE_1" ], "visual_description": "[PERSON_3] and [PERSON_4] are standing together, looking down at [PERSON_5] and [PERSON_6] who are kneeling on the ground. [PERSON_4] speaks to [PERSON_3].", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.8, 5.8 ], "references": [ "PERSON_5", "SCENE_1" ], "visual_description": "[PERSON_5] looks up with a surprised and relieved expression.", "camera": { "shot_type": "Close-up", "angle": "High angle", "movement": "Static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 5.8, 7.0 ], "references": [ "PERSON_3", "SCENE_1", "PERSON_4" ], "visual_description": "[PERSON_3] turns his head to look at [PERSON_4].", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [] }, { "shot_id": "SHOT_5", "time_range": [ 7.0, 8.6 ], "references": [ "PERSON_4", "SCENE_1", "PERSON_3" ], "visual_description": "[PERSON_4] looks back at [PERSON_3].", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [] }, { "shot_id": "SHOT_6", "time_range": [ 8.6, 10.0 ], "references": [ "PERSON_3", "SCENE_1" ], "visual_description": "[PERSON_3] speaks while looking forward.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 9.1, 9.3 ], "content": { "speaker": "PERSON_1", "line": "娘", "description": "Crying out for mother" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 9.3, 9.9 ], "content": { "speaker": "PERSON_3", "line": "子都說了", "description": "Speaking calmly, yielding to his wife's request" } } ], "scene_description": "A tense situation in a village where a couple decides to show mercy to people kneeling before them, after a child is seen crying.", "global_style": "Historical Chinese drama aesthetic with traditional costumes and rustic settings.", "global_audio": "Dramatic background music with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_91004", "media_path": "drama_04/clip_91004.mp4", "source_media_path": "clips/clip_91004.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, wearing elaborate traditional Chinese makeup and hair ornaments", "attributes": "Pink traditional Chinese dress, intricate updo hairstyle with gold and floral hairpins, pearl necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A person wearing a uniform, face partially obscured by a hat and mask", "attributes": "Purple robe, black hat, white face mask" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor covered walkway with red wooden pillars, green lattice railings, and decorative painted beams" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A round, shallow brass basin containing water" } ], "visual_description": "[PERSON_1] walks forward in [SCENE_1]. [PERSON_2] walks in the opposite direction, carrying [OBJECT_1].", "camera": { "shot_type": "Long shot", "angle": "Eye level", "movement": "Static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 2.7, 5.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1", "OBJECT_1" ], "visual_description": "[PERSON_1] and [PERSON_2] bump into each other. [PERSON_2] drops [OBJECT_1], spilling water. [PERSON_1] is startled and steps back.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Pan slightly to follow action" }, "active_events": [ "EVENT_1", "EVENT_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.7, 7.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1", "OBJECT_1" ], "visual_description": "[PERSON_2] kneels on the floor, holding [OBJECT_1], bowing repeatedly in apology. [PERSON_1] stands nearby, looking down.", "camera": { "shot_type": "Medium shot", "angle": "High angle", "movement": "Static" }, "active_events": [ "EVENT_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 7.7, 10.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_1] looks down calmly and speaks to [PERSON_2].", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "EVENT_4" ] } ], "events": [ { "event_id": "EVENT_2", "type": "sfx", "time_range": [ 3.0, 4.0 ], "content": { "description": "Metallic clatter of basin dropping and water splashing" } }, { "event_id": "EVENT_3", "type": "dialogue", "time_range": [ 6.3, 8.8 ], "content": { "speaker": "PERSON_2", "line": "奴才该死奴才该死", "description": "Panicked, apologetic tone" } }, { "event_id": "EVENT_4", "type": "dialogue", "time_range": [ 8.8, 10.3 ], "content": { "speaker": "PERSON_1", "line": "罢了你也不是故意的", "description": "Calm, forgiving tone" } } ], "scene_description": "A servant accidentally bumps into a noblewoman in a palace corridor, dropping a water basin. The servant panics and apologizes profusely, but the noblewoman calmly forgives him.", "global_style": "Historical Chinese drama aesthetic with vibrant colors, traditional costumes, and classical architecture.", "global_audio": "Subtle background music with ambient outdoor sounds." } }, { "dataset": "drama_04", "clip_id": "clip_44717", "media_path": "drama_04/clip_44717.mp4", "source_media_path": "clips/clip_44717.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, wearing a light-colored jacket over a black shirt and a silver necklace", "attributes": "short black hair, light-colored jacket, black shirt, silver necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long wavy brown hair, wearing a dark grey high-necked dress", "attributes": "long wavy brown hair, dark grey dress, high neck" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A lounge area with orange sofas, tables, and blurred figures in the background", "attributes": "orange sofas, tables, dim lighting, background people" } ], "visual_description": "[PERSON_1] and [PERSON_2] are sitting on an orange sofa in [SCENE_1]. [PERSON_1] leans towards [PERSON_2] and speaks. [PERSON_2] smiles and replies.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 5.2, 7.5 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "Close-up of [PERSON_1] looking affectionately at [PERSON_2] and smiling.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.5, 9.3 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_1] puts his arm around [PERSON_2]'s shoulders as they sit on the sofa in [SCENE_1].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.3, 9.7 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "Close-up of [PERSON_1] and [PERSON_2]. [PERSON_2] leans her head on [PERSON_1]'s shoulder, both looking content.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.8, 4.0 ], "content": { "speaker": "PERSON_1", "line": "怎么样我刚才的表演还不错吧", "description": "Confident and playful inquiry" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.0, 4.4 ], "content": { "speaker": "PERSON_2", "line": "很不错", "description": "Warm and approving response" } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Soft, romantic background music" } } ], "scene_description": "A man and a woman are sitting together in a lounge. They share a brief conversation before the man puts his arm around the woman and she leans on his shoulder affectionately.", "global_style": "Romantic, warm lighting, cinematic.", "global_audio": "Soft background music and dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_67417", "media_path": "drama_04/clip_67417.mp4", "source_media_path": "clips/clip_67417.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin and dark hair styled in an elaborate traditional updo with hairpins", "attributes": "Wearing a white traditional Chinese dress with pink accents and a red sash" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious room with wooden partitions, a large ornate bed with sheer curtains, a patterned rug, and floral arrangements" } ], "visual_description": "A medium shot of [PERSON_1] standing in [SCENE_1]. She looks slightly off-camera with a sarcastic expression while speaking.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "EVENT_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.0, 9.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with dark hair styled in a traditional updo", "attributes": "Wearing a purple traditional Chinese dress" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman with dark hair", "attributes": "Wearing a dark grey or black traditional Chinese dress" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman with dark hair", "attributes": "Wearing light-colored traditional clothing" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "A person lying down, mostly obscured", "attributes": "Covered by a red blanket" }, "SCENE_1" ], "visual_description": "A wide shot of [SCENE_1]. [PERSON_1] turns and walks towards the back of the room. In the middle of the room, [PERSON_2] points angrily, but [PERSON_3] holds her back and gestures for her to leave. In the background, [PERSON_4] sits beside [PERSON_5], who is lying on the bed. The shot ends with a bright white flash transition.", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "EVENT_2", "EVENT_3" ] } ], "events": [ { "event_id": "EVENT_1", "type": "dialogue", "time_range": [ 0.5, 1.9 ], "content": { "speaker": "PERSON_1", "line": "这算盘打得真", "description": "Sarcastic and mocking tone." } }, { "event_id": "EVENT_2", "type": "dialogue", "time_range": [ 6.0, 6.1 ], "content": { "speaker": "PERSON_2", "line": "你", "description": "Angry, accusatory tone." } }, { "event_id": "EVENT_3", "type": "dialogue", "time_range": [ 6.1, 6.7 ], "content": { "speaker": "PERSON_3", "line": "别动你走", "description": "Urgent, commanding tone." } } ], "scene_description": "A tense confrontation in a traditional Chinese bedroom where a woman makes a sarcastic remark before walking away, causing another woman to react angrily while being restrained.", "global_style": "Historical Chinese drama aesthetic with elaborate costumes, traditional set design, and soft, naturalistic lighting.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_17118", "media_path": "drama_04/clip_17118.mp4", "source_media_path": "clips/clip_17118.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 7.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, dark eyes, and black hair styled in an elegant updo", "attributes": "Wearing a white sheer top over an orange dress, adorned with pearl hairpins featuring long orange tassels" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden architectural elements, featuring a wooden bed with white pillows and bedding", "attributes": "Traditional, indoor, bedroom setting" } ], "visual_description": "A close-up shot of [PERSON_1] looking slightly downward with a melancholic and thoughtful expression. She speaks softly and then lets out a sigh.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 7.8, 10.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young girl with fair skin and black hair styled in two buns", "attributes": "Wearing a light purple traditional dress with pink ribbons in her hair" }, "SCENE_1" ], "visual_description": "A medium shot showing [PERSON_2] sitting on a bed, rubbing her eye as if she has been crying. [PERSON_1] leans into the frame from the right side, looking affectionately at [PERSON_2] and speaking to her.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.9, 8.7 ], "content": { "speaker": "PERSON_1", "line": "坐在皇宫里就不会整日野的找不到人一定会是被教养得极好的大家闺秀吧", "description": "Thoughtful and slightly melancholic tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 6.0, 7.0 ], "content": { "description": "A soft sigh." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 8.7, 9.5 ], "content": { "speaker": "PERSON_1", "line": "你又看中什么了", "description": "Gentle, inquiring tone." } } ], "scene_description": "A woman reflects melancholically on how a child's life might have been different and more refined in a palace setting, before gently asking the upset child what has caught her attention.", "global_style": "3D animated, traditional Chinese historical fantasy aesthetic with soft, warm lighting.", "global_audio": "Quiet ambient background with clear, expressive dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_97571", "media_path": "drama_04/clip_97571.mp4", "source_media_path": "clips/clip_97571.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with dark hair tied up, wearing a white suit jacket over a white top, and a layered pearl necklace", "attributes": "White suit jacket, white top, layered pearl necklace, dark hair tied up" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A well-lit conference room featuring a large, highly reflective glass table surrounded by wooden chairs", "attributes": "Reflective glass table, wooden chairs, bright lighting" } ], "visual_description": "[PERSON_1] is seated at a reflective glass table in [SCENE_1], speaking directly. Her reflection is clearly visible on the table surface.", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.3, 7.1 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with dark hair, wearing a bright red top", "attributes": "Red top, dark hair" }, "SCENE_1" ], "visual_description": "[PERSON_1] stands up from the table in [SCENE_1] and begins to walk away. [PERSON_2] is seated in the foreground, partially visible from behind.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.1, 10.5 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with short dark hair, wearing a grey suit jacket over a dark t-shirt", "attributes": "Grey suit jacket, dark t-shirt, short dark hair" }, "SCENE_1" ], "visual_description": "A wide view of [SCENE_1] showing multiple people seated around the large glass table. [PERSON_3] is seen speaking from across the table.", "camera": { "shot_type": "Wide shot", "angle": "High angle", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 10.5, 12.0 ], "references": [ "PERSON_3", "SCENE_1" ], "visual_description": "A medium close-up of [PERSON_3] speaking while seated at the table in [SCENE_1].", "camera": { "shot_type": "Medium close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 3.6 ], "content": { "speaker": "PERSON_1", "line": "强盛集团的王总还来找我谈合作我就先行一步", "description": "Confident and assertive statement." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 5.3, 5.6 ], "content": { "speaker": "PERSON_2", "line": "王总", "description": "Surprised exclamation." } } ], "scene_description": "A business meeting in a conference room where a woman announces she is leaving to meet a prominent figure, leaving the other attendees surprised and impressed.", "global_style": "Modern, professional, corporate aesthetic with clean lighting.", "global_audio": "Clear dialogue with natural room acoustics." } }, { "dataset": "drama_04", "clip_id": "clip_20732", "media_path": "drama_04/clip_20732.mp4", "source_media_path": "clips/clip_20732.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long brown hair, half tied up, wearing gold hoop earrings", "attributes": "White blazer over a light-colored top" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair", "attributes": "White cardigan over a blue collared shirt, beige pants" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with large windows, bright natural light, and blurred figures in the background" } ], "visual_description": "[PERSON_1] and [PERSON_2] are standing next to each other in [SCENE_1]. [PERSON_1] turns her head slightly to speak to [PERSON_2].", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.4, 5.8 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "Close-up of [PERSON_2] looking slightly down and then up, listening intently.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.8, 9.0 ], "references": [ "PERSON_1", "SCENE_1", "PERSON_2" ], "visual_description": "Close-up of [PERSON_1] looking directly at [PERSON_2] while speaking.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.0, 10.0 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "Close-up of [PERSON_2] looking slightly down, reacting to what was just said.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.8, 7.5 ], "content": { "speaker": "PERSON_1", "line": "你和他的单人不一样", "description": "Assertive and explanatory tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 7.5, 8.6 ], "content": { "speaker": "PERSON_1", "line": "你是我亲戚家的孩子", "description": "Factual, slightly dismissive tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Soft, dramatic background music." } } ], "scene_description": "A woman explains to a man that he is different from others because he is a relative's child, while he listens with a serious expression.", "global_style": "Bright, modern, soft lighting, dramatic.", "global_audio": "Clear dialogue with soft, dramatic background music." } }, { "dataset": "drama_04", "clip_id": "clip_3004", "media_path": "drama_04/clip_3004.mp4", "source_media_path": "clips/clip_3004.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with a pale complexion, wearing traditional Chinese attire, looking distressed and emotional", "attributes": "Pale yellow outer robe, light blue inner dress with embroidery, elaborate silver and pearl hair ornaments, long black hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit room with blurred background elements, including what appears to be red flowers and wooden architectural details" } ], "visual_description": "A close-up shot of [PERSON_1] looking distressed and speaking, with her gaze directed slightly off-camera.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.7, 6.1 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "An older woman with a serious and concerned expression, wearing rich traditional clothing", "attributes": "Teal green outer robe, red inner dress with gold embroidery, heavy gold and pearl headdress, pearl necklace" }, "SCENE_1" ], "visual_description": "A medium shot showing [PERSON_1] talking to [PERSON_2]. [PERSON_1] clutches her chest with her right hand as she speaks.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.1, 9.5 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A close-up shot of [PERSON_1] continuing to speak. She looks down briefly and then back up, her expression pained.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.5, 12.0 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "A close-up shot of [PERSON_2] listening with a serious and concerned expression while [PERSON_1] speaks off-screen.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.6, 2.9 ], "content": { "speaker": "PERSON_1", "line": "反复梦到表哥被克死", "description": "Distressed and emotional tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.9, 6.3 ], "content": { "speaker": "PERSON_1", "line": "醒来后我我就心惊得厉害", "description": "Anxious and pained tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 6.3, 9.7 ], "content": { "speaker": "PERSON_1", "line": "并且离表哥越近我的心就越痛", "description": "Suffering and vulnerable tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 9.7, 11.7 ], "content": { "speaker": "PERSON_1", "line": "来到表哥门前时我的心", "description": "Trailing off, overwhelmed with emotion." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 11.0 ], "content": { "description": "Dramatic and melancholic background music." } } ], "scene_description": "A young woman tearfully recounts a recurring nightmare and physical pain associated with her cousin to an older woman.", "global_style": "Traditional Chinese historical drama aesthetic with soft lighting and emotional framing.", "global_audio": "Spoken dialogue accompanied by dramatic, melancholic background music." } }, { "dataset": "drama_04", "clip_id": "clip_44783", "media_path": "drama_04/clip_44783.mp4", "source_media_path": "clips/clip_44783.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short dark hair", "attributes": "Black button-down shirt, dark trousers, holding a glass with a yellow liquid" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Dimly lit interior with green neon strip lights, glass railings, and modern chandeliers" } ], "visual_description": "[PERSON_1] leans against a glass railing on a mezzanine level, holding a glass and looking down. The lighting is dark with green neon accents.", "camera": { "shot_type": "medium shot", "angle": "low angle", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 4.6 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long wavy dark hair and earrings", "attributes": "White turtleneck sweater, beige coat" }, "SCENE_1" ], "visual_description": "[PERSON_2] looks up with a serious and slightly angry expression, speaking directly to someone off-screen.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.6, 10.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera returns to the low angle view of [PERSON_1] on the balcony. He stops leaning, stands up straight, and continues to look down. The back of [PERSON_2]'s head is visible in the blurry foreground.", "camera": { "shot_type": "medium shot", "angle": "low angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 1.9 ], "content": { "speaker": "PERSON_2", "line": "那我也烦请陈总自重", "description": "Stern and warning tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.9, 4.2 ], "content": { "speaker": "PERSON_2", "line": "不要做一些无耻之事", "description": "Firm and accusatory tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Tense, dramatic background music." } } ], "scene_description": "A tense confrontation between a woman and a man standing on a balcony in a dimly lit lounge.", "global_style": "Dark, moody, cinematic lighting with green neon accents.", "global_audio": "Dramatic background music with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_49890", "media_path": "drama_04/clip_49890.mp4", "source_media_path": "clips/clip_49890.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with long dark hair styled with braids and an elaborate gold headpiece", "attributes": "Dark blue and teal robes with gold embroidery, elaborate gold headpiece, long dark hair with braids" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with wooden pillars, warm lighting, and traditional Chinese architectural elements" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], speaking with a serious expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.1, 3.5 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "An older man with long white hair and a long white beard, wearing a silver headpiece", "attributes": "Grey and brown patterned robe, silver headpiece, long white hair, long white beard" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with dark hair and a small headpiece", "attributes": "Purple robes with gold trim, dark hair, small headpiece" }, "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] looks towards [PERSON_1] and speaks. [PERSON_3] stands next to him in [SCENE_1].", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.5, 4.5 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] continues speaking in [SCENE_1].", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.5, 9.2 ], "references": [ { "ref_id": "PERSON_4", "type": "person", "id_features": "A young woman with an elaborate hairstyle featuring flowers and braids", "attributes": "Light yellow and white dress, elaborate hairstyle with flowers and braids" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "An outdoor area with traditional wooden buildings, a bridge over water, and a hanging lantern in the foreground" } ], "visual_description": "[PERSON_4] runs across a bridge in [SCENE_2].", "camera": { "shot_type": "Wide shot", "angle": "Eye-level", "movement": "Panning" }, "active_events": [ "DIALOGUE_4", "MUSIC_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 9.2, 10.0 ], "references": [ "PERSON_4", "SCENE_2" ], "visual_description": "A close-up of [PERSON_4] looking worried in [SCENE_2].", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_4", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 1.5 ], "content": { "speaker": "PERSON_1", "line": "卷宗无语", "description": "Serious and assertive tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.5, 4.9 ], "content": { "speaker": "PERSON_2", "line": "那么就从你分馆的卷宗开始", "description": "Calm but authoritative tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.9, 5.4 ], "content": { "speaker": "PERSON_1", "line": "第一个", "description": "Firm and decisive tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.2, 8.4 ], "content": { "speaker": "PERSON_4", "line": "师尊", "description": "Urgent and slightly distressed call." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Dramatic and tense background music." } } ], "scene_description": "A tense confrontation occurs indoors regarding official records, followed by a sudden cut to a young woman running urgently outdoors.", "global_style": "Historical fantasy drama with elaborate costumes and traditional architecture.", "global_audio": "Dialogue-driven with dramatic background music." } }, { "dataset": "drama_04", "clip_id": "clip_98428", "media_path": "drama_04/clip_98428.mp4", "source_media_path": "clips/clip_98428.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with long wavy brown hair, wearing a purple fur-trimmed robe over a black lace top", "attributes": "long wavy brown hair, purple fur-trimmed robe, black lace top, gold necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair, wearing a dark suit, white shirt, and patterned tie", "attributes": "short black hair, dark suit, white shirt, patterned tie" } ], "visual_description": "Close-up of [PERSON_1] speaking, with the back of [PERSON_2]'s head partially visible on the left.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.4, 5.5 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A lavishly decorated room with dark wood paneling, ornate golden furniture, a glass coffee table, and floral arrangements", "attributes": "dark wood paneling, ornate golden sofa, glass coffee table, flowers" } ], "visual_description": "Wide shot showing [PERSON_1] and [PERSON_2] sitting together on an ornate golden sofa in [SCENE_1]. [PERSON_1] leans slightly towards [PERSON_2] while speaking.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.5, 7.8 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "Close-up of [PERSON_2] smiling and speaking to [PERSON_1], then leaning in to kiss her neck.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 7.8, 10.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "Wide shot of [PERSON_2] kissing [PERSON_1] on the sofa in [SCENE_1], viewed through a slightly blurred foreground object.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.3, 4.6 ], "content": { "speaker": "PERSON_1", "line": "只要有空多来陪陪我", "description": "Affectionate and demanding tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.9, 7.0 ], "content": { "speaker": "PERSON_2", "line": "没问题", "description": "Compliant and smooth tone" } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Soft, romantic background music" } } ], "scene_description": "A wealthy woman tells a younger man that he doesn't need to share money with her, asking only for his time and companionship. The man agrees and affectionately kisses her neck.", "global_style": "Luxurious, romantic, and slightly dramatic with warm lighting.", "global_audio": "Soft romantic background music playing throughout the scene." } }, { "dataset": "drama_04", "clip_id": "clip_26009", "media_path": "drama_04/clip_26009.mp4", "source_media_path": "clips/clip_26009.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin and dark hair tied up, looking distressed and angry", "attributes": "Wearing a light blue traditional Chinese dress with white trim. Her hands are bound with thick rope" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with a stern expression", "attributes": "Wearing a dark blue and purple traditional outfit" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden floors, wooden lattice windows, blue curtains, and lit candles in the background" } ], "visual_description": "[PERSON_1] is sitting on a chair, looking highly distressed and shouting. Her hands are bound with rope. [PERSON_3] stands stoically behind her in [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 4.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin, wearing elaborate makeup and a condescending expression", "attributes": "Wearing a light green and white traditional dress with pink floral embroidery on the chest. Her hair is styled up with multiple floral hairpins and she wears a pearl necklace" }, "SCENE_1", "PERSON_1" ], "visual_description": "The camera cuts to [PERSON_2], who is looking off-screen towards [PERSON_1] with a condescending and mocking expression as she speaks.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.7, 6.8 ], "references": [ "PERSON_1", "PERSON_3", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1], who glares angrily and defiantly while listening to the off-screen voice. [PERSON_3] remains standing behind her.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 6.8, 10.0 ], "references": [ "PERSON_1", "PERSON_2", "PERSON_3", { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman with long dark hair, seen mostly from behind", "attributes": "Wearing a green traditional dress with large pink floral patterns and a dark belt" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "A woman seen from behind", "attributes": "Wearing a solid pink traditional dress" }, "SCENE_1" ], "visual_description": "A wider view of the room shows [PERSON_4] and [PERSON_5] from behind in the foreground. [PERSON_4] walks towards the center where [PERSON_1] is seated with [PERSON_3] behind her. [PERSON_2] stands to the right, watching the interaction.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 1.6 ], "content": { "speaker": "PERSON_1", "line": "我爹爹呢", "description": "Anxious and demanding" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.6, 4.8 ], "content": { "speaker": "PERSON_2", "line": "沈青哥你都自身难保了", "description": "Mocking and condescending" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.8, 8.5 ], "content": { "speaker": "PERSON_2", "line": "我劝你先管好你自己吧", "description": "Threatening and dismissive" } } ], "scene_description": "A captive woman is interrogated and mocked by a group of hostile women in a traditional Chinese setting.", "global_style": "Historical Chinese drama with vibrant costumes and dramatic lighting.", "global_audio": "Tense dialogue with no prominent background music." } }, { "dataset": "drama_04", "clip_id": "clip_82374", "media_path": "drama_04/clip_82374.mp4", "source_media_path": "clips/clip_82374.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark, slightly wavy hair, pale skin, and a serious expression", "attributes": "Wearing a black leather coat over a black vest, white shirt, and black tie" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short dark hair, displaying an angry and aggressive facial expression", "attributes": "Wearing a light blue or grey jacket with a dark collar over a black shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Dark, moody outdoor environment with particles falling through the air", "attributes": "Nighttime, snowy or ashy atmosphere" } ], "visual_description": "Close-up of [PERSON_1] looking down with a stoic expression while snow falls around him. [PERSON_2] is visible but blurred in the background.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 2.5 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "Medium shot of [PERSON_2] yelling aggressively and pointing his finger towards the camera.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.5, 4.6 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "Over-the-shoulder shot from behind [PERSON_1], showing the back of his head as he slightly turns. The background is blurred.", "camera": { "shot_type": "over-the-shoulder", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.6, 6.2 ], "references": [ "PERSON_1", { "ref_id": "PERSON_3", "type": "person", "id_features": "A young woman with long dark hair, pale skin, tears in her eyes, and blood on her face", "attributes": "Wearing a white dress with lace details, stained with blood, and a pearl necklace" } ], "visual_description": "Close-up of [PERSON_1]'s hand gently holding [PERSON_3]'s hand. Blood is clearly visible on [PERSON_3]'s white dress.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.2, 8.9 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "Close-up of [PERSON_1] looking down, speaking softly with a serious, slightly menacing expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_6", "time_range": [ 8.9, 10.0 ], "references": [ "PERSON_3", "SCENE_1" ], "visual_description": "Close-up of [PERSON_3] lying on the ground, looking up with tearful eyes. Her face and dress are stained with blood.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.1, 1.3 ], "content": { "speaker": "PERSON_2", "line": "跟我私奔", "description": "Aggressive and taunting tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.3, 3.4 ], "content": { "speaker": "PERSON_2", "line": "害你费了一条腿你现在为了报仇是吗", "description": "Angry, loud, and accusatory tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.4, 3.8 ], "content": { "speaker": "PERSON_1", "line": "到我的悠悠了", "description": "Calm, quiet, but menacing tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Tense, dramatic background music." } } ], "scene_description": "A tense confrontation occurs in a snowy, dark setting. One man angrily taunts another about a woman who eloped and caused an injury. The second man, holding the injured, bleeding woman, calmly responds that the yelling is disturbing her.", "global_style": "Dark, dramatic, cinematic lighting with a cool color palette, emphasizing the falling snow and the blood on the woman's dress.", "global_audio": "Dramatic background music with the sound of falling snow and tense dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_56214", "media_path": "drama_04/clip_56214.mp4", "source_media_path": "clips/clip_56214.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "An older woman with short grey hair and a warm smile", "attributes": "short grey hair, dark plaid shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit outdoor area at night, decorated with string lights", "attributes": "nighttime, string lights, blurred background" } ], "visual_description": "[PERSON_1] smiles broadly and gives a thumbs-up gesture, appearing to communicate with someone off-screen.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.8, 2.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long dark hair, wearing a light blue top and a necklace", "attributes": "long dark hair, light blue v-neck top, necklace, earrings" }, "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] smiles warmly, looking towards the direction of [PERSON_1].", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.2, 5.2 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "A close-up of [PERSON_2]'s hand giving a thumbs-up gesture in response.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.2, 7.2 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man with short dark hair, wearing a formal suit", "attributes": "short dark hair, black suit, white shirt, patterned tie, lapel pin with a chain" }, "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_3] looks at [PERSON_2] with a surprised expression and asks her a question.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 7.2, 10.0 ], "references": [ "PERSON_2", "PERSON_3", "SCENE_1" ], "visual_description": "[PERSON_2] turns her head slightly, smiles, and replies to [PERSON_3].", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_2" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Gentle, emotional background music playing throughout the scene." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 5.9, 8.2 ], "content": { "speaker": "PERSON_3", "line": "你会手语", "description": "Surprised inquiry." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 8.2, 9.7 ], "content": { "speaker": "PERSON_2", "line": "我以前学过一点", "description": "Modest and friendly response." } } ], "scene_description": "A young woman surprises her male companion by communicating with an older woman using sign language during an evening gathering.", "global_style": "Warm, romantic, and slightly cinematic with shallow depth of field and bokeh from string lights.", "global_audio": "Quiet outdoor ambience with soft, sentimental background music." } }, { "dataset": "drama_04", "clip_id": "clip_56767", "media_path": "drama_04/clip_56767.mp4", "source_media_path": "clips/clip_56767.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long, straight black hair and a pale complexion", "attributes": "long black hair, white dress" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair and a serious expression", "attributes": "short black hair, black patterned robe" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A flat, rectangular electronic tablet", "attributes": "rectangular, screen" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with dark background elements and warm, subdued lighting" } ], "visual_description": "[PERSON_2] holds [OBJECT_1] and shows the screen to [PERSON_1]. [PERSON_1] looks down at the device and then raises her head to look at [PERSON_2].", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.9, 6.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera focuses on [PERSON_1] as she speaks with a firm and rejecting expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.0, 8.8 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "The camera cuts to [PERSON_2], who looks intently at [PERSON_1] and speaks.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.8, 10.4 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1], who listens with a conflicted expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_5", "time_range": [ 10.4, 12.0 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "The camera returns to [PERSON_2] as he continues speaking earnestly, gesturing slightly with his hand.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 4.0 ], "content": { "speaker": "PERSON_2", "line": "我们来选一下你喜欢的酒店和场景", "description": "Calm and suggestive tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.0, 8.0 ], "content": { "speaker": "PERSON_1", "line": "我不可能跟你结婚你别做梦了", "description": "Firm, rejecting, and slightly agitated tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 8.0, 11.8 ], "content": { "speaker": "PERSON_2", "line": "白河我真的很喜欢你为什么你为什么不试着爱我呢", "description": "Pleading, earnest, and emotional tone." } } ], "scene_description": "A tense conversation between a man and a woman, where the man is trying to plan a wedding but the woman firmly rejects him, leading to his emotional plea.", "global_style": "Dramatic and intimate, with moody, low-key lighting.", "global_audio": "Quiet room ambience with clear, upfront dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_341", "media_path": "drama_04/clip_341.mp4", "source_media_path": "clips/clip_341.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with black hair, fair skin, and red eye makeup", "attributes": "Wearing red and black traditional Chinese robes, with a gold crown hairpiece" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A wooden pavilion illuminated by glowing yellow lanterns, with a view of bamboo and a stone bridge in the background" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A white ceramic teapot, matching teacups, and a plate of golden mooncakes resting on a wooden table" } ], "visual_description": "[PERSON_1] sits at a table with [OBJECT_1] in [SCENE_1], looking earnest as he speaks.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.3, 5.4 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long silver/white hair, purple eyes, and a beauty mark under her left eye", "attributes": "Wearing purple traditional Chinese robes, adorned with silver hairpins featuring teal tassels" }, "SCENE_1" ], "visual_description": "A close-up of [PERSON_2] speaking instructively, raising her index finger to emphasize her point.", "camera": { "shot_type": "close up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.4, 8.0 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] continues her explanation with a gentle, knowing smile.", "camera": { "shot_type": "close up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.0, 10.5 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] looks down with a blushing face, showing realization and slight embarrassment.", "camera": { "shot_type": "close up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] }, { "shot_id": "SHOT_5", "time_range": [ 10.5, 11.4 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "The view returns to [PERSON_2] as she begins to make her next point.", "camera": { "shot_type": "close up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_5" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 0.9 ], "content": { "speaker": "PERSON_1", "line": "求仙人指", "description": "Earnest and respectful request." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 0.9, 5.0 ], "content": { "speaker": "PERSON_2", "line": "點別的不說你必須先收起那套我要惹你注意的幼稚把", "description": "Instructive and slightly scolding tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.0, 9.8 ], "content": { "speaker": "PERSON_2", "line": "戲喜歡一個人不是故意欺負他擠對他是對他好讓他開心", "description": "Gentle, explanatory, and wise tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 9.8, 10.7 ], "content": { "speaker": "PERSON_1", "line": "原來如此", "description": "Soft realization with a hint of embarrassment." } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 10.7, 10.9 ], "content": { "speaker": "PERSON_2", "line": "首先", "description": "Authoritative start to a new point." } } ], "scene_description": "A young man seeks relationship advice from a wise female immortal in a serene, lantern-lit pavilion at night.", "global_style": "2D anime style animation with a traditional Chinese fantasy aesthetic, featuring vibrant colors and detailed character designs.", "global_audio": "Quiet ambient background with clear, expressive voice acting." } }, { "dataset": "drama_04", "clip_id": "clip_51049", "media_path": "drama_04/clip_51049.mp4", "source_media_path": "clips/clip_51049.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "An older woman with her hair styled in an updo, wearing pearl earrings", "attributes": "green floral cheongsam, pearl earrings, updo hairstyle" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with a round wooden table, white plates, and glasses", "attributes": "round table, white plates, glasses, dining setting" } ], "visual_description": "[PERSON_1] is sitting at [SCENE_1], talking and gesturing slightly with her hand.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.3, 4.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A younger woman with long dark hair, wearing dangling earrings", "attributes": "beige trench coat, long hair, dangling earrings" }, "SCENE_1" ], "visual_description": "[PERSON_2] is sitting at [SCENE_1], smiling and listening attentively.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.0, 12.0 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man with short dark hair, wearing a necklace", "attributes": "white suit jacket, black shirt, necklace" } ], "visual_description": "[PERSON_3] is standing, looking thoughtful. He takes out his phone, holds it near his chin, and speaks.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 2.4 ], "content": { "speaker": "PERSON_1", "line": "过几天打算去你们的节目看看", "description": "Informative and conversational tone." } } ], "scene_description": "A conversation takes place in a dining room where an older woman mentions visiting a program, prompting a thoughtful reaction from a young man.", "global_style": "Modern drama, well-lit interior, realistic aesthetic.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_21790", "media_path": "drama_04/clip_21790.mp4", "source_media_path": "clips/clip_21790.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 0.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman wearing a floral dress with pink roses and a pearl necklace", "attributes": "floral dress, pearl necklace, hair tied back" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with elegant curtains and decor, suggesting a wealthy household" } ], "visual_description": "[PERSON_1] is shown from the chest up, looking down with a serious expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 0.8, 2.5 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "An older woman wearing a dark purple dress, a long pearl necklace, and glasses", "attributes": "dark purple dress, pearl necklace, glasses, hair in a bun" }, "SCENE_1" ], "visual_description": "[PERSON_2] is shown from the chest up, looking down at a blue folder in her hands.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.5, 5.0 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man wearing a crisp white shirt", "attributes": "white shirt, short hair" }, "SCENE_1" ], "visual_description": "[PERSON_3] is shown from the chest up, speaking and looking slightly off-camera to his right.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.0, 6.3 ], "references": [ { "ref_id": "PERSON_4", "type": "person", "id_features": "A man wearing a bright yellow Taoist robe with black stripes", "attributes": "yellow Taoist robe with black stripes, short hair" }, "SCENE_1" ], "visual_description": "[PERSON_4] is shown from the chest up, looking nervous and shifting his gaze.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.3, 7.7 ], "references": [ "PERSON_1", "PERSON_4", "SCENE_1" ], "visual_description": "[PERSON_1] is shown again, looking up towards [PERSON_4] while holding a phone in her hand. A portion of [PERSON_4]'s yellow robe is visible on the left.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_6", "time_range": [ 7.7, 11.7 ], "references": [ { "ref_id": "PERSON_5", "type": "person", "id_features": "A young woman wearing a pink and green outfit with her hair styled in twin braids", "attributes": "pink and green outfit, twin braids, necklace" }, "PERSON_4", "SCENE_1" ], "visual_description": "[PERSON_5] is shown from the chest up, speaking with a mocking expression, looking towards [PERSON_4] who is partially visible on the right edge of the frame.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 8.2 ], "content": { "speaker": "PERSON_3", "line": "这个道士是承熙有名的神棍因为照耀撞骗被关了很多年这个月才放出来的吧", "description": "Accusing and revealing tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 8.2, 11.2 ], "content": { "speaker": "PERSON_5", "line": "这么说大师啊你这刚出来要回去", "description": "Mocking and playful tone" } } ], "scene_description": "A group of people are exposing a man dressed as a Taoist priest as a fraud who was recently released from prison.", "global_style": "Brightly lit indoor drama with clear focus on characters' expressions.", "global_audio": "Clear dialogue with no prominent background music or noise." } }, { "dataset": "drama_04", "clip_id": "clip_101816", "media_path": "drama_04/clip_101816.mp4", "source_media_path": "clips/clip_101816.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair with bangs, wearing a black shirt under a grey tweed jacket with frayed edges", "attributes": "short black hair, black shirt, grey tweed jacket" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A woman with her hair tied back, wearing a light green patterned top and a black skirt", "attributes": "hair tied back, light green patterned top, black skirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A courtroom interior featuring wooden barriers, benches, and a formal atmosphere", "attributes": "wooden barriers, benches, formal setting" } ], "visual_description": "[PERSON_1] is seated, talking animatedly to [PERSON_4], whose shoulder and the back of her head are visible in the foreground.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.2, 5.6 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short black hair, wearing a dark blue suit, a black shirt, and a patterned tie", "attributes": "short black hair, dark blue suit, black shirt, patterned tie" }, "SCENE_1" ], "visual_description": "[PERSON_2] is seated in the courtroom gallery, maintaining a serious and focused expression while looking forward.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.6, 7.6 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "An older man with greying hair and glasses, wearing a beige suit, a black shirt, and a patterned tie", "attributes": "greying hair, glasses, beige suit, black shirt, patterned tie" }, "SCENE_1" ], "visual_description": "[PERSON_3] stands in the courtroom, looking sternly ahead.", "camera": { "shot_type": "Medium close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 7.6, 10.5 ], "references": [ "PERSON_1", "PERSON_4", "SCENE_1" ], "visual_description": "The camera returns to [PERSON_1] as he continues his conversation with [PERSON_4], leaning forward slightly to emphasize his point.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 2.9 ], "content": { "speaker": "PERSON_1", "line": "居然跑到法庭上来睡觉", "description": "Speaking with a slightly mocking or disbelieving tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.9, 5.9 ], "content": { "speaker": "PERSON_1", "line": "三亿对顾总来说虽然只是小数目", "description": "Explaining a situation with a serious tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.9, 7.4 ], "content": { "speaker": "PERSON_1", "line": "但他睚眦必报", "description": "Warning tone, emphasizing a character trait." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 7.4, 10.1 ], "content": { "speaker": "PERSON_1", "line": "案子如果输了就算天王老子来了", "description": "Emphasizing the severe consequences of losing the case." } } ], "scene_description": "A young man explains the high stakes and ruthless nature of a key figure in a court case to a woman, while cutaway shots reveal the serious expressions of the involved parties in the courtroom.", "global_style": "Modern drama with a serious, tense, and formal aesthetic.", "global_audio": "Dialogue-driven with clear speech and no prominent background music." } }, { "dataset": "drama_04", "clip_id": "clip_99625", "media_path": "drama_04/clip_99625.mp4", "source_media_path": "clips/clip_99625.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A male cartoon character with a comical face, wearing a yellow robe and a crown", "attributes": "Yellow robe with black trim, golden crown with dangling beads" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A female cartoon character with long black hair, wearing a blue dress", "attributes": "Light blue dress with flowing sleeves, long black hair" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A pile of regular, light brown potatoes" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A simple room with a wooden floor and a plain wall" } ], "visual_description": "[PERSON_2] stands on the right side of [SCENE_1], gesturing with her arm raised. [PERSON_1] is positioned on the left, looking towards her, with some [OBJECT_1] visible behind him.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.8, 11.0 ], "references": [ "PERSON_1", "OBJECT_1", { "ref_id": "OBJECT_2", "type": "object", "id_features": "A pile of reddish-purple sweet potatoes" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A split background featuring sweet potatoes on the left and regular potatoes on the right" } ], "visual_description": "The setting transitions to [SCENE_2], displaying [OBJECT_2] on the left and [OBJECT_1] on the right. [PERSON_1] appears in the center foreground. He initially displays a dazed, drooling expression, then speaks while looking around, and finally looks upwards with a blushing, excited face.", "camera": { "shot_type": "close up", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1", "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.0, 1.9 ], "content": { "speaker": "PERSON_2", "line": "不要钱", "description": "Firm statement" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.9, 5.0 ], "content": { "speaker": "PERSON_1", "line": "这才对嘛", "description": "Satisfied agreement" } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.0, 4.0 ], "content": { "description": "Comical, distorted vocal sound effect resembling a weird laugh." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.0, 8.3 ], "content": { "speaker": "PERSON_1", "line": "真记得苏达喜之前说过几种红薯的食用方法", "description": "Thoughtful recollection" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.3, 10.2 ], "content": { "speaker": "PERSON_1", "line": "等一下真就让人烤几个来吃", "description": "Excited anticipation" } } ], "scene_description": "An animated short where an emperor character interacts with a female character about money, then transitions to a scene where he excitedly anticipates eating roasted sweet potatoes.", "global_style": "2D cartoon animation with exaggerated expressions and comedic elements.", "global_audio": "Clear dialogue with a comical sound effect during the scene transition." } }, { "dataset": "drama_04", "clip_id": "clip_23899", "media_path": "drama_04/clip_23899.mp4", "source_media_path": "clips/clip_23899.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin and dark hair styled in an elaborate updo with colorful hairpins", "attributes": "Wearing a white and light blue traditional dress with a prominent white fur collar" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Only the lower body and legs are visible", "attributes": "Wearing dark clothing with red accents" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor area with a rocky backdrop, a small wooden bridge, and sparse vegetation" } ], "visual_description": "[PERSON_1] is on the ground, clinging tightly to the leg of [PERSON_2]. She looks up with a pleading expression.", "camera": { "shot_type": "medium close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.2, 3.1 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with dark hair styled in a topknot secured with a headpiece", "attributes": "Wearing a purple and black traditional outfit with a wide belt" }, "SCENE_1" ], "visual_description": "[PERSON_3] bows his head respectfully, acknowledging an order.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.1, 4.5 ], "references": [ { "ref_id": "PERSON_4", "type": "person", "id_features": "A young woman with dark hair styled with two braided loops on the sides", "attributes": "Wearing a pink and white traditional dress with floral embroidery" }, "SCENE_1" ], "visual_description": "[PERSON_4] stands looking distressed and worried.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 4.5, 5.8 ], "references": [ "PERSON_1", "PERSON_3", "SCENE_1" ], "visual_description": "[PERSON_3] grabs [PERSON_1] by the arm and pulls her up, dragging her away. [PERSON_1] struggles.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "pan right" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_5", "time_range": [ 5.8, 7.2 ], "references": [ { "ref_id": "PERSON_5", "type": "person", "id_features": "A young man with dark hair half-up, wearing a prominent gold crown", "attributes": "Wearing a black robe with intricate gold embroidery" }, "SCENE_1" ], "visual_description": "[PERSON_5] stands calmly, watching the scene unfold.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_6", "time_range": [ 7.2, 9.4 ], "references": [ "PERSON_1", "PERSON_3", "SCENE_1", "PERSON_5" ], "visual_description": "[PERSON_1], still held by [PERSON_3], looks back towards [PERSON_5] with a resigned expression, letting out a sigh.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 2.0 ], "content": { "speaker": "PERSON_2", "line": "押回皇城择日定罪", "description": "Authoritative and commanding tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.0, 2.4 ], "content": { "speaker": "PERSON_3", "line": "是", "description": "Obedient and respectful tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 2.4, 2.5 ], "content": { "speaker": "PERSON_1", "line": "不是", "description": "Panicked and struggling tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 7.0, 8.5 ], "content": { "description": "A heavy sigh." } } ], "scene_description": "A woman is ordered to be taken away to the imperial city for sentencing. She struggles briefly before being dragged off by a guard, while others watch.", "global_style": "Historical Chinese costume drama aesthetic with traditional clothing and outdoor natural lighting.", "global_audio": "Dialogue-driven with ambient outdoor sounds." } }, { "dataset": "drama_04", "clip_id": "clip_84602", "media_path": "drama_04/clip_84602.mp4", "source_media_path": "clips/clip_84602.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair", "attributes": "Wearing a dark red button-down shirt and a silver necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring plain walls, with one side being a textured yellowish-green and the other a flat grey", "attributes": "Indoor, plain, slightly dim lighting" } ], "visual_description": "Close-up of [PERSON_1] smiling slightly while speaking.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.1, 2.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with black hair tied up in a bun", "attributes": "Wearing a black dress with a prominent white collar" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A golden, leaf-shaped ornament mounted on a small white rectangular base", "attributes": "Golden, metallic, white base" }, "SCENE_1" ], "visual_description": "Close-up of [PERSON_2] looking defensive and cornered against a grey wall, holding [OBJECT_1] up defensively.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 2.8, 4.5 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "Close-up of [PERSON_1] continuing to speak with a more serious and mocking expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.5, 7.8 ], "references": [ "PERSON_2", "OBJECT_1", "SCENE_1" ], "visual_description": "Close-up of [PERSON_2] listening intently, maintaining her defensive posture with [OBJECT_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_5", "time_range": [ 7.8, 9.4 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "Close-up of [PERSON_1] finishing his statement with a challenging look.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] }, { "shot_id": "SHOT_6", "time_range": [ 9.4, 10.0 ], "references": [ "PERSON_2", "OBJECT_1", "SCENE_1" ], "visual_description": "Close-up of [PERSON_2] looking slightly surprised and anxious.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.2, 2.8 ], "content": { "speaker": "PERSON_1", "line": "爬上我的床", "description": "Condescending and suggestive tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.8, 4.8 ], "content": { "speaker": "PERSON_1", "line": "不比伺候一个奶娃娃强", "description": "Mocking and arrogant tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.8, 7.0 ], "content": { "speaker": "PERSON_1", "line": "还是说你靠你那点小聪明解决了江", "description": "Questioning and slightly accusatory tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.0, 8.9 ], "content": { "speaker": "PERSON_1", "line": "就能站稳脚跟了", "description": "Challenging and dismissive tone." } } ], "scene_description": "A tense confrontation between a man and a woman. The man speaks condescendingly to the woman, who is cornered against a wall and holding a decorative object defensively.", "global_style": "Dramatic and tense, characterized by tight close-up shots that emphasize the characters' facial expressions and the claustrophobic nature of the confrontation.", "global_audio": "Clear, upfront dialogue with a subtle, tense ambient background." } }, { "dataset": "drama_04", "clip_id": "clip_86114", "media_path": "drama_04/clip_86114.mp4", "source_media_path": "clips/clip_86114.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with fair skin and long black hair styled with thin braids", "attributes": "Wearing a light blue and white traditional Chinese outfit with silver armor-like chest pieces, a silver headpiece, and white fur on his right shoulder" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor room featuring wooden furniture, a bed with light blue sheer curtains, and a small bonsai tree visible in the background" } ], "visual_description": "[PERSON_1] is sitting and speaking, looking slightly off-camera to his right. The background shows light blue curtains of [SCENE_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.7, 4.1 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin, pinkish makeup, and long black hair styled in twin buns", "attributes": "Wearing a pink and white traditional Chinese dress with intricate embroidery, adorned with pink floral hairpieces and dangling ornaments" }, "SCENE_1" ], "visual_description": "[PERSON_2] is sitting and speaking, looking to her left towards [PERSON_1], whose profile is partially visible on the left edge of the frame.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.1, 6.6 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "A wider view showing [PERSON_1] and [PERSON_2] sitting facing each other on the edge of a bed with light blue curtains in [SCENE_1]. [PERSON_2] is speaking.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 6.6, 10.8 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "A close-up of [PERSON_2] speaking, looking slightly to her left. The background is softly blurred.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 2.9 ], "content": { "speaker": "PERSON_1", "line": "你怎么能骗师父呢", "description": "Questioning and slightly reproachful tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.9, 5.4 ], "content": { "speaker": "PERSON_2", "line": "那你去跟师父说", "description": "Defiant and challenging tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.4, 8.8 ], "content": { "speaker": "PERSON_2", "line": "我们不但对老魔头谄媚讨好", "description": "Explaining with a hint of sarcasm." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.8, 10.7 ], "content": { "speaker": "PERSON_2", "line": "还假装答应了做魔族奸细", "description": "Continuing the explanation in a matter-of-fact manner." } } ], "scene_description": "Two disciples are having a tense conversation in a traditional room, discussing their deceptive actions involving their master and a demon faction.", "global_style": "Chinese fantasy (Xianxia) drama aesthetic with bright lighting, elaborate traditional costumes, and detailed set design.", "global_audio": "Clear spoken dialogue with quiet, subtle room ambience." } }, { "dataset": "drama_04", "clip_id": "clip_59032", "media_path": "drama_04/clip_59032.mp4", "source_media_path": "clips/clip_59032.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with dark hair, fair skin, wearing makeup", "attributes": "Wearing a light-colored top and white high heels" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short dark hair", "attributes": "Wearing a white long-sleeved shirt, dark pants, and dark shoes" } ], "visual_description": "A close-up shot focusing on [PERSON_1]'s feet, which are wearing white high heels, resting on top of [PERSON_2]'s legs and dark shoes.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "EVENT_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.5, 8.0 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "A close-up shot of [PERSON_1] and [PERSON_2]'s faces. [PERSON_1] is lying down with her eyes closed, smiling slightly, while [PERSON_2] is intimately kissing her neck and cheek.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "EVENT_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 8.0, 10.0 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A bedroom setting with a bed, white sheets, and warm, reddish ambient lighting" } ], "visual_description": "A medium shot showing [PERSON_1] and [PERSON_2] lying on a bed in [SCENE_1]. [PERSON_2] is leaning over [PERSON_1], continuing to embrace and kiss her.", "camera": { "shot_type": "medium shot", "angle": "high angle", "movement": "static" }, "active_events": [ "EVENT_2" ] } ], "events": [ { "event_id": "EVENT_1", "type": "dialogue", "time_range": [ 0.7, 1.4 ], "content": { "speaker": "PERSON_1", "line": "做了好久的", "description": "Soft, contemplative internal monologue" } }, { "event_id": "EVENT_2", "type": "sfx", "time_range": [ 2.0, 9.0 ], "content": { "description": "Soft breathing and gentle kissing sounds" } } ], "scene_description": "An intimate and romantic scene where a couple is lying in bed together, with the woman expressing her internal thoughts about being mentally prepared for the moment.", "global_style": "Moody, romantic, and dimly lit with warm reddish tones.", "global_audio": "Quiet and intimate atmosphere with soft voiceover and gentle ambient sounds." } }, { "dataset": "drama_04", "clip_id": "clip_4303", "media_path": "drama_04/clip_4303.mp4", "source_media_path": "clips/clip_4303.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 6.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, wearing a grey plaid shirt over a light blue button-down shirt. He has a small earring in his left ear", "attributes": "short black hair, grey plaid shirt, light blue button-down shirt, earring" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor area, possibly a balcony or walkway, with a white railing and blurred green trees in the background", "attributes": "outdoor, white railing, blurred trees" } ], "visual_description": "[PERSON_1] stands outdoors, looking slightly downwards with a serious expression. He then raises his eyes slightly as he listens to someone speaking off-screen.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 6.1, 10.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with brown hair tied back, wearing a beige cardigan over a white top, and a delicate necklace with a pendant", "attributes": "brown hair tied back, beige cardigan, white top, necklace with pendant" }, "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], who is looking downwards with a sad and frustrated expression as she speaks.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 3.9, 5.1 ], "content": { "speaker": "PERSON_2", "line": "有的人生下来就不被", "description": "Emotional and slightly bitter tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 6.1, 7.3 ], "content": { "speaker": "PERSON_2", "line": "你有人关心还不知", "description": "Reproachful tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.3, 9.7 ], "content": { "speaker": "PERSON_2", "line": "所自己躲起来什么都不说", "description": "Frustrated tone" } } ], "scene_description": "A tense emotional conversation between a man and a woman outdoors, where the woman expresses frustration over the man's lack of appreciation for the care he receives and his tendency to isolate himself.", "global_style": "Dramatic and emotional, with soft natural lighting and shallow depth of field focusing on the characters' expressions.", "global_audio": "Quiet outdoor ambience with clear, emotional dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_52219", "media_path": "drama_04/clip_52219.mp4", "source_media_path": "clips/clip_52219.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with messy dark hair covering part of her face, wearing torn and dirty brown clothing", "attributes": "messy hair, torn brown clothes, dirty appearance" }, { "ref_id": "ANIMAL_1", "type": "animal", "id_features": "A white horse standing in the background", "attributes": "white coat" } ], "visual_description": "[PERSON_1] leans against a cold stone wall. Her hair is messy and partially covers her face. She wears torn, dirty clothing. In the background, [ANIMAL_1] is visible.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.0, 10.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with an elegant updo adorned with a pink flower, wearing a pink traditional dress with floral patterns, a pearl necklace, and a jade pendant. She has a bloody wound on her chest and scratches on her face, and is bound by iron chains", "attributes": "pink traditional dress, floral hair accessory, pearl necklace, jade pendant, iron chains, bloody wound, facial scratches" }, "ANIMAL_1" ], "visual_description": "The scene cuts to [PERSON_2] standing outdoors, bound tightly by iron chains around her torso and arms. She wears an elegant pink dress but has a visible bloody wound on her chest and scratches on her face. She looks distressed and emotional. In the background, [ANIMAL_1] and several soldiers are visible behind a wooden fence.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "DIALOGUE_4", "DIALOGUE_5", "DIALOGUE_6", "DIALOGUE_7" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 1.7 ], "content": { "speaker": "NARRATOR", "line": "他靠在冰冷的墙壁上", "description": "Somber and descriptive tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.7, 3.0 ], "content": { "speaker": "NARRATOR", "line": "头发散乱地遮住了脸", "description": "Somber and descriptive tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.0, 4.4 ], "content": { "speaker": "NARRATOR", "line": "身上的裘腹破烂不堪", "description": "Somber and descriptive tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 4.4, 6.2 ], "content": { "speaker": "NARRATOR", "line": "露出的皮肤上满是伤痕", "description": "Somber and descriptive tone" } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 6.2, 7.1 ], "content": { "speaker": "NARRATOR", "line": "有铁链磨的", "description": "Somber and descriptive tone" } }, { "event_id": "DIALOGUE_6", "type": "dialogue", "time_range": [ 7.1, 8.0 ], "content": { "speaker": "NARRATOR", "line": "有士兵打的", "description": "Somber and descriptive tone" } }, { "event_id": "DIALOGUE_7", "type": "dialogue", "time_range": [ 8.0, 9.8 ], "content": { "speaker": "NARRATOR", "line": "还有内心的痛苦折磨出来的憔悴", "description": "Somber and descriptive tone" } } ], "scene_description": "A dramatic sequence showing two different women in states of distress and captivity. The first woman is dressed in rags and leans against a wall, while the second woman is bound in iron chains despite wearing elegant clothing, bearing visible wounds.", "global_style": "Historical drama aesthetic with a somber and gritty tone, featuring detailed costumes and realistic makeup for injuries.", "global_audio": "A continuous, somber voiceover narration describing the physical and emotional suffering of a captive." } }, { "dataset": "drama_04", "clip_id": "clip_21577", "media_path": "drama_04/clip_21577.mp4", "source_media_path": "clips/clip_21577.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A middle-aged man with short, styled black hair and glasses", "attributes": "Dark suit, white shirt, brown tie, gold-rimmed glasses, small lapel pin" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with long, wavy black hair", "attributes": "Off-the-shoulder leopard print top, dangling earrings" } ], "visual_description": "Medium shot of [PERSON_1] sitting outdoors. He is speaking with a serious and slightly distressed expression, looking off-camera towards [PERSON_2].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.7, 7.3 ], "references": [ "PERSON_2" ], "visual_description": "Medium shot of [PERSON_2]. She is listening intently, looking slightly downwards before raising her eyes.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.3, 10.0 ], "references": [ "PERSON_1" ], "visual_description": "Medium shot of [PERSON_1] continuing his explanation. He maintains a serious and earnest expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 10.0, 12.0 ], "references": [ "PERSON_2", "PERSON_1" ], "visual_description": "Medium shot of [PERSON_2]. She responds to [PERSON_1] with a contemplative and slightly disappointed expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 3.8 ], "content": { "speaker": "PERSON_1", "line": "我实在是不知道能有什么办法才能靠近你", "description": "Earnest and distressed explanation." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.8, 6.7 ], "content": { "speaker": "PERSON_1", "line": "而且那个时候你跟楚思渝都快要订婚了", "description": "Explaining past circumstances with urgency." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 6.7, 9.6 ], "content": { "speaker": "PERSON_1", "line": "我只有那样才能把你从楚思渝身边给夺回来", "description": "Justifying his actions with determination." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 9.6, 11.3 ], "content": { "speaker": "PERSON_2", "line": "所以你一直伪装自己", "description": "Realization and mild accusation." } } ], "scene_description": "A man explains his past actions and motivations to a woman, revealing that he felt compelled to act a certain way to win her back from another man. The woman realizes he has been pretending.", "global_style": "Dramatic television or short film style with clear, focused lighting and a blurred outdoor background.", "global_audio": "Clear dialogue with subtle ambient outdoor noise." } }, { "dataset": "drama_04", "clip_id": "clip_78109", "media_path": "drama_04/clip_78109.mp4", "source_media_path": "clips/clip_78109.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with a mustache and goatee, displaying a distressed and furrowed expression", "attributes": "Wearing a blue patterned robe with silver trim, a light grey inner collar, and a black historical headpiece" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with wooden shelves, decorative items, and warm lighting", "attributes": "Traditional Chinese interior design" } ], "visual_description": "[PERSON_1] stands and speaks with a distressed expression, furrowing his brows as he questions a decision.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.5, 7.6 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "An older man with grey hair, a grey beard, and a calm, critical demeanor", "attributes": "Wearing a brown robe and a black historical headpiece" }, "SCENE_1", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A wooden grid board with black and white stones placed on it", "attributes": "Traditional Go game" }, "PERSON_1" ], "visual_description": "[PERSON_2] sits at a table with [OBJECT_1], holding a white piece in his hand. He looks up towards [PERSON_1] and speaks calmly but critically.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.6, 11.0 ], "references": [ "PERSON_2", "SCENE_1", "OBJECT_1" ], "visual_description": "A closer view of [PERSON_2] as he looks down at [OBJECT_1] and continues speaking, shaking his head slightly in disappointment.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 2.2 ], "content": { "speaker": "PERSON_1", "line": "那些计策都太过歹毒了", "description": "Distressed and questioning tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.2, 7.2 ], "content": { "speaker": "PERSON_2", "line": "嘛难怪这么多年了你还只是个三品", "description": "Calm, critical, and slightly condescending tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 9.2, 10.7 ], "content": { "speaker": "PERSON_2", "line": "真是烂泥扶不上墙啊", "description": "Disappointed and dismissive tone." } } ], "scene_description": "Two officials in a traditional Chinese setting discuss political strategies. The younger official expresses moral concern over their tactics, while the older official dismisses his concerns, criticizing his lack of ambition and competence.", "global_style": "Historical Chinese drama with traditional costumes, warm lighting, and classical set design.", "global_audio": "Quiet ambient room sound with clear, prominent dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_797", "media_path": "drama_04/clip_797.mp4", "source_media_path": "clips/clip_797.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with fair skin, dark eyes, and long black hair partially tied up with a silver hairpiece", "attributes": "clothing: Black robe with elaborate gold embroidery on the shoulders and chest., hairstyle: Long black hair, half-up with a silver crown-like hairpiece and a horizontal pin., accessories: Silver hairpiece, gold chain detail on the chest" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin, dark eyes, and an elaborate updo hairstyle adorned with pearl ornaments", "attributes": "clothing: Red and black layered robe with gold patterned accents., hairstyle: Complex updo with multiple sections, adorned with dangling pearl ornaments on both sides and a central forehead piece., accessories: Pearl dangling hair ornaments, central forehead jewelry" }, { "ref_id": "ANIMAL_1", "type": "animal", "id_features": "A large black horse with a dark mane" }, { "ref_id": "ANIMAL_2", "type": "animal", "id_features": "A large brown horse with a dark mane" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An outdoor setting at night featuring large, studded wooden doors that are open, revealing a dark background with some greenery" } ], "visual_description": "[PERSON_1] and [PERSON_2] are seated on [ANIMAL_1] and [ANIMAL_2] respectively, positioned side-by-side in front of the large open doors of [SCENE_1]. They are stationary, looking forward.", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 1.9, 5.2 ], "references": [ "PERSON_1" ], "visual_description": "The camera cuts to a close-up of [PERSON_1]'s face. He has a serious expression and speaks.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.2, 7.3 ], "references": [ "PERSON_2" ], "visual_description": "The camera cuts to a close-up of [PERSON_2]'s face. She looks determined and gives a brief command.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 7.3, 10.0 ], "references": [ "PERSON_1", "PERSON_2", "ANIMAL_1", "ANIMAL_2", "SCENE_1" ], "visual_description": "The camera returns to a wide shot. [PERSON_1] and [PERSON_2] spur [ANIMAL_1] and [ANIMAL_2] into motion, riding forward out of [SCENE_1].", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 4.3, 4.9 ], "content": { "speaker": "PERSON_1", "line": "父皇出事了", "description": "Serious and urgent tone, delivering bad news." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 6.5, 9.0 ], "content": { "description": "Sound of horse hooves clopping on the ground as they start to ride." } } ], "scene_description": "Two characters on horseback receive urgent news and immediately ride off into the night.", "global_style": "Historical fantasy drama aesthetic, with elaborate costumes and dramatic lighting.", "global_audio": "Quiet nighttime ambience punctuated by dialogue and the sound of horses." } }, { "dataset": "drama_04", "clip_id": "clip_62477", "media_path": "drama_04/clip_62477.mp4", "source_media_path": "clips/clip_62477.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair", "attributes": "Wearing a black t-shirt under a textured grey and black jacket, light-colored trousers, white sneakers, and a silver necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long, straight black hair", "attributes": "Wearing a light beige, long-sleeved dress and flat sandals" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A sleek interior space with polished marble-like floors, grey walls, and elevator doors in the background", "attributes": "Modern lighting, reflective surfaces" } ], "visual_description": "[PERSON_1] and [PERSON_2] stand facing each other in [SCENE_1]. [PERSON_1] speaks to [PERSON_2].", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.5, 7.3 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "A close-up of [PERSON_2] looking at [PERSON_1] and responding.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.3, 10.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A close-up of [PERSON_1] looking down slightly, then speaking.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.0, 5.3 ], "content": { "speaker": "PERSON_1", "line": "办身份可以但我有个条件", "description": "Serious and conditional tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 5.3, 8.5 ], "content": { "speaker": "PERSON_2", "line": "你说只要我能做到", "description": "Compliant and agreeable tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 8.5, 8.8 ], "content": { "speaker": "PERSON_1", "line": "这周末", "description": "Calm and deliberate tone." } } ], "scene_description": "A man and a woman are having a serious conversation in a modern hallway. The man agrees to help her get an identity but states he has a condition, to which the woman readily agrees.", "global_style": "Modern, sleek, dramatic lighting with a slightly cool color palette.", "global_audio": "Quiet ambient room tone with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_75554", "media_path": "drama_04/clip_75554.mp4", "source_media_path": "clips/clip_75554.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Older woman with dark hair tied back, expressing anger", "attributes": "Beige sparkly top with a bow and a brooch, brown belt" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "Young woman with long dark hair, wearing a white bandage over her right eye", "attributes": "Yellow cardigan over a white top" } ], "visual_description": "[PERSON_1] is shown in a close-up, looking angry and yelling.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.3, 3.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Young man with short dark hair, looking down and listening", "attributes": "Grey knitted vest over a light blue collared shirt" } ], "visual_description": "[PERSON_2] is shown in a close-up, looking down and listening to the scolding.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.2, 4.8 ], "references": [ "PERSON_1", "PERSON_3" ], "visual_description": "[PERSON_1] is shown again in a close-up, continuing to yell and pointing her finger.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.8, 6.7 ], "references": [ "PERSON_1", "PERSON_2", "PERSON_3", { "ref_id": "PERSON_4", "type": "person", "id_features": "Older man with short dark hair and a mustache", "attributes": "Dark jacket over a grey shirt" }, { "ref_id": "PERSON_5", "type": "person", "id_features": "Young man with short dark hair", "attributes": "Light blue and white patterned sweater" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden desks, white walls, and a green chalkboard in the background" } ], "visual_description": "A wide shot reveals the layout of [SCENE_1]. [PERSON_1], [PERSON_3], and [PERSON_4] are standing on the right side of a desk, facing [PERSON_2] and [PERSON_5] on the left.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.7, 8.5 ], "references": [ "PERSON_3", "PERSON_2" ], "visual_description": "[PERSON_3] is shown in a close-up, speaking up to defend [PERSON_2].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] }, { "shot_id": "SHOT_6", "time_range": [ 8.5, 9.6 ], "references": [ "PERSON_1", "PERSON_3" ], "visual_description": "[PERSON_1] is shown in a close-up, looking at [PERSON_3] with a stern expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_5" ] }, { "shot_id": "SHOT_7", "time_range": [ 9.6, 10.4 ], "references": [ "PERSON_3" ], "visual_description": "[PERSON_3] is shown in a close-up again, continuing her explanation.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_6" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 1.4 ], "content": { "speaker": "PERSON_1", "line": "这事没完", "description": "Angry and threatening tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.4, 3.4 ], "content": { "speaker": "PERSON_1", "line": "你必须负责必须赔偿", "description": "Demanding and aggressive tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.4, 4.3 ], "content": { "speaker": "PERSON_1", "line": "否则我连学校一起", "description": "Threatening legal action." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 5.3, 7.1 ], "content": { "speaker": "PERSON_3", "line": "爸妈", "description": "Pleading tone." } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 7.1, 9.1 ], "content": { "speaker": "PERSON_3", "line": "是我自己找三合帮忙的", "description": "Explaining the situation." } }, { "event_id": "DIALOGUE_6", "type": "dialogue", "time_range": [ 9.1, 9.7 ], "content": { "speaker": "PERSON_3", "line": "跟他没关系", "description": "Defending the young man." } } ], "scene_description": "An angry mother confronts a male student in a classroom, demanding compensation and threatening to sue the school over an incident involving her injured daughter. The daughter intervenes, explaining that she asked the student for help and that he is not to blame.", "global_style": "Dramatic and tense, typical of a modern Chinese drama or short series.", "global_audio": "Clear dialogue with no prominent background music or sound effects." } }, { "dataset": "drama_04", "clip_id": "clip_97301", "media_path": "drama_04/clip_97301.mp4", "source_media_path": "clips/clip_97301.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Older woman with her hair tied back, wearing a red textured jacket over a white patterned shirt", "attributes": "Red textured jacket, white patterned shirt, carrying a wooden shoulder pole, strings of garlic, a large burlap sack, a blue striped bag, and a green backpack" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor space with a poster featuring Chinese characters on the wall in the background", "attributes": "Indoor lighting, poster on the wall" } ], "visual_description": "[PERSON_1] stands in [SCENE_1] carrying a heavy load of luggage, including a wooden pole and bags. She points her finger forward emphatically while speaking.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.0, 4.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Young woman with long dark hair, wearing a white cable-knit sweater over a red ruffled collar shirt", "attributes": "Long dark hair, white cable-knit sweater, red ruffled collar shirt" }, "SCENE_1" ], "visual_description": "[PERSON_2] is shown looking surprised and slightly confused.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 4.2, 7.5 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] stands holding her luggage. The camera tilts down to focus on the large burlap sack she is carrying, then tilts back up to her face.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "tilt" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 7.5, 11.4 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] looks at [PERSON_1] with a surprised expression and speaks hesitantly.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 8.7 ], "content": { "speaker": "PERSON_1", "line": "肯定在城里没好好吃饭", "description": "Assertive and caring tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 8.7, 10.7 ], "content": { "speaker": "PERSON_2", "line": "你是妈", "description": "Hesitant, surprised, and questioning tone." } } ], "scene_description": "A mother arrives from the countryside heavily laden with food and supplies, surprising her daughter who initially doesn't recognize her.", "global_style": "Realistic, dramatic, slightly comedic family reunion scene.", "global_audio": "Clear dialogue with no prominent background music." } }, { "dataset": "drama_04", "clip_id": "clip_39531", "media_path": "drama_04/clip_39531.mp4", "source_media_path": "clips/clip_39531.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark hair pulled back, a thin mustache, and a small goatee", "attributes": "clothing: White robe with gold embroidery., hairstyle: Dark hair pulled back into a topknot., accessories: None visible" } ], "visual_description": "A close-up shot of [PERSON_1] speaking with an intense and urgent expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 5.0, 7.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "An older, heavier-set man with a full black beard and mustache", "attributes": "clothing: Dark blue robe with light blue cloud patterns and a large jade belt., hairstyle: Dark hair pulled into a topknot with a gold hairpiece., accessories: Gold hairpiece, jade belt" } ], "visual_description": "A medium shot of [PERSON_2] raising his hand to interrupt, with a serious expression.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.0, 10.0 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden paneled walls, a wooden table, two teacups, a teapot, and a decorative clock" } ], "visual_description": "A wide shot showing [PERSON_2] standing and speaking to [PERSON_1], who is now seated at a table in [SCENE_1].", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.9, 4.4 ], "content": { "speaker": "PERSON_1", "line": "做出政绩来不论是升迁还是让张家更进一步都", "description": "Urgent and passionate tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.4, 8.0 ], "content": { "speaker": "PERSON_2", "line": "能可惜家族已经无力支持你了", "description": "Resigned and regretful tone." } } ], "scene_description": "Two men are having a serious conversation in a traditional room. The younger man is passionately arguing for a course of action to advance their family, but the older man interrupts him with the bad news that the family can no longer support him.", "global_style": "3D animated historical or fantasy drama with realistic character designs and traditional Chinese aesthetics.", "global_audio": "Quiet background with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_75070", "media_path": "drama_04/clip_75070.mp4", "source_media_path": "clips/clip_75070.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair, wearing glasses", "attributes": "White double-breasted suit jacket, black t-shirt, silver necklace, glasses" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious room with a green leather sofa, wooden cabinets, a large patterned rug, and a prominent chandelier" } ], "visual_description": "[PERSON_1] is looking down and speaking with a submissive expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.3, 3.3 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair", "attributes": "Plaid button-up shirt over a white t-shirt" }, "SCENE_1" ], "visual_description": "[PERSON_2] stands with his arms crossed, looking away with a slight smirk.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.3, 5.1 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] looks up towards someone off-screen while speaking earnestly.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.1, 6.5 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "An older man with short black hair and glasses", "attributes": "Black suit, white shirt, brown patterned tie" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "An older woman with her hair tied back", "attributes": "Black and white houndstooth jacket, black skirt, pearl earrings" }, "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_3] and [PERSON_4] stand side-by-side, looking sternly at [PERSON_1].", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4", "DIALOGUE_5" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.5, 8.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] continues speaking with a pleading expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_6" ] }, { "shot_id": "SHOT_6", "time_range": [ 8.0, 9.0 ], "references": [ { "ref_id": "PERSON_5", "type": "person", "id_features": "A young woman with long wavy black hair", "attributes": "White halter top with ruffled sleeves" }, "SCENE_1" ], "visual_description": "[PERSON_5] looks on with an annoyed and conflicted expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_6" ] }, { "shot_id": "SHOT_7", "time_range": [ 9.0, 10.4 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] looks down, maintaining his crossed arms stance.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_8", "time_range": [ 10.4, 11.0 ], "references": [ "PERSON_1", "PERSON_2", "PERSON_3", "PERSON_4", "PERSON_5", "SCENE_1" ], "visual_description": "A high-angle view reveals [PERSON_1] kneeling on the rug in [SCENE_1], surrounded by [PERSON_2], [PERSON_3], [PERSON_4], and [PERSON_5].", "camera": { "shot_type": "wide shot", "angle": "high angle", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.4, 1.5 ], "content": { "speaker": "PERSON_1", "line": "说的没错", "description": "Submissive and admitting tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.5, 3.4 ], "content": { "speaker": "PERSON_1", "line": "我就是一个替代品", "description": "Self-deprecating tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.4, 4.2 ], "content": { "speaker": "PERSON_1", "line": "哪怕是让我", "description": "Pleading tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 4.2, 5.7 ], "content": { "speaker": "PERSON_1", "line": "现在离开亲家", "description": "Resigned tone." } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 5.7, 6.5 ], "content": { "speaker": "PERSON_1", "line": "我", "description": "Hesitant tone." } }, { "event_id": "DIALOGUE_6", "type": "dialogue", "time_range": [ 6.7, 7.3 ], "content": { "speaker": "PERSON_1", "line": "也丝毫没有", "description": "Firm but submissive tone." } } ], "scene_description": "A tense family confrontation where a young man is kneeling and apologizing to the family members, admitting his faults and expressing his willingness to leave.", "global_style": "Modern Chinese drama, well-lit interior, dramatic and emotional.", "global_audio": "Dialogue-driven with a serious and tense atmosphere." } }, { "dataset": "drama_04", "clip_id": "clip_94904", "media_path": "drama_04/clip_94904.mp4", "source_media_path": "clips/clip_94904.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 7.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair and a fair complexion", "attributes": "Wearing a grey cardigan over a green plaid shirt and a white t-shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A softly lit room with a bed and a window in the background" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], looking slightly downward with a serious and frustrated expression as he speaks. The camera captures him from the chest up.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_2", "time_range": [ 7.3, 10.4 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long, dark, wavy hair", "attributes": "Wearing a blue and white striped pajama shirt" }, "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2] sitting on a bed in [SCENE_1]. She is looking away, appearing distant or upset, and holds a black smartphone in her lap.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_3" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Emotional pop song with vocals playing in the background." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.2, 4.3 ], "content": { "speaker": "PERSON_1", "line": "你别老不乐不乐的好吗", "description": "Frustrated and pleading tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.3, 6.1 ], "content": { "speaker": "PERSON_1", "line": "我是不会相信的", "description": "Firm and disbelieving tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 6.1, 7.3 ], "content": { "speaker": "PERSON_1", "line": "你别撒这种幼稚的谎心吗", "description": "Accusatory and exasperated tone." } } ], "scene_description": "A young man confronts a young woman, accusing her of lying, while she sits quietly on a bed.", "global_style": "Dramatic, soft lighting, intimate framing.", "global_audio": "Emotional background music." } }, { "dataset": "drama_04", "clip_id": "clip_89084", "media_path": "drama_04/clip_89084.mp4", "source_media_path": "clips/clip_89084.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, wearing glasses and her dark hair tied back in a ponytail", "attributes": "White zip-up jacket over a white t-shirt, black-rimmed rectangular glasses" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A standard black smartphone", "attributes": "Black casing" } ], "visual_description": "A close-up shot of [PERSON_1] holding [OBJECT_1] to her ear, smiling as she speaks. Her expression quickly shifts to surprise and confusion as she listens to the response. She then awkwardly says goodbye.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_2", "time_range": [ 5.9, 9.4 ], "references": [ "PERSON_1", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room featuring a desk with books, a laptop, a glowing desk lamp, and a large bookshelf filled with books and decorative items in the background", "attributes": "Warm lighting, organized, modern interior" }, "OBJECT_1", { "ref_id": "OBJECT_2", "type": "object", "id_features": "A laptop computer open on the desk", "attributes": "Silver or light-colored" } ], "visual_description": "A wide shot showing [PERSON_1] sitting at her desk in [SCENE_1]. She slowly lowers [OBJECT_1] from her ear, looking embarrassed. Animated crows and ellipsis dots appear above her head to visually represent the awkwardness of the situation.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 9.4, 10.0 ], "references": [ "PERSON_1", "OBJECT_2" ], "visual_description": "A close-up shot of [PERSON_1]. She looks annoyed and slightly resigned, letting out a small sigh before she starts typing on [OBJECT_2].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.1, 2.8 ], "content": { "speaker": "PERSON_1", "line": "不明天我们一起", "description": "Hopeful and friendly suggestion." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.8, 5.3 ], "content": { "speaker": "PERSON_2", "line": "什么我打错电话了不好意思", "description": "Confused realization followed by an apology." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.3, 5.5 ], "content": { "speaker": "PERSON_1", "line": "拜拜", "description": "Awkward and hasty farewell." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 5.0, 7.0 ], "content": { "description": "A comedic crow cawing sound effect, emphasizing an awkward silence." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 8.0, 10.0 ], "content": { "description": "Sound of fingers typing on a keyboard." } } ], "scene_description": "A young woman is on a phone call, seemingly making plans, when the person on the other end reveals they dialed the wrong number. She awkwardly ends the call and, feeling embarrassed, returns to her work on her laptop.", "global_style": "Modern, comedic, slice-of-life short video with bright and warm lighting.", "global_audio": "Clear dialogue with comedic sound effects used to highlight the awkwardness of the situation." } }, { "dataset": "drama_04", "clip_id": "clip_32845", "media_path": "drama_04/clip_32845.mp4", "source_media_path": "clips/clip_32845.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long black hair, wearing a white button-down shirt and white knee-high boots", "attributes": "long black hair, white button-down shirt, white knee-high boots" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair, wearing a white varsity jacket with black stripes, a white t-shirt, a silver necklace, and blue jeans", "attributes": "short black hair, white varsity jacket, white t-shirt, silver necklace, blue jeans" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "The exterior of a house at night, featuring a lit open doorway, a pathway, and some plants", "attributes": "nighttime, lit doorway, pathway, plants" } ], "visual_description": "[PERSON_1] and [PERSON_2] are standing outside [SCENE_1]. [PERSON_1] turns away slightly.", "camera": { "shot_type": "full shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.2, 3.8 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "A close-up of [PERSON_1] looking at [PERSON_2] and speaking.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.8, 5.2 ], "references": [ "PERSON_2", "PERSON_1" ], "visual_description": "A close-up of [PERSON_2] looking at [PERSON_1] and speaking.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.2, 6.8 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "A close-up of [PERSON_1] smiling and nodding as [PERSON_2] continues to speak off-screen.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.8, 8.5 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young man with short black hair, wearing a grey crewneck sweater and a silver necklace, holding a white garment", "attributes": "short black hair, grey sweater, silver necklace, holding a white garment" }, "SCENE_1" ], "visual_description": "Viewed from inside the house, [PERSON_3] appears in the doorway, looking surprised.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_6", "time_range": [ 8.5, 10.0 ], "references": [ "PERSON_1", "PERSON_2" ], "visual_description": "A close-up of [PERSON_2] turning his head with a surprised expression. [PERSON_1] is partially visible in the foreground.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.5, 2.8 ], "content": { "speaker": "PERSON_1", "line": "没有", "description": "Denial" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.8, 4.4 ], "content": { "speaker": "PERSON_1", "line": "我们先回去吧", "description": "Suggesting to leave" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.4, 5.6 ], "content": { "speaker": "PERSON_2", "line": "那先上车吧", "description": "Agreeing and suggesting an action" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 5.6, 5.9 ], "content": { "speaker": "PERSON_2", "line": "你别着凉", "description": "Expressing care" } } ], "scene_description": "A man and a woman are talking outside a house at night, deciding to leave. Suddenly, another man appears in the doorway, surprising them.", "global_style": "Dramatic, nighttime lighting with a focus on character expressions.", "global_audio": "Quiet outdoor ambience with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_96760", "media_path": "drama_04/clip_96760.mp4", "source_media_path": "clips/clip_96760.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Young boy with short dark hair, fair skin", "attributes": "Grey zip-up sweater over a white long-sleeve shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Blurred indoor background with warm lighting" } ], "visual_description": "[PERSON_1] is lying down, resting his arms in front of him, looking attentively downward at something out of frame.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 4.4, 9.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Young man with dark, slightly messy hair, fair skin", "attributes": "Black leather jacket over a black turtleneck sweater, holding a black smartphone" }, "SCENE_1" ], "visual_description": "The scene cuts to [PERSON_2] holding a smartphone to his right ear. He looks down with a serious expression, listens for a moment, and then speaks into the phone.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_1", "DIALOGUE_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 4.0, 7.0 ], "content": { "description": "Electronic ringing or connection tone from a phone." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 8.8, 9.1 ], "content": { "speaker": "PERSON_2", "line": "李老师", "description": "Serious, addressing someone respectfully." } } ], "scene_description": "A young boy is seen resting quietly, followed by a cut to a young man who is making a serious phone call, addressing the person on the other end as 'Teacher Li'.", "global_style": "Cinematic, soft focus background, warm and slightly muted color palette.", "global_audio": "Quiet ambient sound, transitioning to a phone connection sound effect and a brief line of dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_67616", "media_path": "drama_04/clip_67616.mp4", "source_media_path": "clips/clip_67616.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin and black hair tied back", "attributes": "clothing: Black long-sleeved top with a dark green collar., hairstyle: Black hair tied back., accessories: None visible" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor space with dark, muted lighting and indistinct background details" } ], "visual_description": "[PERSON_1] is looking down, wincing in pain, and holding her arm.", "camera": { "shot_type": "Close-up", "angle": "High angle", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.8, 7.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short black hair and glasses", "attributes": "clothing: Black shirt., hairstyle: Short black hair., accessories: Wire-rimmed glasses" }, "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], who is looking at [PERSON_1] with a surprised and concerned expression. He then speaks to her.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.0, 9.7 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1], who looks up with a surprised expression, realizing she just spoke. She points a finger at herself.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 1.5 ], "content": { "speaker": "PERSON_1", "line": "疼疼", "description": "Expressing pain." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 5.0, 6.5 ], "content": { "speaker": "PERSON_2", "line": "你能说话了", "description": "Surprised realization." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.5, 9.0 ], "content": { "speaker": "PERSON_1", "line": "一", "description": "Uttering a sound in disbelief." } } ], "scene_description": "A woman in pain accidentally speaks, surprising both herself and the man with her, implying she was previously unable to speak.", "global_style": "Dramatic and moody with dark, low-key lighting.", "global_audio": "Quiet ambient room tone with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_55370", "media_path": "drama_04/clip_55370.mp4", "source_media_path": "clips/clip_55370.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with fair skin and red lipstick, wearing an elaborate golden outfit and a highly ornate golden headpiece with long red tassels", "attributes": "clothing: Golden robes with intricate embroidery and a wide belt., hairstyle: Updo adorned with a large, complex golden crown-like headpiece featuring dangling red tassels., accessories: Golden headpiece, red tassels, earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An opulent room with golden decorative elements, a patterned floor, and ornate background structures" } ], "visual_description": "[PERSON_1] stands in [SCENE_1], looking forward with a serious and slightly concerned expression.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.3, 3.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A middle-aged man with a mustache and goatee, wearing a red official's robe and a black hat", "attributes": "clothing: Red long-sleeved robe with a dark embroidered square patch on the chest., hairstyle: Concealed by hat., accessories: Black official's hat with a gold band" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A middle-aged man with a mustache and goatee, wearing a red official's robe and a black hat, similar to the speaking official", "attributes": "clothing: Red long-sleeved robe with a dark embroidered square patch on the chest., hairstyle: Concealed by hat., accessories: Black official's hat" }, "SCENE_1" ], "visual_description": "[PERSON_2] and [PERSON_3] are kneeling on the patterned floor of [SCENE_1]. [PERSON_2] has his hands clasped in front of him and is speaking urgently.", "camera": { "shot_type": "Medium shot", "angle": "High angle", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.2, 5.9 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera returns to [PERSON_1], who is listening intently to the report, her expression remaining serious.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.9, 8.5 ], "references": [ "PERSON_2", "PERSON_3", "SCENE_1" ], "visual_description": "The view cuts back to [PERSON_2] and [PERSON_3] kneeling. [PERSON_2] continues to speak with a distressed and urgent demeanor.", "camera": { "shot_type": "Medium shot", "angle": "High angle", "movement": "Static" }, "active_events": [ "DIALOGUE_4", "DIALOGUE_5" ] }, { "shot_id": "SHOT_5", "time_range": [ 8.5, 10.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_4", "type": "person", "id_features": "A man wearing a blue official's robe and a black hat", "attributes": "clothing: Blue long-sleeved robe., hairstyle: Concealed by hat., accessories: Black official's hat" }, "SCENE_1" ], "visual_description": "[PERSON_1] turns around abruptly, her robes swirling, and begins to walk towards the back of [SCENE_1]. [PERSON_4] is partially visible standing on the left side of the frame.", "camera": { "shot_type": "Wide shot", "angle": "Eye level", "movement": "Static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.6, 1.2 ], "content": { "speaker": "PERSON_2", "line": "陛下", "description": "Respectful address" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.2, 3.4 ], "content": { "speaker": "PERSON_2", "line": "自从张求通敌消息传出", "description": "Reporting urgent news" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.4, 4.9 ], "content": { "speaker": "PERSON_2", "line": "半数官员竟卷财", "description": "Describing a dire situation" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 5.7, 7.4 ], "content": { "speaker": "PERSON_2", "line": "皆是张求一党", "description": "Explaining the cause" } }, { "event_id": "DIALOGUE_5", "type": "dialogue", "time_range": [ 7.4, 9.5 ], "content": { "speaker": "PERSON_2", "line": "等着改朝换代", "description": "Expressing grave concern and warning" } } ], "scene_description": "A court official urgently reports to the empress about a crisis involving treason and fleeing officials, prompting the empress to turn away in apparent frustration or resolve.", "global_style": "Historical Chinese costume drama with rich, vibrant colors, focusing on gold and red tones to emphasize royal authority.", "global_audio": "Dramatic and tense background music accompanying the urgent dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_58254", "media_path": "drama_04/clip_58254.mp4", "source_media_path": "clips/clip_58254.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with a fair complexion and dark hair styled elaborately", "attributes": "Green traditional Chinese dress with embroidered patterns, a black fur collar, and ornate hair accessories" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A blurred background showing steps and other figures in traditional clothing", "attributes": "Historical architecture, outdoor lighting" } ], "visual_description": "[PERSON_1] turns around playfully with a smile in [SCENE_1], her green dress flowing.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Tracking" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.7, 10.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young girl with a round face and dark hair styled in twin buns", "attributes": "Blue and white traditional dress with gold accents, a white fur collar with pom-poms, and delicate hair ornaments" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "Only the arms and hands are visible", "attributes": "Light-colored flowing sleeves with a pink sash or trim" } ], "visual_description": "[PERSON_2] is being held by the arms of [PERSON_3]. [PERSON_2] initially has her eyes squeezed shut tightly, appearing braced for something. She then slowly opens her eyes and looks around with a confused and surprised expression.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 1.0 ], "content": { "speaker": "PERSON_1", "line": "呀", "description": "Playful exclamation" } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 1.0, 10.0 ], "content": { "description": "A dramatic, tense sound effect that transitions into a lighter, revealing chime as the girl opens her eyes." } } ], "scene_description": "A woman in traditional dress turns playfully, followed by a cut to a young girl being held who slowly opens her eyes in surprise.", "global_style": "Historical Chinese drama aesthetic with bright, natural lighting and elaborate costumes.", "global_audio": "Dramatic sound effects accompanying the visual transition." } }, { "dataset": "drama_04", "clip_id": "clip_29401", "media_path": "drama_04/clip_29401.mp4", "source_media_path": "clips/clip_29401.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with long dark hair tied in a half-up style with a silver hairpiece, wearing a dark blue or black robe with silver inner layers and gold embroidery", "attributes": "Long dark hair, silver hairpiece, dark robe, gold embroidery, silver inner layers" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A cylindrical wooden stick, likely the handle of a shovel", "attributes": "Wooden, cylindrical, stick" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dirt path or field with sparse grass, illuminated by moonlight or ambient night light", "attributes": "Nighttime, dirt, grass, outdoor" } ], "visual_description": "[PERSON_1] is shown from the waist up, holding [OBJECT_1]. He looks slightly to his left and speaks.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.5, 4.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A younger man with short dark hair, wearing a simple dark outfit", "attributes": "Short dark hair, dark outfit" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A man lying flat on his back on the ground, wearing a dark blue outfit with a prominent belt", "attributes": "Dark blue outfit, belt, lying on the ground" }, "SCENE_1" ], "visual_description": "[PERSON_3] is lying motionless on the ground in [SCENE_1]. [PERSON_2] enters the frame from the right, points his finger at [PERSON_3], and speaks.", "camera": { "shot_type": "Medium shot", "angle": "High angle", "movement": "Pan right" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.2, 9.3 ], "references": [ "PERSON_1", "OBJECT_1", "SCENE_1" ], "visual_description": "[PERSON_1] is shown again holding [OBJECT_1]. He speaks with an exasperated expression, looking forward.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.3, 10.4 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A close-up of [PERSON_1]'s face as he looks slightly down and to the side.", "camera": { "shot_type": "Close-up", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 1.7 ], "content": { "speaker": "PERSON_1", "line": "试试铲子结不结实", "description": "Casual statement" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.7, 4.5 ], "content": { "speaker": "PERSON_2", "line": "王爷郡主这坑不是埋那两个贼人的吗", "description": "Inquiring tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.5, 9.1 ], "content": { "speaker": "PERSON_1", "line": "看看你府上酒囊饭袋这么多人打不过两个还得本王收拾烂摊", "description": "Exasperated and authoritative tone" } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 9.7, 10.0 ], "content": { "speaker": "PERSON_4", "line": "就是", "description": "Agreeing tone" } } ], "scene_description": "A nobleman complains about having to clean up a mess after his subordinates failed to handle two thieves, while standing near an unconscious body at night.", "global_style": "3D animated fantasy or historical drama with realistic lighting and detailed character models.", "global_audio": "Quiet nighttime ambience with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_13298", "media_path": "drama_04/clip_13298.mp4", "source_media_path": "clips/clip_13298.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.6 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Young man with brown hair, wearing a black turtleneck, a silver necklace with a heart pendant, and a brown trench coat with a checkered collar", "attributes": "brown hair, black turtleneck, silver necklace, brown trench coat, checkered collar" } ], "visual_description": "A close-up shot of [PERSON_1] against a plain, light background. He initially looks downwards with a serious expression, then slowly raises his eyes to look forward.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.6, 10.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "Young woman with long dark hair, wearing a light-colored top with draped sleeves and a brown skirt", "attributes": "long dark hair, light-colored top, brown skirt" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "Young man wearing glasses and a white suit", "attributes": "glasses, white suit" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dark room featuring a large, dark wooden double door with ornate golden handles. The view is partially obscured by a dark, blurry foreground, suggesting a perspective through a gap or peephole" } ], "visual_description": "The scene shifts to [SCENE_1], viewed through a dark, blurry foreground opening. [PERSON_2] walks towards the large double doors, followed closely by [PERSON_3]. They stop and stand in front of the doors. Shortly after, [PERSON_1] enters the frame from the left and stands behind them, observing.", "camera": { "shot_type": "wide shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Dramatic and suspenseful instrumental music plays throughout the video." } } ], "scene_description": "A man is shown in a close-up before the scene cuts to a voyeuristic view of a woman and another man approaching a large door. The first man then appears in the scene, standing behind them.", "global_style": "Dramatic and suspenseful, with a shift from a brightly lit portrait shot to a dimly lit, voyeuristic scene.", "global_audio": "Suspenseful instrumental background music." } }, { "dataset": "drama_04", "clip_id": "clip_44055", "media_path": "drama_04/clip_44055.mp4", "source_media_path": "clips/clip_44055.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with a serious expression, wearing traditional royal attire", "attributes": "Yellow and gold patterned robe, hair tied up with an ornate golden crown" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A richly decorated interior with traditional architectural elements", "attributes": "Red pillars, wooden lattice screens, warm lighting" } ], "visual_description": "[PERSON_1] is shown in a close-up, looking slightly downward and speaking with a serious expression.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.5, 7.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with elegant makeup, looking submissive but composed", "attributes": "Yellow and gold dress, elaborate golden hair ornaments, gold necklace" }, "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] is seen in a close-up. She looks down initially, then raises her eyes to respond to [PERSON_1].", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.2, 9.6 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "A medium shot shows both [PERSON_2] and [PERSON_1] in [SCENE_1]. [PERSON_1] steps closer to [PERSON_2] while speaking.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.6, 10.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts back to a close-up of [PERSON_1] as he continues speaking with a stern look.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.0, 5.2 ], "content": { "speaker": "PERSON_2", "line": "臣妾明白", "description": "Submissive and understanding tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.2, 7.7 ], "content": { "speaker": "PERSON_1", "line": "本宫不能行人道之事", "description": "Serious, revealing tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 7.7, 9.3 ], "content": { "speaker": "PERSON_1", "line": "如果你能和杨战有个子嗣", "description": "Instructive and stern tone." } } ], "scene_description": "A tense conversation between a royal couple where the man reveals his inability to consummate the marriage and suggests the woman have a child with another man to secure power.", "global_style": "Traditional Chinese historical drama, rich golden and red tones, dramatic lighting.", "global_audio": "Quiet, tense atmosphere with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_14560", "media_path": "drama_04/clip_14560.mp4", "source_media_path": "clips/clip_14560.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.9 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with short black hair, wearing glasses", "attributes": "Black suit, white shirt, yellow tie, glasses" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A modern indoor environment with blue-tinted walls and glass partitions", "attributes": "Blue walls, glass windows" } ], "visual_description": "[PERSON_1] is looking at a document in his hand and speaking. He briefly looks up before looking back down at the paper.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.9, 8.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with her hair tied back, wearing earrings", "attributes": "Beige trench coat, earrings, necklace" }, "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] is standing with her arms crossed, looking intently towards [PERSON_1] as she listens to him speak.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 8.8, 10.0 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with short black hair, wearing glasses and a stethoscope", "attributes": "White lab coat, glasses, stethoscope" }, "SCENE_1" ], "visual_description": "[PERSON_3] is leaning against a glass partition, holding the earpieces of a stethoscope to his ears and pressing the chest piece against the glass to eavesdrop.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.9, 8.2 ], "content": { "speaker": "PERSON_1", "line": "单位SGLTR一直记五千单位", "description": "Continuing to read medical quantities aloud." } } ], "scene_description": "A man in a suit reads a list of medical supplies to a woman, while a doctor secretly listens in on their conversation from behind a glass wall.", "global_style": "Modern, slightly cool-toned lighting, dramatic.", "global_audio": "Quiet ambient room noise with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_23334", "media_path": "drama_04/clip_23334.mp4", "source_media_path": "clips/clip_23334.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with a serious expression", "attributes": "Wearing a dark blue robe with gold dragon embroidery, a white collar, and a black headpiece with gold accents" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with a surprised or concerned expression", "attributes": "Wearing a white robe with light green accents, hair styled up with hairpins and dangling earrings" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A nighttime scene with red maple leaves visible in the background and green leafy plants in the foreground" } ], "visual_description": "[PERSON_1] and [PERSON_2] are standing in [SCENE_1]. [PERSON_1] is holding a pink cloth or pouch, looking at [PERSON_2] and then down at the object. [PERSON_2] is seen from behind.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.2, 8.9 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young woman with a calm expression", "attributes": "Wearing a bright pink robe, hair styled up with ornaments and a long braid down her back, wearing a necklace" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "A space enclosed by white curtains, featuring a table with teacups and floral arrangements" } ], "visual_description": "[PERSON_3] is standing in [SCENE_2]. She looks around slightly, then turns and walks away, disappearing behind a white curtain.", "camera": { "shot_type": "full shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1", "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 8.9, 10.0 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] is hiding behind green leafy plants in [SCENE_1]. She looks surprised and concerned, peering through the leaves.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Dramatic and slightly suspenseful background music." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 2.0, 3.0 ], "content": { "description": "A sharp, chiming sound effect as the scene transitions." } } ], "scene_description": "A tense sequence where a man and a woman interact in a garden, followed by a cut to another woman in a pavilion. The first woman is then shown hiding and observing from behind plants.", "global_style": "Historical Chinese drama aesthetic with elaborate costumes, nighttime lighting, and rich colors.", "global_audio": "Suspenseful background music with a distinct sound effect marking a scene transition." } }, { "dataset": "drama_04", "clip_id": "clip_59517", "media_path": "drama_04/clip_59517.mp4", "source_media_path": "clips/clip_59517.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long, wavy dark hair, wearing silver hoop earrings", "attributes": "Black blazer over a light blue top" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A blurred, neutral-colored indoor space, possibly an unfinished building or warehouse, with soft natural lighting", "attributes": "Blurred background, neutral tones" } ], "visual_description": "[PERSON_1] is seen in a medium close-up, looking slightly to her right and speaking with a serious, intense expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.3, 5.3 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman wearing a large black wide-brimmed hat and oversized square sunglasses, concealing her eyes", "attributes": "Black-and-white patterned coat with solid black lapels, and a small necklace" }, "SCENE_1" ], "visual_description": "[PERSON_2] is shown in a medium close-up, looking down slightly with a stoic and unreadable expression due to her sunglasses.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.3, 7.5 ], "references": [ "PERSON_2", { "ref_id": "OBJECT_1", "type": "object", "id_features": "A brown paper bag with thick white handles", "attributes": "Brown, paper material, white handles" }, "SCENE_1" ], "visual_description": "A close-up focuses on [PERSON_2]'s hand as she tightly grips the handles of [OBJECT_1], her knuckles slightly white, indicating underlying tension.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "SFX_1", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 7.5, 9.1 ], "references": [ "PERSON_1", "SCENE_1", "PERSON_2" ], "visual_description": "The camera cuts back to [PERSON_1] in a medium close-up, who continues to look intently at [PERSON_2] in silence.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 9.1, 10.0 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "The shot returns to [PERSON_2], who slightly raises her head, maintaining her tense and serious demeanor.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.2, 2.7 ], "content": { "speaker": "PERSON_1", "line": "也是你保全自己性命的唯一", "description": "Serious, threatening, and assertive tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 4.0, 7.0 ], "content": { "description": "Sound of a paper bag being tightly gripped and crinkling." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Tense, dramatic background music that builds suspense." } } ], "scene_description": "A tense confrontation between two women, where one delivers a serious, life-threatening warning to the other, who reacts with silent, physical tension.", "global_style": "Dramatic and cinematic, featuring a shallow depth of field that isolates the characters against a blurred background, emphasizing their facial expressions and subtle gestures.", "global_audio": "Suspenseful background music accompanied by clear dialogue and subtle foley sounds highlighting the physical tension." } }, { "dataset": "drama_04", "clip_id": "clip_28162", "media_path": "drama_04/clip_28162.mp4", "source_media_path": "clips/clip_28162.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin and black hair styled in an elegant updo adorned with hairpins", "attributes": "Wearing a yellow traditional high-collared top" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A traditional Chinese calligraphy brush with a dark wooden handle and dark bristles" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "White paper with black ink Chinese characters written on it" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with wooden lattice doors and windows in the background, suggesting a historical or traditional setting" } ], "visual_description": "[PERSON_1] sits at a desk in [SCENE_1], holding [OBJECT_1] and writing on [OBJECT_2].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.2, 6.5 ], "references": [ "PERSON_1", "OBJECT_1", "OBJECT_2" ], "visual_description": "A close-up view of [PERSON_1]'s hand using [OBJECT_1] to write Chinese characters on [OBJECT_2].", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.5, 8.2 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] looks down at her writing, then slightly raises her eyes.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.2, 10.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A baby with short dark hair, large dark eyes, and chubby cheeks", "attributes": "Wrapped tightly in a beige and gold patterned blanket" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "Only the shoulder and chest area are visible", "attributes": "Wearing a dark garment with intricate gold embroidery" } ], "visual_description": "[PERSON_2] is wrapped tightly in a blanket and held by [PERSON_3]. [PERSON_2] looks around with wide eyes.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.1, 3.1 ], "content": { "speaker": null, "line": "来了来了藏不住了", "description": "Excited narrative voiceover." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.1, 6.8 ], "content": { "speaker": null, "line": "关文斌的字以风骨闻名尤其是那这一笔", "description": "Informative narrative voiceover." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 6.8, 9.7 ], "content": { "speaker": null, "line": "会有一个极其微小的上条被称为文斌钩", "description": "Informative narrative voiceover." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Gentle, traditional instrumental background music." } } ], "scene_description": "A woman practices calligraphy, focusing on a specific brushstroke technique, followed by a shot of a baby.", "global_style": "Historical Chinese drama aesthetic with warm lighting and traditional costumes.", "global_audio": "A female voiceover explains calligraphy techniques over gentle traditional music." } }, { "dataset": "drama_04", "clip_id": "clip_15745", "media_path": "drama_04/clip_15745.mp4", "source_media_path": "clips/clip_15745.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.6 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with long silver hair and a golden mark on his forehead", "attributes": "Wearing elaborate green and gold traditional robes" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with long black hair, cuts on her face, and blood on her clothes", "attributes": "Wearing a white dress with blood stains. In flashbacks, she wears a bright red wedding dress with a gold crown" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A traditional Chinese courtyard or room with wooden architectural elements and a bonsai tree in the background" } ], "visual_description": "A medium shot showing [PERSON_1] and [PERSON_2] facing each other in [SCENE_1]. [PERSON_1] speaks angrily to [PERSON_2], who stands silently with a wounded expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.6, 5.2 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "A close-up shot of [PERSON_2]'s face in [SCENE_1]. She looks down slightly with a sorrowful and resigned expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.2, 8.1 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_2", "type": "scene", "id_features": "An outdoor setting with red pillars, resembling a bridge or balcony" } ], "visual_description": "A flashback shot in [SCENE_2] showing [PERSON_1] and [PERSON_2] holding hands. [PERSON_2] is dressed in elaborate red wedding attire.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.1, 9.7 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "PERSON_3", "type": "person", "id_features": "A woman with brown hair", "attributes": "Wearing a pinkish-red dress" }, "SCENE_2" ], "visual_description": "Another flashback shot in [SCENE_2]. [PERSON_3] is kneeling on the ground in front of [PERSON_1], while [PERSON_2] stands behind them watching the interaction.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.5, 5.8 ], "content": { "speaker": "PERSON_1", "line": "沈青顏不過一碗血你就這般惡毒見不得柔兒好", "description": "Angry and accusatory tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 5.8, 9.1 ], "content": { "speaker": "PERSON_2", "line": "我看著他眼裡的厭氣笑了我曾是他的結髮妻", "description": "Sad, reflective internal monologue." } } ], "scene_description": "A tense confrontation between a man and a wounded woman, followed by the woman's sad internal reflection on their past relationship and marriage.", "global_style": "3D Chinese animation (donghua) with traditional fantasy aesthetics and dramatic lighting.", "global_audio": "Dramatic background music accompanying spoken dialogue and internal monologue." } }, { "dataset": "drama_04", "clip_id": "clip_84353", "media_path": "drama_04/clip_84353.mp4", "source_media_path": "clips/clip_84353.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with black hair, wearing a brown jacket over a black turtleneck, and black sunglasses", "attributes": "brown jacket, black turtleneck, black sunglasses, black hair" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with shoulder-length dark hair, wearing round glasses, a yellow reflective vest over a white sweater", "attributes": "yellow reflective vest, white sweater, round glasses, dark hair" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A street covered in snow, with bare trees and a blurred background", "attributes": "snow, street, trees" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A black sedan parked on the snowy street", "attributes": "black, sedan, car" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A blue and grey electric scooter lying on its side in the snow", "attributes": "blue, grey, scooter" }, { "ref_id": "OBJECT_3", "type": "object", "id_features": "A yellow and pink delivery box lying on the ground", "attributes": "yellow, pink, box" } ], "visual_description": "[PERSON_1] exits [OBJECT_1] and walks towards [PERSON_2], who is sitting on the ground next to [OBJECT_2] and [OBJECT_3] in [SCENE_1].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1", "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.2, 4.5 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_1] grabs [PERSON_2] by the arm and helps her stand up while speaking to her.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "pan" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.5, 6.1 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "A close-up of [PERSON_2] looking up with a surprised and slightly dazed expression.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "SFX_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 6.1, 10.0 ], "references": [ "PERSON_1", "SCENE_1", "PERSON_2" ], "visual_description": "A close-up of [PERSON_1] taking off his sunglasses while looking down at [PERSON_2].", "camera": { "shot_type": "close-up", "angle": "low angle", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 2.0 ], "content": { "description": "Footsteps crunching in the snow." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.2, 5.0 ], "content": { "speaker": "PERSON_1", "line": "路你跑这么快干什么", "description": "Slightly annoyed but concerned tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.0, 5.7 ], "content": { "speaker": "PERSON_1", "line": "幸好我刹车", "description": "Relieved tone." } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 6.0, 8.0 ], "content": { "description": "A magical, sparkling chime sound effect." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 8.0, 10.0 ], "content": { "description": "Romantic background music starts playing." } } ], "scene_description": "A man gets out of his car to help a female delivery rider who has fallen off her scooter in the snow. As he helps her up and speaks to her, she looks at him in surprise, and he takes off his sunglasses, hinting at a romantic encounter.", "global_style": "A dramatic, slightly romantic winter scene with a soft focus and cool color palette.", "global_audio": "Ambient winter sounds with dialogue, transitioning into a magical sound effect and romantic music." } }, { "dataset": "drama_04", "clip_id": "clip_95126", "media_path": "drama_04/clip_95126.mp4", "source_media_path": "clips/clip_95126.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long dark hair, wearing a white lab coat over a yellow collared shirt, with pearl earrings and a blue surgical mask pulled down under her chin", "attributes": "long dark hair, white lab coat, yellow collared shirt, pearl earrings, blue surgical mask under chin" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor setting with low lighting, featuring shelves with bottles or equipment blurred in the background", "attributes": "dimly lit, shelves in background, indoor" } ], "visual_description": "[PERSON_1] is shown from the chest up, looking slightly nervous as she speaks to someone off-screen.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "EVENT_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.7, 6.1 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short dark hair, wearing a black leather jacket over a white shirt and black tie", "attributes": "short dark hair, black leather jacket, white shirt, black tie" }, "SCENE_1" ], "visual_description": "The view cuts to [PERSON_2], shown from the chest up, looking intently off-screen while listening.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "EVENT_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.1, 7.9 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera returns to [PERSON_1] as she continues her explanation.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "EVENT_2", "EVENT_3" ] }, { "shot_id": "SHOT_4", "time_range": [ 7.9, 9.3 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "The view cuts back to [PERSON_2], who maintains his serious and focused gaze.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_5", "time_range": [ 9.3, 9.7 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera shows [PERSON_1] again, who looks down slightly, appearing subdued.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] } ], "events": [ { "event_id": "EVENT_1", "type": "dialogue", "time_range": [ 2.9, 4.0 ], "content": { "speaker": "PERSON_1", "line": "不太熟悉", "description": "Hesitant and slightly defensive tone." } }, { "event_id": "EVENT_2", "type": "dialogue", "time_range": [ 4.0, 6.3 ], "content": { "speaker": "PERSON_1", "line": "这几间办公室都是临时收拾出来的", "description": "Explaining the situation in a matter-of-fact tone." } }, { "event_id": "EVENT_3", "type": "dialogue", "time_range": [ 6.3, 7.5 ], "content": { "speaker": "PERSON_1", "line": "后续会运一些设备过来", "description": "Providing further details to clarify the circumstances." } } ], "scene_description": "A woman in a lab coat explains the makeshift nature of her workspace to a serious-looking man, suggesting an ongoing investigation or inquiry.", "global_style": "Dramatic lighting with close-up shots that create a tense and intimate atmosphere.", "global_audio": "Quiet room ambience with clear, upfront dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_77652", "media_path": "drama_04/clip_77652.mp4", "source_media_path": "clips/clip_77652.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark hair and fair skin", "attributes": "black suit jacket, black patterned tie, small black earring" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin and dark hair", "attributes": "dangling earrings with a pearl-like bead" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A clear wine glass filled with red liquid" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Warm, dim lighting with blurred background elements" } ], "visual_description": "[PERSON_1] looks intently forward. In the blurred foreground, [PERSON_2] holds [OBJECT_1].", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.8, 6.2 ], "references": [ "PERSON_2", "OBJECT_1", "SCENE_1" ], "visual_description": "A close-up profile shot of [PERSON_2] taking a sip from [OBJECT_1]. A drop of wine falls.", "camera": { "shot_type": "close-up", "angle": "side", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.2, 10.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] is seen again, looking slightly to the side and then back towards the front with a subtle expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Rhythmic, slightly tense background music." } } ], "scene_description": "A man intently watches a woman as she drinks a glass of red wine in a dimly lit setting.", "global_style": "Cinematic, moody lighting with shallow depth of field.", "global_audio": "Rhythmic background music." } }, { "dataset": "drama_04", "clip_id": "clip_5217", "media_path": "drama_04/clip_5217.mp4", "source_media_path": "clips/clip_5217.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with short black hair", "attributes": "Wearing a grey cardigan over a white t-shirt and white pants" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A black tablet device" } ], "visual_description": "[PERSON_1] is sitting, looking down at [OBJECT_1] in his lap.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.8, 4.0 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with long black hair", "attributes": "Wearing a fluffy light blue and white jacket" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A living room with a dark grey sofa, a shelf with decorations, and dark walls" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A purple smartphone" } ], "visual_description": "A wider view of [SCENE_1] showing [PERSON_1] and [PERSON_2] sitting on the sofa. [PERSON_2] is looking at [OBJECT_2].", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.0, 6.3 ], "references": [ "PERSON_2", "OBJECT_2", { "ref_id": "OBJECT_3", "type": "object", "id_features": "A small, light-colored hair tie with a decorative element" }, "PERSON_1" ], "visual_description": "[PERSON_2] looks up from [OBJECT_2], holds out [OBJECT_3], and hands it towards [PERSON_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 6.3, 8.8 ], "references": [ "PERSON_1", "OBJECT_3", "PERSON_2" ], "visual_description": "[PERSON_1] looks at [OBJECT_3], takes it from [PERSON_2], and begins to put it on his wrist.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 8.8, 10.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1", "OBJECT_3", { "ref_id": "OBJECT_4", "type": "object", "id_features": "A colorful bag of snacks" } ], "visual_description": "Back to the wider view in [SCENE_1]. [PERSON_1] finishes putting [OBJECT_3] on his wrist. [PERSON_2] is holding [OBJECT_4] and eating from it.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 5.1, 6.3 ], "content": { "speaker": "PERSON_2", "line": "给这个", "description": "Offering an item casually." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 9.6 ], "content": { "description": "Light, upbeat background music." } } ], "scene_description": "A man and a woman are relaxing on a sofa. The woman hands the man a hair tie, which he accepts and puts on his wrist.", "global_style": "Bright, modern, and casual domestic setting.", "global_audio": "Light background music with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_37589", "media_path": "drama_04/clip_37589.mp4", "source_media_path": "clips/clip_37589.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with fair skin and a sorrowful expression", "attributes": "Wearing a light blue robe with a dark belt featuring gold accents. His black hair is tied up with a decorative jeweled crown and a light purple ribbon" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A man standing still in the background", "attributes": "Wearing traditional armor with a red tunic underneath and a dark helmet" } ], "visual_description": "Close-up of [PERSON_1] looking down with a disappointed and sad expression. He then looks up slightly as he speaks. [PERSON_3] is visible in the blurred background.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 5.1, 7.2 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with a serious and calm demeanor", "attributes": "Wearing a dark blue or black outfit with intricate embroidery and a red inner collar. His black hair is tied up with a dark crown" } ], "visual_description": "Close-up of [PERSON_2] shown in profile. He is looking off-camera to the left, listening intently with a serious expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 7.2, 10.0 ], "references": [ "PERSON_1", "PERSON_2", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A traditional Chinese architectural setting with wooden slatted doors, stone steps, and muted lighting" } ], "visual_description": "Medium shot showing [PERSON_1] and [PERSON_2] standing facing each other in [SCENE_1]. [PERSON_1] continues speaking, gesturing slightly. [PERSON_2] responds briefly and turns his head away.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 1.9, 4.1 ], "content": { "speaker": "PERSON_1", "line": "儿", "description": "Sad and hesitant tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.3, 5.9 ], "content": { "speaker": "PERSON_1", "line": "不在那里", "description": "Disappointed tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 5.9, 8.5 ], "content": { "speaker": "PERSON_1", "line": "明天我再带人去其他地方找找", "description": "Determined but slightly defeated tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.5, 8.7 ], "content": { "speaker": "PERSON_2", "line": "去吧", "description": "Calm and dismissive tone." } } ], "scene_description": "Two men are having a serious conversation in a courtyard, discussing a failed search for a missing person.", "global_style": "Historical Chinese drama with a muted, slightly cool color palette and traditional costumes.", "global_audio": "Quiet ambient background with clear, prominent dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_67022", "media_path": "drama_04/clip_67022.mp4", "source_media_path": "clips/clip_67022.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.8 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long, dark wavy hair, fair skin, and a visible red scratch on the right side of her neck", "attributes": "Wearing a white top with a wide neckline and a thin necklace" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short, messy brown hair and fair skin", "attributes": "Wearing a brown leather jacket over a blue denim shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "The background consists of textured, uneven walls resembling a cave or a rustic stone structure. Some blurred white objects, possibly clothing on hangers, are visible in the background" } ], "visual_description": "[PERSON_1] looks directly at [PERSON_2] with a serious expression while speaking. The camera focuses on her face, with the back of [PERSON_2]'s head and shoulder visible in the foreground.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.8, 3.1 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], showing his face as he listens to [PERSON_1]. He has a neutral, slightly concerned expression. The side of [PERSON_1]'s face is visible in the foreground.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.1, 4.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera returns to [PERSON_1] as she continues speaking, her expression growing more resolute.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "MUSIC_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 4.7, 6.8 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_2], who continues to listen silently, his gaze fixed on [PERSON_1].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "MUSIC_1" ] }, { "shot_id": "SHOT_5", "time_range": [ 6.8, 9.7 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1] for her final statement, her eyes locked onto [PERSON_2].", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 3.0 ], "content": { "speaker": "PERSON_1", "line": "我给出了我的心", "description": "Emotional and serious tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.0, 4.8 ], "content": { "speaker": "PERSON_1", "line": "但我主动给的", "description": "Assertive tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.8, 7.1 ], "content": { "speaker": "PERSON_1", "line": "也能主动要回去", "description": "Determined tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 7.1, 8.2 ], "content": { "speaker": "PERSON_1", "line": "现在的你对我而言", "description": "Resolute tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 9.0 ], "content": { "description": "Dramatic and tense instrumental background music." } } ], "scene_description": "A tense and emotional confrontation between a man and a woman in a dimly lit, stone-walled room. The woman asserts her emotional independence, stating that while she gave her heart willingly, she can also take it back.", "global_style": "Dramatic, intimate, utilizing close-up over-the-shoulder shots to emphasize the emotional connection and tension between the characters.", "global_audio": "Tense, dramatic instrumental music plays continuously in the background, underscoring the serious nature of the conversation." } }, { "dataset": "drama_04", "clip_id": "clip_48729", "media_path": "drama_04/clip_48729.mp4", "source_media_path": "clips/clip_48729.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.1 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with long dark hair tied back", "attributes": "Wearing a white double-breasted jacket and a light-colored sheer skirt" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short dark hair", "attributes": "Wearing a grey suit, white shirt, and a patterned tie" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "A man with dark hair", "attributes": "Wearing a black long-sleeved shirt" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "A man with dark hair", "attributes": "Wearing a black jacket and dark pants" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A spacious room with a wooden plank ceiling, white sofas, a coffee table with bottles, a green armchair, and a bookshelf in the background" } ], "visual_description": "[PERSON_2], [PERSON_3], and [PERSON_4] are relaxing in [SCENE_1]. A bright flash of light occurs in the background near the door, and [PERSON_1] suddenly appears.", "camera": { "shot_type": "wide shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.1, 5.5 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] walks forward slowly, looking down with a slightly dazed expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 5.5, 8.0 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] is sleeping on the sofa with his arms crossed. He suddenly wakes up, opens his eyes, and looks forward with an annoyed expression.", "camera": { "shot_type": "close-up", "angle": "low angle", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 8.0, 9.7 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] looks up, appears surprised and confused, and speaks.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 2.0 ], "content": { "description": "A magical whoosh and chime sound effect accompanying the flash of light." } }, { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 8.0, 9.0 ], "content": { "speaker": "PERSON_1", "line": "喂", "description": "Surprised and confused tone." } } ], "scene_description": "A woman magically appears in a living room where three men are resting, waking one of them up.", "global_style": "Modern, slightly dramatic lighting with a fantasy element.", "global_audio": "Quiet room ambience interrupted by a magical sound effect and a single spoken word." } }, { "dataset": "drama_04", "clip_id": "clip_12452", "media_path": "drama_04/clip_12452.mp4", "source_media_path": "clips/clip_12452.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Young man with black hair", "attributes": "Black coat, black shirt, patterned tie" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Young man with black hair", "attributes": "Black suit, black shirt, striped tie" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "Young man with short black hair", "attributes": "Black leather jacket" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "Young man with short black hair", "attributes": "Brown jacket" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Features a large wooden table, chairs, arched windows, and a grand staircase in the background" } ], "visual_description": "[PERSON_1], [PERSON_2], [PERSON_3], and [PERSON_4] are sitting around a large wooden table in [SCENE_1], playing cards.", "camera": { "shot_type": "wide", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.3, 4.2 ], "references": [ { "ref_id": "PERSON_5", "type": "person", "id_features": "Young man with black hair and glasses", "attributes": "Grey herringbone coat, black turtleneck, gold-rimmed glasses" }, { "ref_id": "PERSON_6", "type": "person", "id_features": "Young woman with short black hair", "attributes": "White shawl with fur trim, purple top" }, "SCENE_1" ], "visual_description": "[PERSON_5] and [PERSON_6] walk down the staircase in the background of [SCENE_1].", "camera": { "shot_type": "wide", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 4.2, 5.4 ], "references": [ "PERSON_2" ], "visual_description": "Close-up of [PERSON_2] smiling.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 5.4, 7.0 ], "references": [ "PERSON_1" ], "visual_description": "Close-up of [PERSON_1] looking towards the stairs.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_5", "time_range": [ 7.0, 9.0 ], "references": [ "PERSON_5", "PERSON_6" ], "visual_description": "Medium shot of [PERSON_5] and [PERSON_6] walking arm-in-arm towards the camera.", "camera": { "shot_type": "medium", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_6", "time_range": [ 9.0, 10.0 ], "references": [ "PERSON_5" ], "visual_description": "Close-up of [PERSON_5] looking at the men at the table.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.6, 1.3 ], "content": { "speaker": "PERSON_3", "line": "给个屁", "description": "Dismissive tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 1.3, 3.0 ], "content": { "speaker": "PERSON_4", "line": "给钱", "description": "Demanding tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 3.3, 3.5 ], "content": { "speaker": "PERSON_3", "line": "喽", "description": "Resigned tone" } } ], "scene_description": "A group of men are playing cards when a man and a woman make a grand entrance down the stairs, catching their attention.", "global_style": "Cinematic, elegant, slightly moody lighting.", "global_audio": "Ambient room noise with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_85883", "media_path": "drama_04/clip_85883.mp4", "source_media_path": "clips/clip_85883.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Older man with a black beard and white streaks in his hair, showing a weathered and emotional face", "attributes": "Wearing a green robe and a golden headpiece" } ], "visual_description": "Close-up of [PERSON_1]'s face, tears streaming down his cheeks, looking upwards with a deeply emotional expression.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 5.2 ], "references": [ "PERSON_1", { "ref_id": "PERSON_2", "type": "person", "id_features": "Young man with long black hair and a handsome, expressive face", "attributes": "Wearing a white robe with silver embroidery, a green sash, and a green gem headpiece" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dark, enclosed space with rough stone walls and floor, featuring heavy metal chains attached to the wall", "attributes": "Dimly lit, stone textures, metal chains" } ], "visual_description": "Medium wide shot showing [PERSON_1] sitting on the floor of [SCENE_1], chained to the wall. [PERSON_2] kneels before him, holding his hands. [PERSON_1] speaks to [PERSON_2].", "camera": { "shot_type": "medium shot", "angle": "high angle", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.2, 7.2 ], "references": [ "PERSON_2" ], "visual_description": "Close-up of [PERSON_2]'s face, looking deeply saddened and emotional as he listens.", "camera": { "shot_type": "close-up", "angle": "eye-level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 7.2, 10.0 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "Medium shot of [PERSON_2] standing in [SCENE_1], looking resolute and speaking directly to [PERSON_1].", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3", "DIALOGUE_4" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 2.9 ], "content": { "speaker": "PERSON_1", "line": "你真的回来了", "description": "Emotional, crying, relieved." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.9, 7.5 ], "content": { "speaker": "PERSON_1", "line": "为父没有看错你", "description": "Proud, reassuring." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.5, 8.5 ], "content": { "speaker": "PERSON_2", "line": "是我", "description": "Firm, emotional." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.5, 9.3 ], "content": { "speaker": "PERSON_2", "line": "我回来了父亲", "description": "Reassuring, determined." } } ], "scene_description": "A son reunites with his imprisoned father in a dungeon, sharing a deeply emotional and reassuring moment.", "global_style": "3D animated fantasy or wuxia style with dramatic, moody lighting.", "global_audio": "Somber and emotional background music accompanying the dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_6366", "media_path": "drama_04/clip_6366.mp4", "source_media_path": "clips/clip_6366.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with dark hair, featuring a red mark or bruise on his left cheek", "attributes": "Wearing a grey sweater over a light-colored collared shirt, and a wristwatch" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A room with warm, moody lighting, featuring a window with blinds that cast striped shadows on the wall" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A book with a dark cover, containing printed text and handwritten notes on its pages" } ], "visual_description": "[PERSON_1] sits in [SCENE_1], holding and attentively reading [OBJECT_1].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.4, 6.7 ], "references": [ "OBJECT_1" ], "visual_description": "A close-up view of the open pages of [OBJECT_1], revealing printed text alongside handwritten notes.", "camera": { "shot_type": "close-up", "angle": "high angle", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.7, 10.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A close-up profile of [PERSON_1]'s face, highlighting the red mark on his cheek as he continues to look down.", "camera": { "shot_type": "close-up", "angle": "side view", "movement": "static" }, "active_events": [ "MUSIC_1", "DIALOGUE_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 4.0, 7.0 ], "content": { "speaker": "PERSON_1", "line": "我创造的世界，因我而存在。", "description": "Calm, reflective voiceover" } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Soft, melancholic background music" } } ], "scene_description": "A man reads a book containing handwritten notes, while a voiceover reflects on a specific phrase written inside.", "global_style": "Moody, cinematic, dimly lit with warm tones.", "global_audio": "Soft background music accompanied by a reflective voiceover." } }, { "dataset": "drama_04", "clip_id": "clip_10538", "media_path": "drama_04/clip_10538.mp4", "source_media_path": "clips/clip_10538.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 5.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Young woman with long dark hair tied up", "attributes": "Wearing a light blue cardigan over a top" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "Young man with dark hair", "attributes": "Wearing a black jacket and a silver chain necklace" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "Older woman with dark hair tied back", "attributes": "Wearing a maroon button-up jacket and dark pants" } ], "visual_description": "[PERSON_3] is seen in the foreground looking back, while [PERSON_1] and [PERSON_2] peek cautiously through a doorway behind her. [PERSON_1] smiles and [PERSON_2] looks surprised as they look into the room.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 5.4, 6.6 ], "references": [ "PERSON_3", { "ref_id": "SCENE_1", "type": "scene", "id_features": "A dimly lit room with metal shelving units and cardboard boxes" } ], "visual_description": "[PERSON_3] walks into [SCENE_1], looking around the dimly lit space.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "pan" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.6, 9.2 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] walks into [SCENE_1], passing by metal shelves, viewed from behind.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "tracking" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 9.2, 10.0 ], "references": [ "PERSON_3", "SCENE_1" ], "visual_description": "[PERSON_3] bends down to inspect a cardboard box on a lower shelf in [SCENE_1].", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 10.0 ], "content": { "description": "Ambient room noise and footsteps." } } ], "scene_description": "Three people cautiously enter a dark storage room, with an older woman leading the way and inspecting a box on a shelf.", "global_style": "Dark, suspenseful, low lighting with a cool color palette.", "global_audio": "Quiet ambient noise and footsteps." } }, { "dataset": "drama_04", "clip_id": "clip_64191", "media_path": "drama_04/clip_64191.mp4", "source_media_path": "clips/clip_64191.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.7 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with long brown hair, wearing a white long-sleeved shirt with ruffled shoulders and a black apron with a small rainbow logo", "attributes": "long brown hair, white ruffled shirt, black apron, rainbow logo" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A man with short black hair, wearing glasses, a grey suit jacket, and a black shirt", "attributes": "short black hair, glasses, grey suit jacket, black shirt" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A well-lit modern interior with a white dining table, a wooden cabinet, abstract artwork on the wall, and a living room area visible in the background" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "White ceramic plates and bowls" }, { "ref_id": "OBJECT_2", "type": "object", "id_features": "A wooden cabinet with woven rattan doors" } ], "visual_description": "[PERSON_1] is standing at a white dining table in [SCENE_1], arranging [OBJECT_1]. [PERSON_2] walks into the background and bends down to interact with [OBJECT_2]. [PERSON_1] turns her head to look at him.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 3.7, 5.1 ], "references": [ "PERSON_1", "SCENE_1", "PERSON_2" ], "visual_description": "A closer shot of [PERSON_1] looking towards [PERSON_2] and speaking.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.1, 7.8 ], "references": [ "PERSON_2", "SCENE_1", "PERSON_1" ], "visual_description": "[PERSON_2] turns his head to look back at [PERSON_1].", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_4", "time_range": [ 7.8, 10.0 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "The camera cuts back to [PERSON_1] as she continues speaking, gesturing with her thumb.", "camera": { "shot_type": "medium close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 4.1, 6.7 ], "content": { "speaker": "PERSON_1", "line": "那个", "description": "Hesitant tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 6.7, 9.8 ], "content": { "speaker": "PERSON_1", "line": "我出去跟我朋友小喝几杯", "description": "Informing tone" } } ], "scene_description": "A woman is setting the table when a man enters the room. She hesitantly informs him that she is going out for drinks with a friend.", "global_style": "Modern, clean, and well-lit interior setting.", "global_audio": "Quiet room ambience with clear dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_76241", "media_path": "drama_04/clip_76241.mp4", "source_media_path": "clips/clip_76241.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.3 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young boy with messy white hair, wearing dark sunglasses", "attributes": "Black jacket with straps and buckles, black choker, dark sunglasses" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A standard grey and dark blue megaphone" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "Ornate wooden paneled walls or doors" } ], "visual_description": "[PERSON_1] is standing in [SCENE_1], holding [OBJECT_1] to his mouth and shouting.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 3.3, 10.0 ], "references": [ "PERSON_1", "OBJECT_1" ], "visual_description": "A close-up of [PERSON_1]'s face as he continues to shout into [OBJECT_1].", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3" ] }, { "shot_id": "SHOT_3", "time_range": [ 10.0, 11.0 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with short brown hair and brown eyes", "attributes": "Grey and black tactical suit with armor plating" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "Cloudy, grey sky" } ], "visual_description": "[PERSON_2] is shown standing in [SCENE_2] with a shocked and confused expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.7, 3.8 ], "content": { "speaker": "PERSON_1", "line": "秦氏民宿酒店正式开业", "description": "Loud, announcing tone" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.8, 7.0 ], "content": { "speaker": "PERSON_1", "line": "前三天情侣入住打折", "description": "Promotional, enthusiastic tone" } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.0, 9.6 ], "content": { "speaker": "PERSON_1", "line": "单身狗入住还送鬼友陪聊哦", "description": "Playful, slightly mischievous tone" } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 9.0, 11.0 ], "content": { "description": "Dramatic sting indicating surprise" } } ], "scene_description": "A young boy uses a megaphone to announce the opening of a hotel with bizarre promotional offers, causing another young man to react with shock.", "global_style": "Anime style animation with expressive character designs.", "global_audio": "Clear dialogue with a dramatic sound effect at the end." } }, { "dataset": "drama_04", "clip_id": "clip_71965", "media_path": "drama_04/clip_71965.mp4", "source_media_path": "clips/clip_71965.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A woman with long, wavy black hair, wearing a black coat with white stitching and gold buttons, gold earrings, and a delicate necklace", "attributes": "long wavy black hair, black coat with white stitching, gold buttons, gold earrings, necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A modern office setting with blurred background elements including curtains and a potted plant", "attributes": "office interior, curtains, potted plant, blurred background" } ], "visual_description": "[PERSON_1] looks directly ahead with a serious expression and speaks.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.4, 5.7 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with her hair tied back featuring a black bow, wearing a black and white off-the-shoulder top with a black ribbon tie, pearl earrings, and a black leather skirt", "attributes": "hair tied back, black bow in hair, black and white off-the-shoulder top, black ribbon tie, pearl earrings, black leather skirt" }, "SCENE_1" ], "visual_description": "[PERSON_2] looks slightly off-camera, speaking with a defiant and annoyed expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.7, 7.5 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "[PERSON_1] is seen listening, maintaining a stern expression.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_4", "time_range": [ 7.5, 11.7 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] crosses her arms while continuing to speak confidently, asserting her dominance.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 2.6, 3.6 ], "content": { "speaker": "PERSON_1", "line": "捡", "description": "Commanding and stern tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 3.6, 6.1 ], "content": { "speaker": "PERSON_2", "line": "我不但不捡我还要告诉你", "description": "Defiant and confrontational tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 6.1, 11.1 ], "content": { "speaker": "PERSON_2", "line": "你现在已经不是陆氏的副总裁陆氏的副总裁是我", "description": "Arrogant and triumphant tone." } } ], "scene_description": "A tense confrontation in an office setting where one woman refuses a command from another and reveals a shift in corporate power.", "global_style": "Modern corporate drama with sharp lighting and shallow depth of field focusing on the characters' expressions.", "global_audio": "Clear dialogue with no prominent background music, emphasizing the tension between the characters." } }, { "dataset": "drama_04", "clip_id": "clip_74311", "media_path": "drama_04/clip_74311.mp4", "source_media_path": "clips/clip_74311.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 3.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young man with a fair complexion, dark eyes, and dark hair", "attributes": "Dark hair tied in a topknot, wearing a blue wrap-around tunic with a fabric belt" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "An older man with a grey beard and mustache", "attributes": "Hair tied up, wearing a brown robe" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A paved street lined with traditional wooden buildings, illuminated by warm red lanterns at dusk" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A large, bulging sack made of brown burlap material, tied at the top" } ], "visual_description": "[PERSON_1] stands in [SCENE_1] holding [OBJECT_1] tightly against his chest, looking around with a slightly anxious expression. [PERSON_2] stands behind him, observing.", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 3.2, 6.1 ], "references": [ "PERSON_1", "SCENE_1", "OBJECT_1" ], "visual_description": "A first-person perspective looking down at [OBJECT_1] held securely in [PERSON_1]'s hands. Various pedestrians walk towards the camera along the paved street of [SCENE_1].", "camera": { "shot_type": "POV shot", "angle": "High angle", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 6.1, 9.8 ], "references": [ "PERSON_1", { "ref_id": "PERSON_3", "type": "person", "id_features": "An older man with a warm expression", "attributes": "Wearing a grey tunic and a cap" }, "SCENE_1", "OBJECT_1", { "ref_id": "OBJECT_2", "type": "object", "id_features": "A round bamboo steamer filled with white steamed buns, emitting steam" } ], "visual_description": "[PERSON_1] is seen again holding [OBJECT_1], muttering to himself with a serious expression. He then turns his attention to a food stall, points at [OBJECT_2], and speaks directly to [PERSON_3].", "camera": { "shot_type": "Medium shot", "angle": "Eye level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "DIALOGUE_2", "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 3.6, 5.6 ], "content": { "speaker": "PERSON_1", "line": "十母良田十几年开", "description": "Muttering to himself, calculating" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 5.6, 8.7 ], "content": { "speaker": "PERSON_1", "line": "枝十几个黄花闺女十个", "description": "Muttering to himself, calculating" } } ], "scene_description": "A young man in an ancient street holds a sack of money, calculating his wealth and what it could buy, before abruptly deciding to buy ten steamed buns from a vendor.", "global_style": "3D animated, ancient Chinese fantasy style, warm lighting.", "global_audio": "Bustling street ambience, footsteps, distant chatter." } }, { "dataset": "drama_04", "clip_id": "clip_58920", "media_path": "drama_04/clip_58920.mp4", "source_media_path": "clips/clip_58920.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.2 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A tall man with dark hair, wearing a black trench coat over a black turtleneck", "attributes": "black trench coat, black turtleneck, dark hair" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with her hair tied up, wearing a light green sleeveless dress and a colorful jeweled necklace", "attributes": "light green sleeveless dress, colorful jeweled necklace, pearl earrings, hair in an updo" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A well-lit room with large windows showing greenery outside, featuring a crystal chandelier", "attributes": "large windows, chandelier, bright lighting" } ], "visual_description": "[PERSON_1] and [PERSON_2] stand facing each other in [SCENE_1]. [PERSON_1] looks down at [PERSON_2] with a serious expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [] }, { "shot_id": "SHOT_2", "time_range": [ 2.2, 5.8 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "A close-up of [PERSON_2] as she speaks, looking up with a slightly anxious and earnest expression.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 5.8, 10.7 ], "references": [ "PERSON_1", "SCENE_1" ], "visual_description": "A close-up of [PERSON_1]. He looks down, his expression softens into a slight smile, and he speaks gently.", "camera": { "shot_type": "close-up", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 2.8, 10.1 ], "content": { "speaker": "PERSON_2", "line": "我只是觉得我跟他们年纪差不多", "description": "Explaining, slightly defensive and earnest" } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 10.1, 10.3 ], "content": { "speaker": "PERSON_1", "line": "听你的", "description": "Gentle, conceding" } } ], "scene_description": "An intimate and slightly tense conversation between a man and a woman in an elegant setting, ending with the man yielding to her perspective.", "global_style": "Romantic drama, well-lit, elegant aesthetic.", "global_audio": "Quiet room ambience with clear, close-mic dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_62738", "media_path": "drama_04/clip_62738.mp4", "source_media_path": "clips/clip_62738.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 1.5 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, wearing a pink Hanfu with intricate embroidery. She has long black hair styled with braids and adorned with pink floral hairpins and a forehead ornament", "attributes": "clothing: Pink Hanfu with white trim and embroidery, hairstyle: Long black hair with braids and elaborate styling, accessories: Pink floral hairpins, dangling earrings, forehead ornament, pearl necklace" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A blurred outdoor background with hints of greenery and traditional architecture" } ], "visual_description": "[PERSON_1] looks directly at the camera with a slightly frustrated or resigned expression.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 1.5, 5.3 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "A young man with fair skin, wearing a white Hanfu. He has long black hair tied up with a white ribbon", "attributes": "clothing: White Hanfu with subtle patterns, hairstyle: Long black hair, partially tied up, accessories: White hair ribbon, hair stick" } ], "visual_description": "[PERSON_2] looks off to the side, then slowly turns his head slightly, appearing thoughtful.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [] }, { "shot_id": "SHOT_3", "time_range": [ 5.3, 8.1 ], "references": [ "PERSON_1", { "ref_id": "SCENE_2", "type": "scene", "id_features": "An interior space with a patterned blue floor, dark wooden furniture, and an open red door leading outside to a courtyard with a red pillar" } ], "visual_description": "[PERSON_1] walks through an open red door from the outside into [SCENE_2].", "camera": { "shot_type": "Wide shot", "angle": "Low angle", "movement": "Static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 8.1, 10.0 ], "references": [ { "ref_id": "PERSON_3", "type": "person", "id_features": "A young woman with fair skin, wearing a light green and white Hanfu. Her hair is tied up and decorated with small blue floral accessories", "attributes": "clothing: Light green and white Hanfu, hairstyle: Black hair tied up, accessories: Blue floral hair accessories" }, "SCENE_2" ], "visual_description": "[PERSON_3] is wiping a dark wooden table in [SCENE_2], then stops and looks up towards the entrance.", "camera": { "shot_type": "Medium shot", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "SFX_2" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.0, 1.5 ], "content": { "speaker": "PERSON_1", "line": "算了，不想了", "description": "Frustrated sigh, inner monologue" } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 4.5, 7.5 ], "content": { "description": "Footsteps on a hard surface" } }, { "event_id": "SFX_2", "type": "sfx", "time_range": [ 7.5, 9.5 ], "content": { "description": "Sound of cloth wiping wood and subtle movement" } } ], "scene_description": "A young woman decides to stop overthinking and enters a room where another woman is cleaning.", "global_style": "Historical Chinese drama aesthetic, soft lighting, traditional costumes.", "global_audio": "Quiet ambient sound with clear dialogue and distinct foley for footsteps and cleaning." } }, { "dataset": "drama_04", "clip_id": "clip_50523", "media_path": "drama_04/clip_50523.mp4", "source_media_path": "clips/clip_50523.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.4 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A man with short black hair, wearing a black suit jacket over a striped vest, a black shirt, and a black tie. He has dirt smudges on his face", "attributes": "clothing: Black suit jacket, striped vest, black shirt, black tie, hairstyle: Short black hair, accessories: Watch" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A woman with black hair tied back, wearing a brown coat over a white shirt. She has dirt smudges on her face and is crying", "attributes": "clothing: Brown coat, white shirt, hairstyle: Black hair tied back, accessories: Pearl hair clip, earrings" }, { "ref_id": "OBJECT_1", "type": "object", "id_features": "A silver handgun" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An indoor area featuring a prominent wooden staircase in the background" } ], "visual_description": "[PERSON_1] is seen holding [OBJECT_1], looking down with a serious expression. The hands of [PERSON_2] are visible, gripping his hand and the gun.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_1", "MUSIC_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.4, 10.0 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "The camera cuts to [PERSON_2], who is crying and looking intensely at [PERSON_1]. She speaks emotionally while continuing to hold his hand.", "camera": { "shot_type": "Close-up", "angle": "Eye-level", "movement": "Static" }, "active_events": [ "DIALOGUE_2", "DIALOGUE_3", "DIALOGUE_4", "MUSIC_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 2.7 ], "content": { "speaker": "PERSON_1", "line": "最见不得有人蒙冤", "description": "Serious and resolute tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 2.7, 4.8 ], "content": { "speaker": "PERSON_2", "line": "若是谁有冤情", "description": "Emotional, crying tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 4.8, 8.7 ], "content": { "speaker": "PERSON_2", "line": "皆可到少帅府门口求救", "description": "Emotional, crying tone." } }, { "event_id": "DIALOGUE_4", "type": "dialogue", "time_range": [ 8.7, 9.6 ], "content": { "speaker": "PERSON_2", "line": "是吗张太臣", "description": "Questioning, emotional tone." } }, { "event_id": "MUSIC_1", "type": "music", "time_range": [ 0.0, 10.0 ], "content": { "description": "Dramatic and tense background music." } } ], "scene_description": "A tense and emotional confrontation between a man and a woman, where the woman tearfully questions the man's principles while holding his hand, which is gripping a gun.", "global_style": "Dramatic, cinematic lighting with a slightly muted color palette, emphasizing the emotional intensity of the characters.", "global_audio": "Dramatic background music accompanying emotional dialogue." } }, { "dataset": "drama_04", "clip_id": "clip_66699", "media_path": "drama_04/clip_66699.mp4", "source_media_path": "clips/clip_66699.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 4.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "A young woman with fair skin, wearing dark red traditional Chinese clothing with gold embroidery", "attributes": "Dark red Hanfu, elaborate ancient Chinese updo hairstyle with gold hairpins and ornaments" }, { "ref_id": "PERSON_2", "type": "person", "id_features": "A young woman with fair skin, wearing a light pink traditional Chinese dress with white accents", "attributes": "Light pink Hanfu, ancient Chinese updo hairstyle with delicate hairpins" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "An antique room featuring wooden lattice windows, dark wood furniture, and traditional decor", "attributes": "Wooden lattice windows, antique furniture, traditional Chinese architecture" } ], "visual_description": "[PERSON_1] and [PERSON_2] stand side by side in [SCENE_1]. [PERSON_1] is positioned on the left, and [PERSON_2] is on the right. Both women are looking forward with neutral expressions.", "camera": { "shot_type": "medium full shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 4.0, 8.3 ], "references": [ "PERSON_1", "PERSON_2", "SCENE_1" ], "visual_description": "[PERSON_2] turns her head to look at [PERSON_1]. [PERSON_1] maintains her forward-facing posture and smiles gently.", "camera": { "shot_type": "medium full shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_2" ] }, { "shot_id": "SHOT_3", "time_range": [ 8.3, 9.4 ], "references": [ "PERSON_2", "SCENE_1" ], "visual_description": "The scene cuts to [PERSON_2] standing alone in [SCENE_1]. She looks slightly downward with a somber and melancholic expression.", "camera": { "shot_type": "medium shot", "angle": "eye level", "movement": "static" }, "active_events": [ "DIALOGUE_3" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 0.3, 4.1 ], "content": { "speaker": "NARRATOR", "line": "如玉是她的名字安如玉也是户部尚书的嫡女", "description": "Calm and narrative tone, introducing a character." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 4.1, 7.1 ], "content": { "speaker": "NARRATOR", "line": "从前在宫外她明理之事活泼开朗", "description": "Reflective and slightly nostalgic tone." } }, { "event_id": "DIALOGUE_3", "type": "dialogue", "time_range": [ 7.1, 9.0 ], "content": { "speaker": "NARRATOR", "line": "最爱承鄂阳兄不知什么时候", "description": "Continuing the reflection with a hint of impending sorrow." } } ], "scene_description": "A narrator introduces a character named Ru Yu, describing her noble background and her formerly cheerful personality, while showing two women dressed in traditional Chinese attire in an antique setting.", "global_style": "Ancient Chinese historical drama aesthetic, elegant and slightly melancholic.", "global_audio": "Soft, dramatic background music accompanied by a female voiceover narration." } }, { "dataset": "drama_04", "clip_id": "clip_100596", "media_path": "drama_04/clip_100596.mp4", "source_media_path": "clips/clip_100596.mp4", "caption": { "shots": [ { "shot_id": "SHOT_1", "time_range": [ 0.0, 2.0 ], "references": [ { "ref_id": "PERSON_1", "type": "person", "id_features": "Young man with a fair complexion, seen in profile", "attributes": "Long black hair tied in a half ponytail, wearing a tattered, patched brown robe" }, { "ref_id": "SCENE_1", "type": "scene", "id_features": "A snowy outdoor setting with a wooden fence and a tree with orange fruits, likely persimmons, in the background" } ], "visual_description": "[PERSON_1] is seen in profile, eating from a dark bowl with chopsticks in [SCENE_1] as snow falls around him.", "camera": { "shot_type": "medium close-up", "angle": "eye-level", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_2", "time_range": [ 2.0, 3.8 ], "references": [ { "ref_id": "PERSON_2", "type": "person", "id_features": "Young man with a serious expression", "attributes": "Long black hair, wearing a tattered grey robe with a fabric belt" }, { "ref_id": "PERSON_3", "type": "person", "id_features": "Older man with a weathered face and a distressed expression", "attributes": "Messy greyish-black hair tied back, wearing a tattered dark grey robe" }, { "ref_id": "PERSON_4", "type": "person", "id_features": "Older woman with a kind, weathered face", "attributes": "Grey hair tied in a bun with a wooden hairpin, wearing a tattered, patched blue robe" }, { "ref_id": "SCENE_2", "type": "scene", "id_features": "The wooden doorway of a simple, rustic house" } ], "visual_description": "[PERSON_2], [PERSON_3], and [PERSON_4] stand together in [SCENE_2]. [PERSON_4] looks forward with a sympathetic expression and speaks.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_1", "SFX_1" ] }, { "shot_id": "SHOT_3", "time_range": [ 3.8, 5.2 ], "references": [ { "ref_id": "SCENE_3", "type": "scene", "id_features": "A wide view of a snow-covered village nestled in a valley, featuring wooden houses with snow-laden roofs and smoke rising from a chimney" } ], "visual_description": "A wide view of [SCENE_3] showing snow falling heavily over the rustic houses.", "camera": { "shot_type": "wide shot", "angle": "high angle", "movement": "static" }, "active_events": [ "SFX_1" ] }, { "shot_id": "SHOT_4", "time_range": [ 5.2, 10.0 ], "references": [ "PERSON_3", { "ref_id": "SCENE_4", "type": "scene", "id_features": "The dimly lit interior of a wooden house with shelves and hanging dried goods in the background" } ], "visual_description": "[PERSON_3] stands in [SCENE_4], looking highly distressed. He gestures with his hands as he speaks anxiously.", "camera": { "shot_type": "medium shot", "angle": "eye-level", "movement": "static" }, "active_events": [ "DIALOGUE_2", "SFX_1" ] } ], "events": [ { "event_id": "DIALOGUE_1", "type": "dialogue", "time_range": [ 2.0, 6.7 ], "content": { "speaker": "PERSON_4", "line": "这孩子也是个可怜人本性真不坏", "description": "Sympathetic and gentle tone." } }, { "event_id": "DIALOGUE_2", "type": "dialogue", "time_range": [ 6.7, 9.7 ], "content": { "speaker": "PERSON_3", "line": "这血要再不停家里就要断粮了", "description": "Anxious and worried tone." } }, { "event_id": "SFX_1", "type": "sfx", "time_range": [ 0.0, 9.5 ], "content": { "description": "Ambient sound of wind and subtle, somber background music." } } ], "scene_description": "In a snowy, impoverished village, an older woman expresses sympathy for a young man eating outside, while an older man worries about their dwindling food supply due to the relentless snow.", "global_style": "Historical, rustic, and bleak winter aesthetic with muted colors and tattered clothing.", "global_audio": "Somber background music mixed with the ambient sound of a winter storm." } } ] }