| { |
| "benchmark": "TAVR cross-scene benchmark", |
| "description": "158 reference/target video pairs. Each side points to a source video and the clip's time span (seconds) and frame span at the source fps. Clips are drawn from the TalkVid dataset. target_caption is the scene caption used as the text prompt.", |
| "n_samples": 158, |
| "samples": [ |
| { |
| "reference": { |
| "video_id": "o9KZh8Eopw4", |
| "video_url": "https://www.youtube.com/watch?v=o9KZh8Eopw4", |
| "start_time": 261.5694900138422, |
| "end_time": 266.6111566805089, |
| "start_frame": 6271, |
| "end_frame": 6392, |
| "fps": 23.976028712444112, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "hE6k1t9jE6E", |
| "video_url": "https://www.youtube.com/watch?v=hE6k1t9jE6E", |
| "start_time": 289.9312777511388, |
| "end_time": 294.9729444178055, |
| "start_frame": 6951, |
| "end_frame": 7072, |
| "fps": 23.97601823350032, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a blonde woman in a brightly lit, modern kitchen and living area. She wears a red and white tank top, her long, wavy hair cascading over her shoulders. She holds a smartphone in her left hand, initially looking down at the screen with her mouth slightly open as if speaking or reacting. The background features white kitchen cabinets, a coffee machine, and a glimpse of a living room with a window and a dark couch, all bathed in soft, natural daylight. As she speaks, her eyes widen, and she shifts her gaze directly towards the viewer, conveying an engaged and thoughtful expression. Her subtle head movements and direct eye contact create a sense of personal address. The scene maintains a realistic and cinematic aesthetic, capturing a candid, conversational moment." |
| }, |
| { |
| "reference": { |
| "video_id": "nkmHqs1I_z0", |
| "video_url": "https://www.youtube.com/watch?v=nkmHqs1I_z0", |
| "start_time": 336.34, |
| "end_time": 341.38166666666666, |
| "start_frame": 8408, |
| "end_frame": 8535, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "_g5roKHj95o", |
| "video_url": "https://www.youtube.com/watch?v=_g5roKHj95o", |
| "start_time": 242.57999999999998, |
| "end_time": 247.62166666666664, |
| "start_frame": 6064, |
| "end_frame": 6191, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young man with short dark hair and a dark grey t-shirt sits centrally at a desk, facing the camera in a medium close-up shot. He is positioned against a modern, well-lit office or study background, featuring a wooden shelving unit filled with books, binders, and various office supplies, including a white printer on the left and a stack of blue binders on the right. The lighting is bright and even, casting soft illumination on his face and the environment, suggesting a daytime setting. He speaks directly to the viewer, his mouth moving articulately, and he uses subtle hand gestures to emphasize his points. His expression is calm and focused, conveying an informative and engaging tone. The overall aesthetic is realistic and cinematic, with clear details and a professional presentation." |
| }, |
| { |
| "reference": { |
| "video_id": "eIrMbAQSU34", |
| "video_url": "https://www.youtube.com/watch?v=eIrMbAQSU34", |
| "start_time": 974.9837646408025, |
| "end_time": 980.0254313074691, |
| "start_frame": 29220, |
| "end_frame": 29371, |
| "fps": 29.97003107417848, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "_uQrJ0TkZlc", |
| "video_url": "https://www.youtube.com/watch?v=_uQrJ0TkZlc", |
| "start_time": 96.59640100307254, |
| "end_time": 101.63806766973921, |
| "start_frame": 2895, |
| "end_frame": 3046, |
| "fps": 29.970029658493853, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A bald man with a short beard and black-rimmed glasses is centered in a bright, modern indoor setting, captured in a medium close-up shot at eye-level. He wears a plain black t-shirt. The background features a clean white wall, a white sofa, and a glimpse of a kitchen area with warm wooden cabinets and a dark appliance. He looks directly at the camera, speaking with a clear, engaging expression. His mouth moves actively as he articulates words, accompanied by subtle head nods. A consistent, friendly smile plays on his lips, conveying confidence and approachability. The scene is brightly and evenly lit, likely by soft natural light, creating minimal shadows and a clean, professional aesthetic. The overall style is realistic and cinematic, focusing on direct communication." |
| }, |
| { |
| "reference": { |
| "video_id": "PS_oFG9W0fw", |
| "video_url": "https://www.youtube.com/watch?v=PS_oFG9W0fw", |
| "start_time": 0.1, |
| "end_time": 5.141666666666667, |
| "start_frame": 2, |
| "end_frame": 123, |
| "fps": 23.976055954800813, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "IpsxpuXg64E", |
| "video_url": "https://www.youtube.com/watch?v=IpsxpuXg64E", |
| "start_time": 57.131742291524304, |
| "end_time": 62.17340895819097, |
| "start_frame": 1370, |
| "end_frame": 1491, |
| "fps": 23.97606117567153, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with shoulder-length brown hair and blue eyes, wearing a teal long-sleeved top and small blue earrings. She stands centered in a brightly lit indoor space, speaking directly to the camera with a calm and composed demeanor. Her mouth moves articulately as she delivers her message, accompanied by subtle, natural head movements. The background is a vibrant display of lush green foliage, with large, leafy plants creating a natural, serene atmosphere. To her right, a tall vase overflows with a cheerful bouquet of bright yellow sunflowers, adding a pop of color and warmth. A dark lantern sits nearby, complementing the rustic-chic decor. To her left, a wooden shelf holds several rolled items, possibly posters or documents, and a small red YouTube play button icon is visible. The scene is bathed in soft, natural daylight, casting gentle shadows and highlighting the realistic cinematic style. The overall mood is informative and inviting." |
| }, |
| { |
| "reference": { |
| "video_id": "Yi-8BcQyXDg", |
| "video_url": "https://www.youtube.com/watch?v=Yi-8BcQyXDg", |
| "start_time": 716.9828333333334, |
| "end_time": 722.0245, |
| "start_frame": 21488, |
| "end_frame": 21639, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "2fb0mlA1eO8", |
| "video_url": "https://www.youtube.com/watch?v=2fb0mlA1eO8", |
| "start_time": 0.1, |
| "end_time": 5.141666666666667, |
| "start_frame": 3, |
| "end_frame": 154, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with dark hair, styled in a half-updo with loose strands framing her face, sits in a bright, minimalist bedroom. She wears a black long-sleeved top with buttons at the neckline and a delicate gold necklace with small charms. Her expression is friendly and engaging, with a soft smile as she looks directly into the camera and speaks. In the background, a neatly made bed with white bedding and a patterned pillow is visible on the left, alongside a tall mirror. To the right, a white dresser and a closed white door complete the clean, uncluttered environment. The room is bathed in soft, even daylight, creating a calm and inviting atmosphere. She gestures subtly with her right hand, raising her index finger as she talks, conveying a sense of explanation or emphasis. The shot is a medium close-up, capturing her upper body and the immediate surroundings, presented in a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "2XWsTDZl4pM", |
| "video_url": "https://www.youtube.com/watch?v=2XWsTDZl4pM", |
| "start_time": 134.42, |
| "end_time": 139.46166666666664, |
| "start_frame": 3360, |
| "end_frame": 3487, |
| "fps": 25.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "ggVLt8FEGHc", |
| "video_url": "https://www.youtube.com/watch?v=ggVLt8FEGHc", |
| "start_time": 391.0583333333333, |
| "end_time": 396.09999999999997, |
| "start_frame": 11732, |
| "end_frame": 11883, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a young woman with long, dark hair and a light-colored, textured top, speaking directly to the camera. She stands in a brightly lit, modern indoor setting with a vibrant yellow wall behind her. The background is softly blurred, revealing a grey armchair and decorative shelves with small objects on the right, and a light wooden panel on the left. The woman's expression is cheerful and engaging, with a friendly smile as her mouth moves in sync with her speech. She occasionally nods her head and uses subtle hand gestures to emphasize her words, conveying a sense of confidence and approachability. At the bottom of the frame, a \"SUBSCRIBED\" button with a bell icon briefly animates, showing a click and a ring, before disappearing. The lighting is soft and even, creating a warm and inviting atmosphere. The overall aesthetic is a realistic, clean cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "yHKKtxliYaY", |
| "video_url": "https://www.youtube.com/watch?v=yHKKtxliYaY", |
| "start_time": 130.18829166666666, |
| "end_time": 135.22995833333331, |
| "start_frame": 3121, |
| "end_frame": 3242, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "E5CenqVtkZw", |
| "video_url": "https://www.youtube.com/watch?v=E5CenqVtkZw", |
| "start_time": 563.8962, |
| "end_time": 568.9378666666667, |
| "start_frame": 16900, |
| "end_frame": 17051, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames an older, bald man with round glasses, wearing a textured olive-green hooded sweatshirt. He sits centered, looking directly into the camera with a focused and calm expression, his mouth moving as he speaks. His hands are clasped together at chest level, occasionally making small, deliberate gestures to emphasize his words. The background is a warm, inviting study or office, dominated by dark wooden bookshelves packed with numerous books of various sizes and colors. Vintage items like old suitcases and typewriters are visible on the shelves, adding character to the environment. A black microphone on a boom arm is positioned to the right of the frame, slightly out of focus. The lighting is bright and even, illuminating the scene clearly without harsh shadows, suggesting an indoor setting during the day. The overall aesthetic is a realistic, cinematic style, conveying a sense of direct communication and intellectual engagement." |
| }, |
| { |
| "reference": { |
| "video_id": "GZW13_DpMOQ", |
| "video_url": "https://www.youtube.com/watch?v=GZW13_DpMOQ", |
| "start_time": 144.85999999999999, |
| "end_time": 149.90166666666664, |
| "start_frame": 3621, |
| "end_frame": 3748, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "d2vAnl5-5dA", |
| "video_url": "https://www.youtube.com/watch?v=d2vAnl5-5dA", |
| "start_time": 106.86333333333334, |
| "end_time": 111.90500000000002, |
| "start_frame": 2672, |
| "end_frame": 2798, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, straight brown hair and a friendly expression is captured in a medium close-up shot, speaking directly to the camera. She wears a simple black t-shirt and a delicate gold chain necklace. Her mouth moves articulately as she speaks, occasionally accompanied by subtle, expressive hand gestures that rise slightly into the frame before falling. Her eyes are bright and engaging, conveying a calm and approachable demeanor. The background is a clean, minimalist white wall, adorned with three modern black planters holding vibrant green and muted beige plants, arranged in a geometric metal frame. The lighting is soft and even, illuminating her face without harsh shadows, suggesting a bright indoor setting during the day. The overall aesthetic is realistic and cinematic, focusing on clear, natural details and a warm, inviting atmosphere." |
| }, |
| { |
| "reference": { |
| "video_id": "hxq6dypx9h0", |
| "video_url": "https://www.youtube.com/watch?v=hxq6dypx9h0", |
| "start_time": 97.06179166666666, |
| "end_time": 102.10345833333334, |
| "start_frame": 2327, |
| "end_frame": 2448, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Oos9UXRvr28", |
| "video_url": "https://www.youtube.com/watch?v=Oos9UXRvr28", |
| "start_time": 154.10075, |
| "end_time": 159.14241666666666, |
| "start_frame": 3695, |
| "end_frame": 3816, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian woman with long, straight dark hair and a light grey ribbed tank top sits at a desk, facing the camera in a medium shot. She is positioned centrally, with a bright white wall behind her, adorned with a cork board displaying various notes and pictures. To her left, a computer monitor shows text, and a silver laptop is open on a stand. A red mug with a geometric pattern sits on the desk. The woman speaks directly, her mouth moving articulately, and she uses expressive hand gestures to emphasize her points, extending her hands outwards and then drawing them back. A small black lavalier microphone is clipped to her top. Her expression is calm and communicative, conveying a sense of engagement. The scene is brightly and evenly lit, suggesting a clear daytime setting, with soft shadows. The overall aesthetic is clean, modern, and realistic, typical of a professional video presentation." |
| }, |
| { |
| "reference": { |
| "video_id": "6rzWZmvtrA8", |
| "video_url": "https://www.youtube.com/watch?v=6rzWZmvtrA8", |
| "start_time": 545.6833333333334, |
| "end_time": 550.725, |
| "start_frame": 16371, |
| "end_frame": 16522, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "vCUVP0oLMOs", |
| "video_url": "https://www.youtube.com/watch?v=vCUVP0oLMOs", |
| "start_time": 309.0583333333333, |
| "end_time": 314.09999999999997, |
| "start_frame": 7726, |
| "end_frame": 7852, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian man with short dark hair and round, gold-rimmed glasses is centered in a medium close-up shot, speaking directly to the camera. He wears a dark blue t-shirt and holds a black \"Rode\" microphone with a foam cover near his chest. His mouth moves actively as he articulates words, and he occasionally uses subtle hand gestures, briefly raising his left hand with fingers slightly spread before lowering it. He maintains a calm and focused expression, conveying an informative or conversational tone. The scene is set outdoors under a white, open-air pergola with a slatted roof, providing diffused natural light. In the soft-focused background, lush green foliage, trees, and distant urban buildings are visible, suggesting a park or public garden environment. The ground beneath him is paved. The lighting is bright and even, indicating daytime, with soft shadows under the structure. The overall aesthetic is a realistic, cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "y5kl9MU1urc", |
| "video_url": "https://www.youtube.com/watch?v=y5kl9MU1urc", |
| "start_time": 2669.133333333333, |
| "end_time": 2674.1749999999997, |
| "start_frame": 160148, |
| "end_frame": 160450, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "SJOnhWiJArM", |
| "video_url": "https://www.youtube.com/watch?v=SJOnhWiJArM", |
| "start_time": 351.6845666666666, |
| "end_time": 356.7262333333333, |
| "start_frame": 10540, |
| "end_frame": 10691, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A woman with long, dark hair, subtly streaked with gray, occupies the left side of a medium shot, speaking directly to the viewer. She wears a collared shirt featuring a complex, multi-patterned design in black, white, and hints of red and blue florals. Her facial expression is composed and engaging, conveying a sense of calm instruction as her lips articulate words precisely. She occasionally uses subtle hand gestures, raising her right hand slightly to emphasize a point. The background is a uniformly light gray wall, suggesting a clean, minimalist studio environment. Bright, soft front lighting illuminates her face evenly, creating minimal, gentle shadows. White text overlays the right side of the frame, stating \"Step 3: Have small conversations with yourself in English.\" In the top left corner, \"RachelsEnglish.com\" is displayed. The video maintains a realistic, professional aesthetic, typical of an educational tutorial." |
| }, |
| { |
| "reference": { |
| "video_id": "FePHGABQ6kw", |
| "video_url": "https://www.youtube.com/watch?v=FePHGABQ6kw", |
| "start_time": 585.7916666666666, |
| "end_time": 590.8333333333333, |
| "start_frame": 35148, |
| "end_frame": 35450, |
| "fps": 60.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "zFzeWKvA6Ak", |
| "video_url": "https://www.youtube.com/watch?v=zFzeWKvA6Ak", |
| "start_time": 735.0, |
| "end_time": 740.0416666666666, |
| "start_frame": 22050, |
| "end_frame": 22201, |
| "fps": 30.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A young woman with long blonde hair and a blue, textured top stands on a sunlit urban sidewalk, facing the camera directly. She holds a small, black, furry microphone in her right hand, positioned near her chest. Her expression is cheerful and engaging, with a wide smile as she speaks, her mouth moving clearly. Behind her, a tall black metal fence runs horizontally, separating the sidewalk from a large building. In the mid-ground, a historic-looking building with a prominent clock tower and a flag (green, white, and orange) flying from its roof is visible. Lush green trees line the street further back, and a few cars are parked or moving in the distance. The scene is bathed in bright, natural daylight, casting clear shadows and highlighting the woman's features. The overall aesthetic is a realistic, cinematic portrayal of a bright day in a city." |
| }, |
| { |
| "reference": { |
| "video_id": "l69yZ5xabbo", |
| "video_url": "https://www.youtube.com/watch?v=l69yZ5xabbo", |
| "start_time": 649.8799999999999, |
| "end_time": 654.9216666666665, |
| "start_frame": 16247, |
| "end_frame": 16373, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "394CSs2rVeI", |
| "video_url": "https://www.youtube.com/watch?v=394CSs2rVeI", |
| "start_time": 270.42499999999995, |
| "end_time": 275.46666666666664, |
| "start_frame": 6761, |
| "end_frame": 6887, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with voluminous dark curly hair, wearing a grey striped t-shirt, dark jeans, and a gold belt, standing in a brightly lit, minimalist room. She faces the camera directly, smiling warmly and speaking with engaging hand gestures. Her right hand forms an \"OK\" sign, while her left hand makes a flat, open gesture, moving subtly as she articulates words. The background features a large window with sheer white curtains on the left, and white walls adorned with wooden shelves holding a small plant, a golden owl figurine, and a YouTube play button plaque on the right. A light wooden desk is visible on the left, and a similar console table with a pink box sits on the right. Text overlays \"selfish shellfish\" appear on the left, with specific letters highlighting in yellow as she speaks. The scene is illuminated by soft, natural daylight, creating a clear, inviting atmosphere with a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "KEO4LZPAp54", |
| "video_url": "https://www.youtube.com/watch?v=KEO4LZPAp54", |
| "start_time": 66.19936666666668, |
| "end_time": 71.24103333333335, |
| "start_frame": 3968, |
| "end_frame": 4270, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "97K8x3qJJY4", |
| "video_url": "https://www.youtube.com/watch?v=97K8x3qJJY4", |
| "start_time": 857.7234333333333, |
| "end_time": 862.7651, |
| "start_frame": 25706, |
| "end_frame": 25857, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, wavy brown hair and striking blue eyes, speaking directly to the camera. She wears a textured olive-green blazer over a dark top, accessorized with layered gold and silver chain necklaces. Her expression is bright and enthusiastic, with a wide smile revealing her teeth as she articulates words. Her hands rise into the frame, fingers spread wide, emphasizing her speech with an open, welcoming gesture. The background features light-colored shelves adorned with various decorative items, including bottles, framed pictures, and colorful cosmetic products, suggesting a modern, organized indoor setting. The lighting is bright and even, casting minimal shadows and highlighting her features, contributing to a clean, professional, and realistic cinematic aesthetic. Her body language conveys genuine happiness and engagement." |
| }, |
| { |
| "reference": { |
| "video_id": "UZGaMs26u2A", |
| "video_url": "https://www.youtube.com/watch?v=UZGaMs26u2A", |
| "start_time": 1489.0844, |
| "end_time": 1494.1260666666667, |
| "start_frame": 44628, |
| "end_frame": 44779, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "-utdCRH8ozY", |
| "video_url": "https://www.youtube.com/watch?v=-utdCRH8ozY", |
| "start_time": 667.9974666666667, |
| "end_time": 673.0391333333333, |
| "start_frame": 20020, |
| "end_frame": 20171, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with dark, wavy hair and a brown turtleneck sits in a cozy bedroom, captured in a medium close-up shot. Her expression is calm and conversational as she speaks directly to the camera, holding a small, black square device near her chest with both hands. The background reveals a light blue wall, a large wooden headboard with intricate carvings, and patterned white and green bedding. To her right, a dresser with a large oval mirror reflects a soft, diffused light, suggesting daytime. The overall lighting is even and gentle, creating a warm and inviting atmosphere. Her subtle head movements and hand gestures emphasize her words, conveying an engaged and informative tone. The aesthetic is realistic and cinematic, focusing on the subject within her personal space." |
| }, |
| { |
| "reference": { |
| "video_id": "LI8yDfWhk0k", |
| "video_url": "https://www.youtube.com/watch?v=LI8yDfWhk0k", |
| "start_time": 547.6439, |
| "end_time": 552.6855666666667, |
| "start_frame": 16413, |
| "end_frame": 16564, |
| "fps": 29.97002997002997, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "cJZ_xhf2sLQ", |
| "video_url": "https://www.youtube.com/watch?v=cJZ_xhf2sLQ", |
| "start_time": 946.0583333333334, |
| "end_time": 951.1, |
| "start_frame": 56764, |
| "end_frame": 57066, |
| "fps": 60.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A young woman with long, wavy brown hair and blue eyes sits in a cream-colored office chair, facing the camera directly. She wears a simple black sweater, her expression calm and engaging as she speaks, her mouth moving articulately. Throughout the segment, she gestures expressively with both hands, palms often facing each other, then opening outwards to emphasize her words. Her fingernails are painted a dark color. The setting is an indoor space with a large window behind her, offering a wide, high-angle view of an urban landscape under a bright, clear blue sky with scattered clouds. Various city buildings, including brick structures and distant skyscrapers, are visible. Inside, to her left, a tall green plant adds a touch of nature, and to her right, a silver YouTube play button award and small potted plants are arranged on a shelf. The scene is brightly lit by natural daylight streaming through the window, creating a clear, realistic cinematic aesthetic. Her body language conveys a sense of confident communication." |
| }, |
| { |
| "reference": { |
| "video_id": "YO_iX9UTiAc", |
| "video_url": "https://www.youtube.com/watch?v=YO_iX9UTiAc", |
| "start_time": 350.4333333333333, |
| "end_time": 355.47499999999997, |
| "start_frame": 8410, |
| "end_frame": 8531, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "BCH104c5GN0", |
| "video_url": "https://www.youtube.com/watch?v=BCH104c5GN0", |
| "start_time": 207.95833333333334, |
| "end_time": 213.0, |
| "start_frame": 6239, |
| "end_frame": 6390, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures a man with dark skin and short, dark hair, wearing distinctive black and white framed glasses. He is positioned centrally, speaking directly into a black microphone held just below his chin. He wears a black long-sleeved shirt adorned with small white dots. His mouth moves as he articulates words, and he occasionally makes subtle gestures with his right hand, emphasizing his speech. The background features a clean white wall, with a vibrant green leafy plant on the left, adding a touch of nature. To the right, a tall wooden bookshelf filled with various books creates a studious atmosphere. A small white shelf with decorative items is visible on the far left. Bright, even lighting illuminates the scene, creating a clear and professional aesthetic. The man's expression is focused and engaged, conveying a serious tone. The overall style is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "foa9ZhtyrfM", |
| "video_url": "https://www.youtube.com/watch?v=foa9ZhtyrfM", |
| "start_time": 124.93304166666667, |
| "end_time": 129.97470833333333, |
| "start_frame": 2995, |
| "end_frame": 3116, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "3kAiPSEnrHI", |
| "video_url": "https://www.youtube.com/watch?v=3kAiPSEnrHI", |
| "start_time": 559.6172916666667, |
| "end_time": 564.6589583333333, |
| "start_frame": 13417, |
| "end_frame": 13538, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A fair-skinned man with short, neatly styled brown hair and striking blue eyes is featured in a medium close-up shot. He wears a simple white t-shirt adorned with small, colorful paint splatters in pink, blue, and yellow, along with a thin silver chain around his neck. The background is softly blurred, revealing a light-colored wall and the muted green leaves of a houseplant, suggesting a clean, modern indoor environment. The man speaks directly, his mouth articulating words clearly, and his eyes blink naturally, conveying a calm and engaged demeanor. His head makes subtle, natural movements as he talks. The scene is bathed in bright, soft, and even lighting, creating a clear, realistic cinematic aesthetic without harsh shadows, indicative of daytime." |
| }, |
| { |
| "reference": { |
| "video_id": "dt_rX9I_bF0", |
| "video_url": "https://www.youtube.com/watch?v=dt_rX9I_bF0", |
| "start_time": 1112.4333333333334, |
| "end_time": 1117.4750000000001, |
| "start_frame": 33373, |
| "end_frame": 33524, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "zxgxRL4-Bok", |
| "video_url": "https://www.youtube.com/watch?v=zxgxRL4-Bok", |
| "start_time": 397.62499999999994, |
| "end_time": 402.66666666666663, |
| "start_frame": 11929, |
| "end_frame": 12080, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian woman with dark hair styled in two braids sits in a modern apartment, speaking directly to the camera in a medium close-up shot. She wears a maroon t-shirt with a white logo and a delicate silver infinity necklace. Her expression is calm and articulate as she speaks, occasionally making small, deliberate gestures with her right hand to emphasize her points. The background reveals a bright, contemporary living space with white walls. To her left, a large flat-screen television displays a serene landscape image of rocky islands in blue water, framed by a decorative window-like border. To her right, a clean, white kitchen area is visible, featuring a counter with two white bar stools and stainless steel appliances. The lighting is bright and even, creating a clear, realistic cinematic look, suggesting a daytime setting." |
| }, |
| { |
| "reference": { |
| "video_id": "kIyDXBqdpzw", |
| "video_url": "https://www.youtube.com/watch?v=kIyDXBqdpzw", |
| "start_time": 1099.4381666666668, |
| "end_time": 1104.4798333333335, |
| "start_frame": 32950, |
| "end_frame": 33101, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "o2OUhbIPS1c", |
| "video_url": "https://www.youtube.com/watch?v=o2OUhbIPS1c", |
| "start_time": 87.55403333333334, |
| "end_time": 92.59570000000001, |
| "start_frame": 2624, |
| "end_frame": 2775, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with short dark hair, wearing a light pink sleeveless dress, seated in a bright, indoor setting. She faces the camera directly, speaking with an animated and engaging expression, her eyes wide and mouth open. Her hands are actively gesturing; initially, they are open with palms facing each other, then she brings them together in a clasped motion, before opening them again to emphasize her words. Behind her, a clean white wall serves as a backdrop, with a light wooden shelf visible on the left, holding potted plants and several books. A light-colored armchair is partially visible on the right. A white rectangular overlay with the green text \"Review your exam strategies\" occupies the upper left corner of the frame. The scene is evenly lit, creating a clear and professional atmosphere, typical of a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "-59cJcC2HJY", |
| "video_url": "https://www.youtube.com/watch?v=-59cJcC2HJY", |
| "start_time": 229.41241666666664, |
| "end_time": 234.4540833333333, |
| "start_frame": 5500, |
| "end_frame": 5621, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "mmyPObbuRAs", |
| "video_url": "https://www.youtube.com/watch?v=mmyPObbuRAs", |
| "start_time": 41.474666666666664, |
| "end_time": 46.51633333333333, |
| "start_frame": 994, |
| "end_frame": 1115, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a blonde woman, identified as Dr. Kim Foster, from the chest up, seated on a light-colored couch in a well-appointed indoor setting. She wears a dark, collared shirt and a delicate gold chain necklace, with small gold hoop earrings. Her expression is calm and friendly, maintaining direct eye contact with the viewer, occasionally blinking. Her mouth moves subtly as she speaks. The background features a blurred but discernible bookshelf filled with books on the left, a tall floor lamp with a warm glow on the right, and a potted plant. Soft, even lighting illuminates the scene, creating a bright yet gentle atmosphere without harsh shadows. A text overlay appears at the bottom, identifying her as \"Dr. Kim Foster MD & COACH,\" then fades away. The overall aesthetic is a realistic, cinematic style, conveying a professional and approachable mood." |
| }, |
| { |
| "reference": { |
| "video_id": "ZZOz0qS5EBk", |
| "video_url": "https://www.youtube.com/watch?v=ZZOz0qS5EBk", |
| "start_time": 506.6742916666666, |
| "end_time": 511.7159583333333, |
| "start_frame": 12148, |
| "end_frame": 12269, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "rSzAxfVDW-U", |
| "video_url": "https://www.youtube.com/watch?v=rSzAxfVDW-U", |
| "start_time": 409.6203749999999, |
| "end_time": 414.6620416666666, |
| "start_frame": 9821, |
| "end_frame": 9942, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with shoulder-length brown hair, dressed in a dark olive green t-shirt, seated at a dark dining table. She looks directly into the camera, speaking with an earnest expression, her eyes wide and mouth slightly open. Initially, her hands are clasped together on the table, then she opens them, gesturing expressively to emphasize her words. In the foreground, to her right, a small white candle holder with a lit candle flickers gently, alongside a dark jar and two tall golden candles in a holder. The background reveals a modern kitchen with white cabinets, stainless steel appliances, and a white chair, all brightly lit. The scene has a realistic cinematic aesthetic, with clear, even lighting suggesting daytime or well-lit indoor conditions, creating a calm and focused atmosphere." |
| }, |
| { |
| "reference": { |
| "video_id": "UQt-8tCvMPQ", |
| "video_url": "https://www.youtube.com/watch?v=UQt-8tCvMPQ", |
| "start_time": 0.1, |
| "end_time": 5.141666666666667, |
| "start_frame": 2, |
| "end_frame": 123, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Yn0jlfgfQvk", |
| "video_url": "https://www.youtube.com/watch?v=Yn0jlfgfQvk", |
| "start_time": 110.14016666666666, |
| "end_time": 115.18183333333333, |
| "start_frame": 2641, |
| "end_frame": 2762, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young man with dark, neatly styled hair and a confident expression is centered in a medium shot, speaking directly to the camera. He wears a navy blue suit jacket over a dark blue sweater and a light blue checkered shirt, with a patterned pocket square adding a touch of color. His hands are actively used for emphasis; he initially places a hand on his chest, then raises three fingers to illustrate a point, before gesturing with an open palm. The background reveals an elegant, brightly lit room with a decorative white fireplace mantelpiece, a gold-toned bar cart with a globe, and a framed picture, all contributing to a sophisticated, clean aesthetic. Soft, even lighting illuminates the scene, creating a professional and engaging atmosphere. The overall style is realistic and cinematic, capturing a clear, direct presentation." |
| }, |
| { |
| "reference": { |
| "video_id": "XP1zadauE7E", |
| "video_url": "https://www.youtube.com/watch?v=XP1zadauE7E", |
| "start_time": 5.141666666666667, |
| "end_time": 10.183333333333334, |
| "start_frame": 154, |
| "end_frame": 305, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "-VUlkQSPRZM", |
| "video_url": "https://www.youtube.com/watch?v=-VUlkQSPRZM", |
| "start_time": 333.19576666666666, |
| "end_time": 338.23743333333334, |
| "start_frame": 9986, |
| "end_frame": 10137, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark hair and a white hoodie occupies the right side of a medium close-up shot, speaking directly to the camera. Her mouth moves articulately, and she gestures subtly with her hands, conveying a calm and engaged demeanor. On the left, a book cover for \"Krakatoa\" by Simon Winchester is digitally superimposed, featuring a red top half and a beige bottom half with an illustration of a volcano. The background reveals a warm, inviting indoor setting with a brick fireplace, a wooden mantelpiece adorned with a framed picture and a blue and white decorative vase. Soft, warm light illuminates the scene from the front, casting gentle shadows and creating a cozy atmosphere. The overall aesthetic is a realistic, cinematic portrayal of a casual, informative presentation." |
| }, |
| { |
| "reference": { |
| "video_id": "QmwIHgXbY7g", |
| "video_url": "https://www.youtube.com/watch?v=QmwIHgXbY7g", |
| "start_time": 1874.7, |
| "end_time": 1879.7416666666668, |
| "start_frame": 56241, |
| "end_frame": 56392, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "CAzJF3PTYnM", |
| "video_url": "https://www.youtube.com/watch?v=CAzJF3PTYnM", |
| "start_time": 532.7583333333333, |
| "end_time": 537.8, |
| "start_frame": 15983, |
| "end_frame": 16134, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a man with dark, curly hair and a full beard, wearing a black Batman graphic t-shirt, seated indoors. He is positioned slightly right of center, looking down intently at something off-screen, his expression serious and focused. To the left, a bright white mobile app interface is visible, displaying the word \"garden\" for pronunciation practice. In the background, bookshelves filled with books and a guitar lean against a wall, suggesting a personal study or office. As the man speaks into a black microphone positioned in front of him, his mouth moves subtly. Suddenly, the app interface changes, displaying \"Excellent!\" and a sound wave, accompanied by a cheerful chime. The man's face immediately brightens, and he looks up with a broad, satisfied smile, his eyes crinkling with joy. The scene is brightly lit with even, soft light, creating a clear and realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "VAvKmcrn7AM", |
| "video_url": "https://www.youtube.com/watch?v=VAvKmcrn7AM", |
| "start_time": 509.0983333333333, |
| "end_time": 514.14, |
| "start_frame": 12727, |
| "end_frame": 12854, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "WRiwhl1NDTc", |
| "video_url": "https://www.youtube.com/watch?v=WRiwhl1NDTc", |
| "start_time": 478.6583333333333, |
| "end_time": 483.7, |
| "start_frame": 11966, |
| "end_frame": 12092, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a young woman with long, wavy brown hair and striking blue eyes, seated on a plush brown sofa. She wears a vibrant green, intricately crocheted top with a V-neck and a delicate necklace. Her expression is engaging and articulate as she speaks directly to the camera, her mouth forming various shapes to emphasize her words. Her hands move subtly to gesture, adding to her expressive communication. The background is a brightly lit, modern indoor space, featuring white walls, a glimpse of red curtains on the left, and blurred shelves or furniture in the distance. A green leafy plant is visible in the foreground on the left, adding a touch of nature. The lighting is soft and even, creating a clear, realistic cinematic aesthetic without harsh shadows, suggesting a well-lit daytime setting. She conveys a calm and confident demeanor, actively communicating with the viewer." |
| }, |
| { |
| "reference": { |
| "video_id": "FOQ140HPMPs", |
| "video_url": "https://www.youtube.com/watch?v=FOQ140HPMPs", |
| "start_time": 450.3333333333333, |
| "end_time": 455.375, |
| "start_frame": 13510, |
| "end_frame": 13661, |
| "fps": 30.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "De9wq1vFUVo", |
| "video_url": "https://www.youtube.com/watch?v=De9wq1vFUVo", |
| "start_time": 160.4, |
| "end_time": 165.44166666666666, |
| "start_frame": 4812, |
| "end_frame": 4963, |
| "fps": 30.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A medium shot captures a woman with long, wavy brown hair, wearing a simple white t-shirt and a black cord necklace with a gold ring pendant. She stands in a brightly lit indoor space, likely a room with light-colored walls. Behind her, a metal clothing rack holds several dark garments on black hangers, and to the right, a large mirror with an ornate gold frame is partially visible, reflecting a soft, diffused light. The woman is positioned centrally, looking directly at the camera. Her mouth moves as she speaks, and she uses subtle hand gestures to emphasize her points, raising and lowering her hands gently. Her expression is calm and conversational, conveying an engaged and informative tone. The lighting is soft and even, suggesting natural daylight, creating a clear and realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "ZIoMgeSjWxM", |
| "video_url": "https://www.youtube.com/watch?v=ZIoMgeSjWxM", |
| "start_time": 765.239375, |
| "end_time": 770.2810416666666, |
| "start_frame": 18347, |
| "end_frame": 18468, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "8JGoOBZz38U", |
| "video_url": "https://www.youtube.com/watch?v=8JGoOBZz38U", |
| "start_time": 466.06549999999993, |
| "end_time": 471.1071666666666, |
| "start_frame": 11174, |
| "end_frame": 11295, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A young adult man, centered in a medium close-up shot, speaks directly to the camera from a well-lit, modern indoor setting. He wears a black t-shirt and a black baseball cap backward, revealing neck tattoos and ear gauges. His expression is calm and engaging, with a slight smile as he articulates his words, occasionally using subtle hand gestures for emphasis. The background features a minimalist white wall. To his left, a brown armchair and a black floor lamp emit a warm glow. To his right, a wooden shelf holds a black electronic keyboard and two small black cameras, with a vibrant green potted plant behind him. Soft, diffused lighting creates a clean, realistic cinematic aesthetic, suggesting a bright daytime environment." |
| }, |
| { |
| "reference": { |
| "video_id": "jpQRP_5pM8I", |
| "video_url": "https://www.youtube.com/watch?v=jpQRP_5pM8I", |
| "start_time": 35.39166666666667, |
| "end_time": 40.43333333333334, |
| "start_frame": 1062, |
| "end_frame": 1213, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "QaquOBT5JVs", |
| "video_url": "https://www.youtube.com/watch?v=QaquOBT5JVs", |
| "start_time": 24.96666666666667, |
| "end_time": 30.008333333333336, |
| "start_frame": 749, |
| "end_frame": 900, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with brown hair tied in a high bun and wearing a light gray crewneck sweatshirt is centered in a medium close-up shot. Her expressive blue eyes, framed by noticeable makeup, look directly at the viewer, then briefly shift to the side before returning. She speaks animatedly, her mouth forming words, and occasionally makes a small, open-handed gesture with her right hand, conveying an engaging and friendly demeanor. A warm smile plays on her lips. The background reveals a cozy indoor setting, likely a living room, with a light gray sofa adorned with patterned pillows. To her left, a side table holds a modern lamp with a caged base and a small candle. The white wall behind her is decorated with various framed artworks, including a world map and botanical prints, adding a personal touch. The scene is brightly and evenly lit, suggesting daytime, with a realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "ZxPshcGRu28", |
| "video_url": "https://www.youtube.com/watch?v=ZxPshcGRu28", |
| "start_time": 273.35283333333336, |
| "end_time": 278.39450000000005, |
| "start_frame": 8192, |
| "end_frame": 8343, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "GipejeRYkcg", |
| "video_url": "https://www.youtube.com/watch?v=GipejeRYkcg", |
| "start_time": 496.0621333333333, |
| "end_time": 501.1038, |
| "start_frame": 14867, |
| "end_frame": 15018, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a young woman with long, straight brown hair, wearing a white blouse adorned with colorful patterns, speaking directly to the viewer. She stands in a brightly lit room with a light blue wall as the backdrop. Her expression is calm and engaging, with a slight smile and direct eye contact, conveying a friendly demeanor. A black microphone is positioned centrally in front of her, indicating she is recording or presenting. As she speaks, her mouth moves clearly, and she uses expressive hand gestures, raising and lowering her left hand to emphasize points. Behind her, a white shelf unit holds various colorful books and small potted plants, while a golden YouTube Play Button plaque rests on a white desk to her left. The lighting is soft and even, creating a clean, professional aesthetic. The overall style is realistic and cinematic, focusing on clear communication." |
| }, |
| { |
| "reference": { |
| "video_id": "olJ7eI_Co7w", |
| "video_url": "https://www.youtube.com/watch?v=olJ7eI_Co7w", |
| "start_time": 820.2526666666666, |
| "end_time": 825.2943333333333, |
| "start_frame": 19666, |
| "end_frame": 19787, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "4b6hetdvQbI", |
| "video_url": "https://www.youtube.com/watch?v=4b6hetdvQbI", |
| "start_time": 837.4782083333333, |
| "end_time": 842.519875, |
| "start_frame": 20079, |
| "end_frame": 20200, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A medium close-up shot frames a man with light brown hair and a neatly trimmed beard, wearing a plain black t-shirt. He is positioned centrally, looking directly into the camera with a calm, engaged expression, his mouth moving as he speaks. His hands make subtle, expressive gestures to emphasize his words. The background is a brightly lit, minimalist indoor setting with white walls. To the left, a segment of a wooden table is visible, along with a tall, vertical light source emitting a soft glow. Behind him, a large, circular golden object stands on a tripod, possibly another light or a decorative element. On the right, a dark metal shelving unit holds various items, and a vibrant green potted plant adds a touch of nature. The lighting is soft and even, creating a clear, professional aesthetic without harsh shadows. The overall mood is one of direct communication and clarity, presented in a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "IGSewS_iElI", |
| "video_url": "https://www.youtube.com/watch?v=IGSewS_iElI", |
| "start_time": 449.59999999999997, |
| "end_time": 454.64166666666665, |
| "start_frame": 10790, |
| "end_frame": 10911, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "dJA7k58zlA8", |
| "video_url": "https://www.youtube.com/watch?v=dJA7k58zlA8", |
| "start_time": 435.6083333333333, |
| "end_time": 440.65, |
| "start_frame": 10455, |
| "end_frame": 10576, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures a young Asian woman with long, dark, wavy hair, wearing a black long-sleeved top, speaking directly to the camera. She stands in a modern, well-lit indoor setting. The background features a light beige wall, a dark grey sofa with a striped cushion, and a tall, dark metal floor lamp with three warm, glowing rectangular shades. To her left, a small wooden table holds two potted green snake plants, adding a touch of nature to the minimalist decor. The woman's expression is calm and engaged as she articulates words, her mouth moving clearly. She uses subtle hand gestures, raising and lowering her open palms slightly to emphasize her points. The lighting is soft and warm, emanating from the lamp and an unseen front source, creating a gentle glow without harsh shadows. The overall aesthetic is realistic and cinematic, conveying a sense of direct communication in a comfortable, contemporary environment." |
| }, |
| { |
| "reference": { |
| "video_id": "oUCQH11m-yY", |
| "video_url": "https://www.youtube.com/watch?v=oUCQH11m-yY", |
| "start_time": 530.8385416666666, |
| "end_time": 535.8802083333333, |
| "start_frame": 12727, |
| "end_frame": 12848, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "js2vfr96iAQ", |
| "video_url": "https://www.youtube.com/watch?v=js2vfr96iAQ", |
| "start_time": 0.1, |
| "end_time": 5.141666666666667, |
| "start_frame": 2, |
| "end_frame": 123, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A bald man with a short reddish-brown beard and a black V-neck shirt is centered in a medium close-up shot, speaking directly to the camera. His face is illuminated by soft, even front lighting, casting minimal shadows. He maintains a calm and focused expression, articulating words with subtle movements of his mouth and occasional blinks. His head makes slight, natural shifts as he speaks, conveying engagement. The background is softly blurred, revealing an inviting indoor setting. To the left, a green leafy plant adds a touch of nature, while a white fireplace mantel is visible behind him. On the right, a dark metal shelf holds a spherical lamp emitting a warm, ambient glow, contributing to the scene's cozy and cinematic atmosphere. The overall aesthetic is realistic and polished." |
| }, |
| { |
| "reference": { |
| "video_id": "kZvb5pkr0UU", |
| "video_url": "https://www.youtube.com/watch?v=kZvb5pkr0UU", |
| "start_time": 371.5544166666666, |
| "end_time": 376.5960833333333, |
| "start_frame": 8908, |
| "end_frame": 9029, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 960 |
| }, |
| "target": { |
| "video_id": "4WmW1e2GD8U", |
| "video_url": "https://www.youtube.com/watch?v=4WmW1e2GD8U", |
| "start_time": 256.6615416666666, |
| "end_time": 261.7032083333333, |
| "start_frame": 6154, |
| "end_frame": 6275, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A medium close-up shot frames a young man with distinctive dark, curly hair and a neatly trimmed beard, wearing stylish sunglasses and a dark blue collared shirt. He stands outdoors in a sunlit urban environment, looking directly into the camera with a calm and engaged expression. A small black lavalier microphone is discreetly clipped to his shirt, just below his collar. The background, softly blurred, reveals a bustling city scene with various brick buildings of different architectural styles and heights, some featuring large windows. Lush green trees are interspersed among the structures, providing a natural contrast to the urban landscape. Bright natural daylight illuminates the scene, creating clear highlights and soft shadows that define his features. The aesthetic is realistic and cinematic, capturing a moment of direct address in a vibrant city setting as his mouth moves, indicating he is speaking." |
| }, |
| { |
| "reference": { |
| "video_id": "H6yKrCg6KiE", |
| "video_url": "https://www.youtube.com/watch?v=H6yKrCg6KiE", |
| "start_time": 529.1285, |
| "end_time": 534.1701666666667, |
| "start_frame": 15858, |
| "end_frame": 16009, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "JcbZ2onkr-s", |
| "video_url": "https://www.youtube.com/watch?v=JcbZ2onkr-s", |
| "start_time": 139.80953333333332, |
| "end_time": 144.85119999999998, |
| "start_frame": 4190, |
| "end_frame": 4341, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with dark, wavy hair stands in a brightly lit, modern living room, decorated with festive string lights and a blurred Christmas tree in the background. She wears a cozy white cardigan adorned with a repeating pattern of red and green flowers. Positioned in a medium shot, she looks directly at the camera, speaking with an open mouth and a friendly, engaging expression. Her hands make small, expressive gestures as she talks, occasionally touching her necklace or moving her fingers. The room features white walls, a large window letting in soft natural light from the left, and wooden shelves with decorative items on the right. The overall atmosphere is warm and inviting, illuminated by a combination of daylight and the soft glow of holiday lights, creating a cheerful cinematic mood." |
| }, |
| { |
| "reference": { |
| "video_id": "tJiTUoAxIoU", |
| "video_url": "https://www.youtube.com/watch?v=tJiTUoAxIoU", |
| "start_time": 205.84216666666663, |
| "end_time": 210.88383333333329, |
| "start_frame": 4935, |
| "end_frame": 5056, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "4quA9WiAPbQ", |
| "video_url": "https://www.youtube.com/watch?v=4quA9WiAPbQ", |
| "start_time": 172.76940000000002, |
| "end_time": 177.81106666666668, |
| "start_frame": 5178, |
| "end_frame": 5329, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a middle-aged woman with shoulder-length brown hair and red-framed glasses, wearing a green patterned blouse, speaking directly to the camera. She stands in a well-lit indoor setting, likely an office, with a light-colored wall and a dark bookshelf filled with various decorative items behind her. These items include a large white letter 'A', a potted plant, books, and small figurines, adding a personalized touch to the background. The woman's face is expressive, conveying an engaged and friendly demeanor as she articulates her words. She uses dynamic hand gestures, raising her left hand with fingers splayed, then bringing both hands together before spreading them wide again, emphasizing her points. Her eyes are wide, and a slight smile plays on her lips, suggesting enthusiasm and clear communication. The lighting is bright and even, illuminating her face without harsh shadows, contributing to a realistic and clear cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "eTg5yKuOzRM", |
| "video_url": "https://www.youtube.com/watch?v=eTg5yKuOzRM", |
| "start_time": 13.524999999999999, |
| "end_time": 18.566666666666666, |
| "start_frame": 406, |
| "end_frame": 557, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "7uGNA4rLAeU", |
| "video_url": "https://www.youtube.com/watch?v=7uGNA4rLAeU", |
| "start_time": 118.07500000000002, |
| "end_time": 123.11666666666669, |
| "start_frame": 3542, |
| "end_frame": 3694, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, wavy brown hair and striking blue eyes, wearing a cozy beige knit sweater. She is positioned centrally, speaking directly to the camera with an engaging and informative expression, her mouth articulating words clearly. Her hands occasionally rise to gesture subtly, emphasizing her points. Behind her, a neatly made bed with a textured grey comforter and decorative pillows featuring red and white patterns fills the background. Several small, dark-colored bottles with droppers are arranged on the bed, slightly out of focus. The room features a soft lavender wall and a white paneled door, suggesting a comfortable, domestic setting. The lighting is bright and even, casting no harsh shadows, contributing to a clear, realistic cinematic aesthetic. Her calm demeanor and direct gaze convey a sense of approachability." |
| }, |
| { |
| "reference": { |
| "video_id": "fX60uyhby2o", |
| "video_url": "https://www.youtube.com/watch?v=fX60uyhby2o", |
| "start_time": 248.9486, |
| "end_time": 253.99026666666666, |
| "start_frame": 7461, |
| "end_frame": 7612, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Oaq8IpOwR2I", |
| "video_url": "https://www.youtube.com/watch?v=Oaq8IpOwR2I", |
| "start_time": 60.42693333333334, |
| "end_time": 65.46860000000001, |
| "start_frame": 1811, |
| "end_frame": 1962, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with medium brown hair and blue eyes is centered in a medium close-up shot, speaking directly to the camera. She wears a brown, black, and white plaid shirt over a black top, accessorized with silver hoop earrings and a delicate silver necklace. Her expression is calm and engaging, with subtle head nods and mouth movements as she articulates words. Her right hand occasionally gestures gently near her chest, while her left hand remains still. The background reveals a cozy indoor setting, likely a bedroom, with a white wall adorned with small, minimalist art pieces including a rainbow and cacti, and a white macrame hanging. A bed with a white and grey patterned duvet and a pink pillow is visible to the left. The scene is brightly and evenly lit, suggesting natural daylight, creating a clear and inviting atmosphere. The overall aesthetic is a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "gnV0Nfb67Tc", |
| "video_url": "https://www.youtube.com/watch?v=gnV0Nfb67Tc", |
| "start_time": 589.74, |
| "end_time": 594.7816666666666, |
| "start_frame": 14744, |
| "end_frame": 14870, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "t5VjVWEDPT8", |
| "video_url": "https://www.youtube.com/watch?v=t5VjVWEDPT8", |
| "start_time": 141.06, |
| "end_time": 146.10166666666666, |
| "start_frame": 3526, |
| "end_frame": 3653, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, straight brown hair, parted in the middle, is framed in a medium close-up shot against a clean, white background. To her right, a vibrant green plant with large, glossy leaves adds a touch of natural color. She wears a dark blue turtleneck sweater with a silver zipper detail at the collar. Her expression is calm and engaged as she speaks directly to the camera, her mouth articulating words clearly. Her eyes blink naturally, and she makes subtle head movements, conveying a thoughtful and communicative demeanor. Briefly, her right hand enters the lower left of the frame, holding a small, reflective object, before moving out again. The lighting is soft and even, suggesting a bright daytime setting with minimal harsh shadows, contributing to a realistic and intimate cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "1j-CGxlGREo", |
| "video_url": "https://www.youtube.com/watch?v=1j-CGxlGREo", |
| "start_time": 562.8966666666666, |
| "end_time": 567.9383333333333, |
| "start_frame": 14072, |
| "end_frame": 14198, |
| "fps": 25.0, |
| "width": 1280, |
| "height": 720 |
| }, |
| "target": { |
| "video_id": "VU0b0ST8dN4", |
| "video_url": "https://www.youtube.com/watch?v=VU0b0ST8dN4", |
| "start_time": 611.515, |
| "end_time": 616.5566666666666, |
| "start_frame": 15288, |
| "end_frame": 15414, |
| "fps": 25.0, |
| "width": 1280, |
| "height": 720 |
| }, |
| "target_caption": "A medium close-up shot captures a woman with dark skin and long, wavy brown hair with blonde highlights, wearing a vibrant royal blue top with ruffled sleeves. She is seated indoors, speaking directly to the camera with a calm and conversational demeanor. Her mouth moves expressively as she articulates words, and her eyes blink naturally. Throughout the segment, her facial expressions shift subtly, conveying a sense of engagement and occasional lightheartedness, with a slight smile or smirk appearing at times. She nods her head gently to emphasize points. The background is a softly blurred, modern interior featuring light gray walls, a gray armchair, and a white lamp. On the right, a professional microphone with a glowing blue and purple light stands prominently. Further back, framed artwork, a dark television, and a white shelving unit with various objects are visible. The scene is brightly and evenly lit, creating a clear, realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "BsEDM0naj9M", |
| "video_url": "https://www.youtube.com/watch?v=BsEDM0naj9M", |
| "start_time": 878.2955416666666, |
| "end_time": 883.3372083333333, |
| "start_frame": 21058, |
| "end_frame": 21179, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "aWUSypQYWl4", |
| "video_url": "https://www.youtube.com/watch?v=aWUSypQYWl4", |
| "start_time": 462.275, |
| "end_time": 467.31666666666666, |
| "start_frame": 11095, |
| "end_frame": 11216, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, flowing dark brown hair and fair skin is prominently featured in a medium close-up shot, seated inside a parked car. She wears a casual blue tie-dye hoodie, and a small, subtle pink earbud is visible in her left ear. Her gaze is directed straight into the camera, conveying a direct and engaging presence. As she speaks, her lips articulate words, and her eyes blink naturally, maintaining a calm and conversational demeanor. Bright, diffused natural daylight floods the car's interior from the large windows, casting a soft, even illumination across her face and creating gentle, subtle shadows that define the car's contours. Through the sun-drenched windows, a blurred outdoor scene of trees and other vehicles suggests a clear, bright daytime environment. The visual style is realistic and cinematic, emphasizing a personal, direct address." |
| }, |
| { |
| "reference": { |
| "video_id": "wqNu6pNRAR4", |
| "video_url": "https://www.youtube.com/watch?v=wqNu6pNRAR4", |
| "start_time": 293.3333333333333, |
| "end_time": 298.375, |
| "start_frame": 8800, |
| "end_frame": 8951, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Z405ehfiEJI", |
| "video_url": "https://www.youtube.com/watch?v=Z405ehfiEJI", |
| "start_time": 88.96666666666667, |
| "end_time": 94.00833333333334, |
| "start_frame": 2669, |
| "end_frame": 2820, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A middle-aged man with light skin and short brown hair is featured in a medium close-up shot, positioned slightly below eye level. He wears a dark olive green t-shirt and is seated indoors against a plain, warm brown wall adorned with several framed landscape pictures. A black microphone stands prominently in the lower left foreground. The man speaks directly to the camera, his mouth articulating words and his eyes blinking naturally, conveying a calm and focused demeanor. His facial muscles subtly shift with his speech, but his head remains largely still. Bright, even frontal lighting illuminates the scene, casting soft, minimal shadows and creating a clear, realistic cinematic aesthetic, typical of a daytime indoor setting. The overall mood is one of direct communication and instruction." |
| }, |
| { |
| "reference": { |
| "video_id": "6ryI5z6aEZA", |
| "video_url": "https://www.youtube.com/watch?v=6ryI5z6aEZA", |
| "start_time": 69.01833333333333, |
| "end_time": 74.06, |
| "start_frame": 1725, |
| "end_frame": 1852, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "nJIZlXvKsXk", |
| "video_url": "https://www.youtube.com/watch?v=nJIZlXvKsXk", |
| "start_time": 21.779999999999998, |
| "end_time": 26.821666666666665, |
| "start_frame": 544, |
| "end_frame": 671, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a man with a neatly trimmed beard and dark hair, wearing a plain black t-shirt, speaking directly to the camera. He stands in a brightly lit, minimalist room with white walls. Behind him, a large window with light-colored curtains allows soft, natural daylight to illuminate the scene. On the right side of the frame, a small wooden table holds a vibrant green plant in a red pot and a glowing orange Himalayan salt lamp, casting a warm, ambient light. Two framed, abstract art pieces hang on the wall further back. The man's expression is friendly and engaging, with a slight smile, as he articulates words and uses subtle hand gestures to emphasize his points. The overall mood is calm and inviting, presented in a realistic cinematic style with even, bright lighting." |
| }, |
| { |
| "reference": { |
| "video_id": "VKKhoWewklM", |
| "video_url": "https://www.youtube.com/watch?v=VKKhoWewklM", |
| "start_time": 1383.592, |
| "end_time": 1388.6336666666668, |
| "start_frame": 41466, |
| "end_frame": 41617, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "n_WMBQR5BO4", |
| "video_url": "https://www.youtube.com/watch?v=n_WMBQR5BO4", |
| "start_time": 593.6963, |
| "end_time": 598.7379666666666, |
| "start_frame": 17793, |
| "end_frame": 17944, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, straight brown hair and blue eyes is centered in a medium close-up shot, looking directly at the camera. She wears a light blue, fuzzy crew-neck sweater. Her expression is calm and focused as she speaks, her mouth moving subtly to form words, and her eyes occasionally blinking. The background is a bright, minimalist indoor setting with white walls. To her left, a white bookshelf holds various decorative items, including a glass jar filled with light-colored objects and a colorful framed picture. To her right, a vibrant green potted plant with heart-shaped leaves adds a touch of natural color. The scene is evenly lit with soft, bright light, suggesting a daytime setting, creating a clean and professional aesthetic. The overall mood is calm and informative." |
| }, |
| { |
| "reference": { |
| "video_id": "e2UbmAPYf1Q", |
| "video_url": "https://www.youtube.com/watch?v=e2UbmAPYf1Q", |
| "start_time": 372.6805416666666, |
| "end_time": 377.7222083333333, |
| "start_frame": 8935, |
| "end_frame": 9056, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "E36Ku6MvaFY", |
| "video_url": "https://www.youtube.com/watch?v=E36Ku6MvaFY", |
| "start_time": 178.55620833333333, |
| "end_time": 183.597875, |
| "start_frame": 4281, |
| "end_frame": 4402, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, wavy brown hair, wearing a textured, bright green sweater, as she sits and looks directly into the camera. The background is dimly lit, creating an intimate and focused atmosphere. Warm, soft light emanates from a lamp positioned to the left, casting a gentle glow on a hanging guitar, while a dark green sofa and a white cabinet are subtly visible on the right, receding into soft shadows. The woman speaks calmly and articulately, her mouth moving precisely, and her head occasionally shifts with subtle, natural movements. Her expression is composed and thoughtful, conveying a sense of earnestness and direct engagement with the viewer. The predominant warm lighting suggests an evening or indoor setting, with soft shadows adding depth and a realistic cinematic quality to the scene, fostering a mood of quiet concentration." |
| }, |
| { |
| "reference": { |
| "video_id": "RqPQnt0YrRU", |
| "video_url": "https://www.youtube.com/watch?v=RqPQnt0YrRU", |
| "start_time": 28.05816666666666, |
| "end_time": 33.09983333333333, |
| "start_frame": 841, |
| "end_frame": 992, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "P8NBpFYfFtM", |
| "video_url": "https://www.youtube.com/watch?v=P8NBpFYfFtM", |
| "start_time": 26.89343333333333, |
| "end_time": 31.9351, |
| "start_frame": 806, |
| "end_frame": 957, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures a young Black woman with long, dark, wavy hair, styled with a side part, speaking directly to the camera. She wears a brown top and delicate gold jewelry, including hoop earrings and a layered necklace. Her face is highly expressive, featuring a bright, engaging smile that reveals her white teeth, and her eyes are wide and animated. She gestures frequently with both hands, palms open and fingers spread, emphasizing her words with dynamic, fluid movements. Her head subtly tilts as she speaks, conveying enthusiasm and a friendly demeanor. The background is a softly lit indoor space with light gray walls, a white paneled door on the left, and horizontal window blinds on the right. A dark green plant is partially visible behind her left shoulder. The lighting is soft and even, illuminating her face without harsh shadows, contributing to a clear, realistic cinematic aesthetic. She appears cheerful and confident, actively communicating with the viewer." |
| }, |
| { |
| "reference": { |
| "video_id": "NobUwnT6MtI", |
| "video_url": "https://www.youtube.com/watch?v=NobUwnT6MtI", |
| "start_time": 987.2583333333334, |
| "end_time": 992.3000000000001, |
| "start_frame": 29618, |
| "end_frame": 29769, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "lD6bYkyC5Ag", |
| "video_url": "https://www.youtube.com/watch?v=lD6bYkyC5Ag", |
| "start_time": 1539.1833333333334, |
| "end_time": 1544.2250000000001, |
| "start_frame": 46176, |
| "end_frame": 46327, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with medium-brown hair, pulled back in a ponytail, stands centered in a medium shot, speaking directly to the camera. She wears a textured, olive-green zippered sweater over a white top. Her expression is friendly and engaging, with a slight smile and active eye contact, as she occasionally makes subtle hand gestures to emphasize her words. Behind her, two tall, brightly lit bookshelves are filled with numerous books of varying sizes and colorful spines, creating a vibrant, organized backdrop. The left shelf is dark green, while the right is white, both packed with titles. The lighting is soft and even, illuminating her face and the books without harsh shadows, suggesting an indoor, daytime setting. The overall aesthetic is clean, realistic, and well-composed, typical of a personal video or vlog." |
| }, |
| { |
| "reference": { |
| "video_id": "Wup12Ts4bZg", |
| "video_url": "https://www.youtube.com/watch?v=Wup12Ts4bZg", |
| "start_time": 623.6126333333333, |
| "end_time": 628.6542999999999, |
| "start_frame": 18690, |
| "end_frame": 18841, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Tw9g6UhcUgU", |
| "video_url": "https://www.youtube.com/watch?v=Tw9g6UhcUgU", |
| "start_time": 231.331, |
| "end_time": 236.37266666666665, |
| "start_frame": 6933, |
| "end_frame": 7084, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a middle-aged woman with light brown hair, wearing a cream-colored sleeveless top and a dark beaded necklace, seated indoors. She holds an open book in her right hand, occasionally glancing down at its pages. Her left hand gestures expressively as she speaks directly to the camera, her mouth moving articulately. Her facial expression is calm and engaged, with a slight, pleasant smile. The background features a plain light-colored wall, with a white bookshelf visible to her right. The shelf holds various books, a framed black-and-white picture, a vibrant green potted plant, and a purple water bottle. The scene is brightly and evenly lit, suggesting natural daylight, creating a clear and inviting atmosphere. The overall aesthetic is a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "LFWLM65bkBo", |
| "video_url": "https://www.youtube.com/watch?v=LFWLM65bkBo", |
| "start_time": 1051.2333333333336, |
| "end_time": 1056.2750000000003, |
| "start_frame": 63074, |
| "end_frame": 63377, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "2_XnFu3quHw", |
| "video_url": "https://www.youtube.com/watch?v=2_XnFu3quHw", |
| "start_time": 1031.8983333333333, |
| "end_time": 1036.94, |
| "start_frame": 51595, |
| "end_frame": 51847, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, wavy brown hair and a light-colored turtleneck sweater is centered in a medium shot, speaking directly to the camera. Her expression is animated and enthusiastic as she articulates words, her mouth moving fluidly. In the background, a white bookshelf filled with various books creates a cozy, intellectual atmosphere. Festive green garland and a large red bow on a decorative object add a touch of holiday cheer to the scene. The woman gestures expressively with her hands, opening them wide to emphasize a point, then bringing them together in a soft, clapping motion. Her eyes close briefly with a thoughtful or emphatic expression before opening again. The lighting is bright and even, illuminating her face and the background without harsh shadows, creating a clear and inviting visual. A graphic overlay of a book cover titled \"God of Fury\" and the number \"7\" are visible in the upper right corner. The overall aesthetic is a realistic, cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "nZMBv_cdjo4", |
| "video_url": "https://www.youtube.com/watch?v=nZMBv_cdjo4", |
| "start_time": 376.17999999999995, |
| "end_time": 381.22166666666664, |
| "start_frame": 9404, |
| "end_frame": 9531, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "ICNIGBvjeBA", |
| "video_url": "https://www.youtube.com/watch?v=ICNIGBvjeBA", |
| "start_time": 1475.4583333333333, |
| "end_time": 1480.5, |
| "start_frame": 36886, |
| "end_frame": 37012, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a young woman with long, wavy blonde hair, wearing a dark top, speaking directly to the camera. She gestures subtly with her right hand, her mouth moving as she articulates words. Her expression shifts from engaged speaking to a brief, gentle smile. The background features a large, white bookshelf densely packed with colorful books, illuminated by warm, twinkling string lights draped across its shelves. To the right, a brightly lit Christmas tree, adorned with numerous ornaments and more string lights, adds a festive glow to the cozy indoor setting. The lighting is soft and warm, creating an inviting and intimate atmosphere, suggesting an evening or indoor scene. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "CetgZkixtaM", |
| "video_url": "https://www.youtube.com/watch?v=CetgZkixtaM", |
| "start_time": 445.22499999999997, |
| "end_time": 450.26666666666665, |
| "start_frame": 13357, |
| "end_frame": 13508, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "yydcMX979tI", |
| "video_url": "https://www.youtube.com/watch?v=yydcMX979tI", |
| "start_time": 258.5604, |
| "end_time": 263.6020666666667, |
| "start_frame": 7749, |
| "end_frame": 7900, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with short, curly grey hair and a light-colored top, seated in a brightly lit indoor setting. Behind her, two tall white bookshelves filled with colorful books frame the scene. To her left, a large window allows natural light to stream in, illuminating a small wooden table with a candle and a white folding table holding potted plants and white flowers. A pink blanket is visible on a chair to her right. She engages in conversation, her lips articulating words clearly. Her gaze shifts subtly, occasionally looking slightly off-camera to her left and then back towards the viewer, conveying a thoughtful and engaging presence. She wears small, dark, dangling earrings. Her head makes slight, natural movements as she speaks, emphasizing her points. Her expression is calm and focused, suggesting a relaxed yet attentive demeanor. The shot is eye-level, providing a direct and personal perspective. Soft, natural light from the window illuminates her face and the room, creating gentle shadows and a warm, inviting atmosphere. The aesthetic is realistic and cinematic, with clear focus on the subject." |
| }, |
| { |
| "reference": { |
| "video_id": "-i9oQjlT2lg", |
| "video_url": "https://www.youtube.com/watch?v=-i9oQjlT2lg", |
| "start_time": 726.8062166666667, |
| "end_time": 731.8478833333334, |
| "start_frame": 43565, |
| "end_frame": 43867, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "DvIB8qcXfKI", |
| "video_url": "https://www.youtube.com/watch?v=DvIB8qcXfKI", |
| "start_time": 502.025, |
| "end_time": 507.06666666666666, |
| "start_frame": 30122, |
| "end_frame": 30424, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, straight blonde hair and light blue eyes is centered in a medium close-up shot, speaking directly to the camera. She wears a simple black turtleneck top. Her facial expressions are animated, with her mouth forming various shapes as she articulates words, and her eyes occasionally shifting slightly to the side before returning to direct gaze. She gestures subtly with her hands, bringing them up to emphasize points in her speech. The background reveals a modern, minimalist room with a grey wall on the left and a white wall on the right. White floating shelves adorned with small decorative items, including a pink floral arrangement, are visible behind her. The lighting is soft and even, illuminating her face clearly and creating a calm, engaging atmosphere. The overall aesthetic is a realistic, clean cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "E2bwzMqBM-M", |
| "video_url": "https://www.youtube.com/watch?v=E2bwzMqBM-M", |
| "start_time": 398.6648333333333, |
| "end_time": 403.7065, |
| "start_frame": 11948, |
| "end_frame": 12099, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "rhU13A1zRys", |
| "video_url": "https://www.youtube.com/watch?v=rhU13A1zRys", |
| "start_time": 216.94996666666665, |
| "end_time": 221.9916333333333, |
| "start_frame": 6502, |
| "end_frame": 6653, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian man with short, dark hair and a grey t-shirt is centered in a medium close-up shot, speaking directly to the camera. He maintains a calm, engaging expression, with his mouth moving as he articulates words. The background reveals a minimalist home office or studio setup: a plain white wall adorned with three framed, dark-toned pictures. Below the pictures, a desk is visible, featuring two dark computer monitors and two black studio speakers with silver accents. The lighting is bright and even, illuminating the man's face without harsh shadows, suggesting a well-lit indoor environment. Blue, bold, capitalized text, \"TARGETS GET RECRUITED BY EVERY FIRM,\" appears overlaid at the bottom of the frame, adding an informative element to the realistic cinematic aesthetic. The overall mood is direct and instructional." |
| }, |
| { |
| "reference": { |
| "video_id": "uF3VGAvakv4", |
| "video_url": "https://www.youtube.com/watch?v=uF3VGAvakv4", |
| "start_time": 397.1083333333333, |
| "end_time": 402.15, |
| "start_frame": 9531, |
| "end_frame": 9652, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "igDXJuTVdyI", |
| "video_url": "https://www.youtube.com/watch?v=igDXJuTVdyI", |
| "start_time": 921.5787083333333, |
| "end_time": 926.620375, |
| "start_frame": 22096, |
| "end_frame": 22217, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames an Asian man with short, dark hair, wearing a white t-shirt, speaking directly to the camera. He stands in a brightly lit room with a light-colored wall as the background. To his left, a framed picture displays a grid of dollar bills, while a large, vibrant green plant with numerous leaves occupies the right side of the frame, adding a touch of natural color. The man's mouth moves articulately as he speaks, his head making subtle, natural movements to emphasize his words. His expression is calm and engaged, conveying a sense of thoughtful communication. His hands occasionally make small, understated gestures. The lighting is soft and even, suggesting a well-lit indoor environment during the day, with minimal harsh shadows. The overall aesthetic is realistic and clean, presenting a clear and direct visual." |
| }, |
| { |
| "reference": { |
| "video_id": "l6eJbT5t7bM", |
| "video_url": "https://www.youtube.com/watch?v=l6eJbT5t7bM", |
| "start_time": 485.3213666666667, |
| "end_time": 490.36303333333336, |
| "start_frame": 14545, |
| "end_frame": 14696, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "SYFywX3AedE", |
| "video_url": "https://www.youtube.com/watch?v=SYFywX3AedE", |
| "start_time": 40.43333333333334, |
| "end_time": 45.475, |
| "start_frame": 969, |
| "end_frame": 1090, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian woman with long, straight brown hair, styled with a side part, is featured in a medium close-up shot. She wears a light blue off-the-shoulder top with intricate eyelet embroidery and a delicate silver necklace adorned with a small clover pendant. Her expression is calm and composed as she speaks directly to the camera, maintaining consistent eye contact. Her lips articulate words clearly, and she blinks naturally, occasionally shifting her gaze slightly downwards before returning to the lens. The background reveals a simple, uncluttered indoor setting with light beige walls. To her right, a white closed door is visible, and further right, a window with closed white horizontal blinds allows soft, diffused daylight to illuminate the scene. The lighting is bright and even, casting minimal shadows and contributing to a clear, realistic cinematic aesthetic. The overall mood is conversational and engaging." |
| }, |
| { |
| "reference": { |
| "video_id": "aMB0D2MR2kA", |
| "video_url": "https://www.youtube.com/watch?v=aMB0D2MR2kA", |
| "start_time": 770.3177083333334, |
| "end_time": 775.359375, |
| "start_frame": 18469, |
| "end_frame": 18590, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Ez8qGA8QBNY", |
| "video_url": "https://www.youtube.com/watch?v=Ez8qGA8QBNY", |
| "start_time": 344.27203333333335, |
| "end_time": 349.31370000000004, |
| "start_frame": 10318, |
| "end_frame": 10469, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A bald man with a neatly trimmed beard and a blue t-shirt featuring faded white text stands in a medium shot, addressing the viewer directly. He occupies the center of the frame, his gaze steady and engaged. Behind him, a textured gray concrete wall provides a minimalist backdrop, contrasted by a vibrant green leafy plant positioned to his left. A subtle silver metal railing runs horizontally across the mid-ground. The man speaks with clear articulation, his mouth forming words, and he occasionally uses small, deliberate hand gestures to emphasize his points. His expression is serious and focused, conveying a sense of earnestness. The scene is brightly and evenly lit, casting soft shadows and highlighting the realistic cinematic style. White text overlays the top right corner of the frame, providing additional context." |
| }, |
| { |
| "reference": { |
| "video_id": "UQuqEglQAoA", |
| "video_url": "https://www.youtube.com/watch?v=UQuqEglQAoA", |
| "start_time": 124.89463333333335, |
| "end_time": 129.93630000000002, |
| "start_frame": 3743, |
| "end_frame": 3894, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "4tEz-Si5-VQ", |
| "video_url": "https://www.youtube.com/watch?v=4tEz-Si5-VQ", |
| "start_time": 312.53712499999995, |
| "end_time": 317.57879166666663, |
| "start_frame": 7493, |
| "end_frame": 7614, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a man with dark, wavy hair and glasses, wearing a black zip-up jacket with \"THE NORTH FACE\" logo, seated in front of a plain, light blue background. He is positioned behind a silver laptop, which is partially visible in the lower foreground. The man is actively speaking, his mouth moving clearly, and his head occasionally nodding to emphasize points. He uses expressive hand gestures, at one moment pointing forward with his right index finger, then opening both hands, and later tapping his left hand with his right. His expression is calm and engaged, conveying a thoughtful demeanor as he communicates. The lighting is bright and even, casting minimal shadows and creating a clean, professional studio aesthetic. The overall style is realistic and cinematic, presented in high definition." |
| }, |
| { |
| "reference": { |
| "video_id": "6gQTZMG-sZg", |
| "video_url": "https://www.youtube.com/watch?v=6gQTZMG-sZg", |
| "start_time": 63.49666666666666, |
| "end_time": 68.53833333333333, |
| "start_frame": 1522, |
| "end_frame": 1643, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "rDjC11iOgt8", |
| "video_url": "https://www.youtube.com/watch?v=rDjC11iOgt8", |
| "start_time": 157.92433333333332, |
| "end_time": 162.96599999999998, |
| "start_frame": 3786, |
| "end_frame": 3907, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a middle-aged man with a grey beard and hair, wearing round glasses and a black zip-up jacket with a small polo logo over a dark scarf. He sits in an indoor setting, speaking directly, his mouth moving with each word, and his eyes blinking occasionally. His expression is calm and thoughtful, conveying a sense of engagement. The background reveals a softly lit room with a light-colored bookshelf adorned with various decorative objects, a table lamp, and a window letting in natural light. A patterned armchair is partially visible to the right. The lighting is bright and even, casting soft shadows and highlighting the realistic cinematic style of the scene. The overall atmosphere is serene and conducive to an interview or conversation, with the man's subtle head movements emphasizing his speech." |
| }, |
| { |
| "reference": { |
| "video_id": "RT8VJhMv4pc", |
| "video_url": "https://www.youtube.com/watch?v=RT8VJhMv4pc", |
| "start_time": 754.5916666666667, |
| "end_time": 759.6333333333333, |
| "start_frame": 22638, |
| "end_frame": 22789, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "FPKthdjDWzk", |
| "video_url": "https://www.youtube.com/watch?v=FPKthdjDWzk", |
| "start_time": 935.1416666666667, |
| "end_time": 940.1833333333333, |
| "start_frame": 28054, |
| "end_frame": 28206, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long blonde hair and a red headband sits in a fluffy white chair, positioned in a well-lit room. She wears a light blue long-sleeved top with delicate lace trim. In front of her, a silver laptop with a glowing Apple logo rests on a surface. To her left, a tall wooden bookshelf is packed with numerous books, some featuring vibrant covers, alongside decorative items like a small house-shaped ornament. A gold floor lamp stands behind her, adding to the warm ambiance. The woman is actively speaking, her mouth moving expressively, and she frequently gestures with her right hand, raising it and moving her fingers as she articulates her thoughts. Her gaze alternates between the laptop screen and directly towards the viewer, conveying an engaged and conversational mood. The scene is captured in a medium shot at eye-level, illuminated by soft, bright indoor lighting, creating a clear and realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "y5TxuLgPixU", |
| "video_url": "https://www.youtube.com/watch?v=y5TxuLgPixU", |
| "start_time": 308.4246833333333, |
| "end_time": 313.46635, |
| "start_frame": 18487, |
| "end_frame": 18789, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Y7RLQdD7dRM", |
| "video_url": "https://www.youtube.com/watch?v=Y7RLQdD7dRM", |
| "start_time": 826.1919333333334, |
| "end_time": 831.2336, |
| "start_frame": 49522, |
| "end_frame": 49824, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with short brown hair, wearing a cream-colored cardigan over a black top, sits in a cozy, festive indoor setting. To her left, a vibrant Christmas tree, adorned with twinkling lights and red and silver ornaments, creates a warm, inviting glow. On her right, a white bookshelf displays various decorative items, including a red-striped gnome and a Christmas stocking. She holds a small black microphone in her right hand and a dark-covered book titled \"Heartless Hunter\" in her left. Her expression is pleasant and engaging as she speaks directly to the camera, gesturing subtly with her hands. The medium shot, captured at eye-level, highlights her enthusiastic demeanor. The scene is bathed in soft, even indoor lighting, enhancing the cheerful holiday atmosphere with a realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "BecK-9NEh88", |
| "video_url": "https://www.youtube.com/watch?v=BecK-9NEh88", |
| "start_time": 114.98803333333333, |
| "end_time": 120.0297, |
| "start_frame": 3446, |
| "end_frame": 3597, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "af5LW8x-TCs", |
| "video_url": "https://www.youtube.com/watch?v=af5LW8x-TCs", |
| "start_time": 486.48279999999994, |
| "end_time": 491.5244666666666, |
| "start_frame": 14580, |
| "end_frame": 14731, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures a woman with long, dark hair, wearing a white t-shirt and a delicate silver necklace, speaking directly to the camera. Her expression is calm and engaging, with a slight, friendly smile as her mouth moves in conversation. She uses expressive hand gestures, initially spreading her palms outwards, then bringing her hands up towards her chest and shoulders in a more contained motion, before extending them outwards again. The background is a plain, light grey wall, providing a clean, uncluttered setting. To the right of the frame, a black stand holds two rolled-up backdrops in shades of pink and red, adding a subtle pop of color. The lighting is bright and even, casting soft shadows and highlighting her features. The overall aesthetic is a realistic, cinematic style, typical of an instructional or conversational video." |
| }, |
| { |
| "reference": { |
| "video_id": "GA2fkjnOyLY", |
| "video_url": "https://www.youtube.com/watch?v=GA2fkjnOyLY", |
| "start_time": 1173.3787, |
| "end_time": 1178.4203666666667, |
| "start_frame": 35166, |
| "end_frame": 35317, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "nE8VHqk_VS8", |
| "video_url": "https://www.youtube.com/watch?v=nE8VHqk_VS8", |
| "start_time": 34.20073333333333, |
| "end_time": 39.242399999999996, |
| "start_frame": 1025, |
| "end_frame": 1176, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, reddish-brown hair and dark-rimmed glasses, wearing a red sweater adorned with subtle heart patterns and a small black microphone clipped to her collar. She is positioned centrally, looking directly at the camera with a warm, engaging smile. Her expression is friendly and calm, conveying a sense of approachability as she speaks, with subtle movements of her head and facial muscles animating her speech. The background reveals a cozy indoor setting, likely a living room or study, with a white bookshelf filled with various books on the right side. A trailing green plant hangs gracefully from above the bookshelf, adding a touch of natural vibrancy. The scene is brightly lit with soft, natural light, suggesting daytime, creating a clear and inviting atmosphere. The overall aesthetic is realistic and cinematic, capturing a genuine and personal interaction." |
| }, |
| { |
| "reference": { |
| "video_id": "eKWv0BN6Pl4", |
| "video_url": "https://www.youtube.com/watch?v=eKWv0BN6Pl4", |
| "start_time": 1142.7246333333335, |
| "end_time": 1147.7663000000002, |
| "start_frame": 34247, |
| "end_frame": 34399, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "TnTygKyPc0U", |
| "video_url": "https://www.youtube.com/watch?v=TnTygKyPc0U", |
| "start_time": 934.6336, |
| "end_time": 939.6752666666666, |
| "start_frame": 28011, |
| "end_frame": 28162, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with light brown hair pulled back sits comfortably on a grey sofa in a well-lit living room, captured in a medium, eye-level shot. She wears a light grey sweater with black horizontal stripes and silver hoop earrings. Her right arm rests on the back of the sofa, near a yellow throw pillow, and she occasionally gestures with her hand as she speaks. Her expression is calm and engaged, with a slight smile as she articulates her thoughts. In the background, a wooden staircase leads upwards, and a kitchen area with a sink is partially visible. Decorative elements on the sofa include a patterned blanket and colorful throw pillows. A distinctive mushroom-shaped lamp with a soft glow, a potted plant, and a purple vase adorn the sofa's backrest, adding to the cozy, domestic atmosphere. The lighting is bright and even, suggesting daytime, creating a realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "7FP_0SXbbtU", |
| "video_url": "https://www.youtube.com/watch?v=7FP_0SXbbtU", |
| "start_time": 540.8000000000001, |
| "end_time": 545.8416666666667, |
| "start_frame": 16224, |
| "end_frame": 16375, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "bIIbp6vM5y0", |
| "video_url": "https://www.youtube.com/watch?v=bIIbp6vM5y0", |
| "start_time": 642.3666666666667, |
| "end_time": 647.4083333333333, |
| "start_frame": 19271, |
| "end_frame": 19422, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with dark, wavy hair and round glasses is captured in a medium close-up shot, centered in a brightly lit room. She wears a cozy, speckled turtleneck sweater in shades of lime green, yellow, and white. Her head is slightly tilted down as she appears to be reading or speaking, her lips articulating words with subtle movements. Her eyes occasionally shift, conveying focus and engagement. The background features a clean, minimalist aesthetic with white walls, a dark green curtain, a white wardrobe or door, and a mirror reflecting a sliver of the room. To the right, a vintage botanical print hangs on the wall, adding a touch of natural elegance. The lighting is soft and even, suggesting a bright daytime setting, casting no harsh shadows and contributing to a calm, introspective mood. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "ufzQIKCprvI", |
| "video_url": "https://www.youtube.com/watch?v=ufzQIKCprvI", |
| "start_time": 210.03333333333333, |
| "end_time": 215.075, |
| "start_frame": 6301, |
| "end_frame": 6452, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "LLzCNMfEngI", |
| "video_url": "https://www.youtube.com/watch?v=LLzCNMfEngI", |
| "start_time": 31.591666666666665, |
| "end_time": 36.63333333333333, |
| "start_frame": 948, |
| "end_frame": 1099, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A woman with long, light brown hair and a black sleeveless top speaks directly into the camera in a medium close-up shot. She stands in front of a textured brick wall, which serves as a backdrop. Behind her, to the left, is a large, vibrant painting depicting a white horse galloping through a lush green landscape with distant mountains and a small wooden cabin. The woman's mouth moves continuously as she articulates words, her expression earnest and focused. She frequently gestures with her right hand, forming a fist and moving it up and down to emphasize her speech. Her eyes maintain direct contact with the viewer, conveying a sense of storytelling or explanation. The lighting is bright and even, illuminating her face and the background without harsh shadows, contributing to a clear, realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "pT6opDDBgJo", |
| "video_url": "https://www.youtube.com/watch?v=pT6opDDBgJo", |
| "start_time": 15.225, |
| "end_time": 20.266666666666666, |
| "start_frame": 457, |
| "end_frame": 608, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "8tyN9b5vXfs", |
| "video_url": "https://www.youtube.com/watch?v=8tyN9b5vXfs", |
| "start_time": 322.59999999999997, |
| "end_time": 327.64166666666665, |
| "start_frame": 9678, |
| "end_frame": 9829, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, light brown hair, wearing a blue and white plaid shirt, speaking directly to the camera. Her mouth moves articulately as she speaks, and her right hand makes subtle, expressive gestures, opening and closing her fingers near her chest. Her blue eyes are focused, and her expression is calm and earnest, conveying a sense of sincerity. The background is a brightly lit, minimalist room with white walls. To her left, a white dresser holds a small green plant and a black cap. Above it, a serene painting depicts a sandy path leading to a blue ocean under a clear sky. A white door is visible on the far left, and a white closet door on the right. The lighting is soft and even, suggesting natural daylight, creating a clear, realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "niWikvT-xNE", |
| "video_url": "https://www.youtube.com/watch?v=niWikvT-xNE", |
| "start_time": 80.07990000000001, |
| "end_time": 85.12156666666668, |
| "start_frame": 2400, |
| "end_frame": 2551, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "hNZuyI0TQiw", |
| "video_url": "https://www.youtube.com/watch?v=hNZuyI0TQiw", |
| "start_time": 1394.8000000000002, |
| "end_time": 1399.841666666667, |
| "start_frame": 41844, |
| "end_frame": 41995, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young man with short brown hair, a neatly trimmed beard, and black-rimmed glasses is centered in a medium close-up shot. He wears a grey t-shirt, a white pearl necklace, and a silver chain. He is seated in a dark, textured gaming chair, facing directly towards the camera. His mouth moves as he speaks, articulating words clearly, and his eyes blink occasionally, maintaining a focused and direct gaze. A black microphone on an arm stand is positioned in the lower right foreground, partially obscuring the view. The background consists of white shelving units filled with various colorful anime figures, collectibles, and other items, creating a personal and detailed environment. The lighting is bright and even, illuminating the scene without harsh shadows, suggesting an indoor setting during the day or under strong artificial lights. The overall aesthetic is realistic and cinematic, typical of a modern video blog or online content. His expression is calm and engaged as he communicates." |
| }, |
| { |
| "reference": { |
| "video_id": "4S86yoe5RDo", |
| "video_url": "https://www.youtube.com/watch?v=4S86yoe5RDo", |
| "start_time": 988.4540333333334, |
| "end_time": 993.4957, |
| "start_frame": 29624, |
| "end_frame": 29775, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "pZiu3gHb-eA", |
| "video_url": "https://www.youtube.com/watch?v=pZiu3gHb-eA", |
| "start_time": 765.7618, |
| "end_time": 770.8034666666666, |
| "start_frame": 22950, |
| "end_frame": 23101, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A fair-skinned man with shoulder-length blonde hair and black-rimmed glasses sits at a dark desk in a well-lit indoor studio. He wears a white collared shirt, a dark red vest, and a dark tie, with a black watch on his left wrist. Behind him, a white bookshelf filled with books and figurines occupies the left, while black sound-dampening foam panels cover the wall on the right. A black microphone on an articulated arm is positioned in front of him, and a laptop with a blue screen sits to his right. The man speaks directly to the camera, his expression calm and engaging with a slight smile. He gestures expressively, initially extending his right hand forward with an open palm, then bringing both hands up, palms open, as he articulates his point. The shot is a medium close-up, captured at eye-level, with bright, even lighting creating a clear, realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "BMiX7ycgq38", |
| "video_url": "https://www.youtube.com/watch?v=BMiX7ycgq38", |
| "start_time": 62.01185, |
| "end_time": 67.05351666666667, |
| "start_frame": 3717, |
| "end_frame": 4019, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "_ieoPw1uBH8", |
| "video_url": "https://www.youtube.com/watch?v=_ieoPw1uBH8", |
| "start_time": 49.599450000000004, |
| "end_time": 54.64111666666667, |
| "start_frame": 2973, |
| "end_frame": 3275, |
| "fps": 59.94005994005994, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A medium close-up shot captures a woman with long, dark hair, wearing a black long-sleeved shirt, seated in a gaming chair. She faces the camera directly, speaking with an energetic and engaging expression, her mouth forming words with visible teeth. Her eyes are bright, conveying a sense of direct communication. The background is bathed in a vibrant, almost neon green light, featuring shelves adorned with various objects: a large Bitcoin logo, a golden rifle, a violin, a small red toy car, and a miniature palm tree figurine. As she speaks, her right hand gestures dynamically, initially with an open palm, then pointing upwards with her index finger. She subsequently brings her thumb and index finger together before extending multiple fingers, seemingly counting or emphasizing points. The lighting is bright and even, casting minimal shadows, enhancing the vivid green backdrop. The overall aesthetic is a realistic, cinematic style, focusing on her expressive delivery within a distinctively lit environment." |
| }, |
| { |
| "reference": { |
| "video_id": "JIk_NQMkTSo", |
| "video_url": "https://www.youtube.com/watch?v=JIk_NQMkTSo", |
| "start_time": 248.43333333333334, |
| "end_time": 253.475, |
| "start_frame": 7453, |
| "end_frame": 7604, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "EPa8LT4KYOc", |
| "video_url": "https://www.youtube.com/watch?v=EPa8LT4KYOc", |
| "start_time": 97.14166666666667, |
| "end_time": 102.18333333333334, |
| "start_frame": 5828, |
| "end_frame": 6131, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A woman with light brown hair and black-rimmed glasses is featured in a medium close-up shot, speaking directly to the camera with an earnest and thoughtful expression. She wears a light blue collared shirt, with a small black microphone clipped to the collar, and occasionally nods her head subtly as she articulates her words. The background is a modern indoor setting, slightly out of focus, revealing a large window on the left with a blurred outdoor view. A tall fiddle-leaf fig plant stands prominently beside the window, while a beige lamp and shelves with decorative items are visible on the right. Soft, natural light streams in from the left, illuminating her face and creating gentle shadows. The overall aesthetic is realistic and clean, conveying a calm and professional atmosphere during daytime." |
| }, |
| { |
| "reference": { |
| "video_id": "bm8EtiaxwGg", |
| "video_url": "https://www.youtube.com/watch?v=bm8EtiaxwGg", |
| "start_time": 557.7237333333334, |
| "end_time": 562.7654, |
| "start_frame": 16715, |
| "end_frame": 16866, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Jrd6POciCBI", |
| "video_url": "https://www.youtube.com/watch?v=Jrd6POciCBI", |
| "start_time": 225.26156666666665, |
| "end_time": 230.3032333333333, |
| "start_frame": 6751, |
| "end_frame": 6902, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A woman with long, dark curly hair and a floral patterned top is centered in a medium close-up shot, speaking directly to the camera. She holds a white spiral-bound notebook in her left hand, displaying handwritten text that reads \"Pillar #2 SEEING Solutions, NOT Problems\" with bullet points below. Her right hand gestures expressively near her head and then points towards the notebook as she articulates her message. Her facial expression is calm and focused, with a direct gaze, conveying an engaging and informative tone. The background is softly blurred, revealing framed artwork and a string instrument, suggesting a warm, indoor environment. Bright, diffused lighting illuminates the scene, creating a clear and inviting atmosphere, typical of a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "NuBZfnA28TM", |
| "video_url": "https://www.youtube.com/watch?v=NuBZfnA28TM", |
| "start_time": 1033.1622666666667, |
| "end_time": 1038.2039333333335, |
| "start_frame": 30964, |
| "end_frame": 31115, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "EfNuvlhHLCA", |
| "video_url": "https://www.youtube.com/watch?v=EfNuvlhHLCA", |
| "start_time": 272.46899999999994, |
| "end_time": 277.5106666666666, |
| "start_frame": 8166, |
| "end_frame": 8317, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, light brown hair, wearing a dark grey t-shirt and a delicate silver necklace, is centered in a medium shot, directly facing the camera. She speaks with a calm and articulate expression, her mouth moving clearly while her head makes subtle, natural movements. The background reveals a bright, modern living room. A large, light-colored sectional sofa, adorned with various throw pillows, occupies the mid-ground, positioned behind a substantial brown leather ottoman. On the white wall behind her, three square mirrors with black grid frames are evenly spaced. A floor lamp with a white shade is visible on the left, and a woven table lamp on the right. The scene is brightly and evenly lit, suggesting daytime, creating soft shadows and a clean, realistic aesthetic. A promotional text overlay is visible at the bottom of the frame." |
| }, |
| { |
| "reference": { |
| "video_id": "zJ84n_d-5rg", |
| "video_url": "https://www.youtube.com/watch?v=zJ84n_d-5rg", |
| "start_time": 1648.9433333333334, |
| "end_time": 1653.9850000000001, |
| "start_frame": 41224, |
| "end_frame": 41350, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "BjVqQCT5rRg", |
| "video_url": "https://www.youtube.com/watch?v=BjVqQCT5rRg", |
| "start_time": 783.74, |
| "end_time": 788.7816666666666, |
| "start_frame": 19594, |
| "end_frame": 19720, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark hair and a white t-shirt with blue lettering is centered in a medium close-up shot, speaking directly to the camera. She stands in an indoor setting, likely a home office or study, with a white bookshelf filled with numerous colorful books visible in the background. To her right, a wall displays various artworks or posters, adding a personal touch to the environment. Her facial expressions are natural and engaging as she articulates words, her mouth moving clearly. She occasionally makes subtle, deliberate gestures with her right hand, emphasizing her points. The lighting is bright and even, casting soft shadows and illuminating her face clearly, suggesting a daytime setting. The overall aesthetic is a realistic cinematic style, capturing a calm and communicative mood." |
| }, |
| { |
| "reference": { |
| "video_id": "WegvQVDewKY", |
| "video_url": "https://www.youtube.com/watch?v=WegvQVDewKY", |
| "start_time": 0.9894583333333333, |
| "end_time": 6.031125, |
| "start_frame": 24, |
| "end_frame": 145, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "jrLymlTBiQU", |
| "video_url": "https://www.youtube.com/watch?v=jrLymlTBiQU", |
| "start_time": 235.98333333333335, |
| "end_time": 241.025, |
| "start_frame": 5900, |
| "end_frame": 6026, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot features a woman with dark skin and long, straight dark hair, looking directly into the camera. She wears a soft grey cardigan over a dark top, her expression calm and engaging as her lips move while speaking. She holds a small black lavalier microphone near her chest with her right hand, occasionally making subtle adjustments. The background reveals a cozy indoor setting, likely a living room. To her right, a white brick fireplace with a dark wooden mantel contains a flickering fire, casting a warm, orange glow. To her left, a white bookshelf is filled with books and decorative items, including a small potted plant and string lights. The lighting is soft and warm, creating an inviting atmosphere. The overall aesthetic is realistic and cinematic, conveying a personal and direct communication style." |
| }, |
| { |
| "reference": { |
| "video_id": "NzZW4t_EewY", |
| "video_url": "https://www.youtube.com/watch?v=NzZW4t_EewY", |
| "start_time": 390.02, |
| "end_time": 395.06166666666667, |
| "start_frame": 9750, |
| "end_frame": 9877, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "kZyy-UoTXjY", |
| "video_url": "https://www.youtube.com/watch?v=kZyy-UoTXjY", |
| "start_time": 1009.5400000000001, |
| "end_time": 1014.5816666666667, |
| "start_frame": 25239, |
| "end_frame": 25365, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a young woman with long, wavy blonde hair, styled with a side part, as she speaks directly into a black microphone. She wears a light blue denim jacket with white stripes on the sleeves and large hoop earrings. Her manicured nails, painted light blue with subtle glitter, grip the microphone firmly. Her lips move articulately as she speaks, her expression thoughtful and earnest. Occasionally, her eyes close briefly or gaze downwards, conveying a sense of introspection or emphasis. The background is a softly lit, minimalist indoor space with a light-colored wall, a glimpse of a white pillow or couch, and a framed abstract artwork visible in the distance. The lighting is bright and even, casting no harsh shadows, creating a clean and calm atmosphere. The overall aesthetic is a realistic, cinematic style, focusing on the subject's communication." |
| }, |
| { |
| "reference": { |
| "video_id": "eaOVlsBmZ-0", |
| "video_url": "https://www.youtube.com/watch?v=eaOVlsBmZ-0", |
| "start_time": 772.2714000000001, |
| "end_time": 777.3130666666667, |
| "start_frame": 23145, |
| "end_frame": 23296, |
| "fps": 29.97002997002997, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "AB5wOBZW22E", |
| "video_url": "https://www.youtube.com/watch?v=AB5wOBZW22E", |
| "start_time": 560.3226666666667, |
| "end_time": 565.3643333333333, |
| "start_frame": 16793, |
| "end_frame": 16944, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Black woman with dark hair neatly pulled back sits facing the camera in a medium close-up shot, positioned at eye level. She wears a long-sleeved brown top, light-colored jeans, and a delicate gold necklace, complemented by subtle makeup and small hoop earrings. To her left, a black metal shelving unit holds clear plastic bins filled with packaged items, one clearly labeled \"boxer.\" The background behind her is a plain, light-colored wall, with additional cardboard boxes visible further back on the right, suggesting a storage or workspace environment. She speaks directly to the viewer, her mouth articulating words and her hands actively gesturing to emphasize her points. Her movements are fluid and expressive, conveying an engaged and confident demeanor. The scene is brightly and evenly lit, creating a clear, realistic, and cinematic aesthetic with minimal shadows." |
| }, |
| { |
| "reference": { |
| "video_id": "U1n-XOtOcAE", |
| "video_url": "https://www.youtube.com/watch?v=U1n-XOtOcAE", |
| "start_time": 1372.1333333333334, |
| "end_time": 1377.1750000000002, |
| "start_frame": 41164, |
| "end_frame": 41315, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "9PzaH5Ar7-A", |
| "video_url": "https://www.youtube.com/watch?v=9PzaH5Ar7-A", |
| "start_time": 255.65833333333333, |
| "end_time": 260.7, |
| "start_frame": 7670, |
| "end_frame": 7821, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A man with dark, neatly styled hair and clear-rimmed glasses is centered in a medium shot, speaking directly to the viewer. He wears a simple grey t-shirt with a dark trim, seated in what appears to be a comfortable, dark-colored chair. Behind him, a floor-to-ceiling wooden bookshelf, brimming with an eclectic array of books in various colors and sizes, creates a rich, academic backdrop. A few small framed pictures and decorative objects are visible among the books. The lighting is soft yet bright, casting a gentle glow on the man's face and the surrounding shelves, suggesting a well-lit indoor setting during the day. He articulates his words clearly, his mouth moving precisely, and uses his right hand to make small, deliberate gestures, emphasizing his points with a calm and focused demeanor. His expression is thoughtful and engaging, conveying an informative tone. The scene has a realistic, cinematic quality, evoking a sense of intellectual discussion." |
| }, |
| { |
| "reference": { |
| "video_id": "0-Cekahx2rw", |
| "video_url": "https://www.youtube.com/watch?v=0-Cekahx2rw", |
| "start_time": 479.58, |
| "end_time": 484.62166666666667, |
| "start_frame": 11990, |
| "end_frame": 12116, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "K2opkhYwGfw", |
| "video_url": "https://www.youtube.com/watch?v=K2opkhYwGfw", |
| "start_time": 408.2983333333333, |
| "end_time": 413.34, |
| "start_frame": 10207, |
| "end_frame": 10334, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A woman with long, reddish-brown hair and bangs is featured in a medium close-up shot, set against a verdant outdoor environment. She wears a beige trench coat over a dark top. The background is a soft blur of green foliage, tall grass, and trees, with scattered autumn leaves visible on the ground to her left, suggesting a park or garden. She holds an open book with a blue spine in her left hand, speaking directly with a focused and somewhat serious expression, her lips moving distinctly. Her hair subtly sways with her movements. As she concludes her thought, her expression shifts to a more determined or slightly exasperated look, and she decisively closes the book, bringing her hands together. The scene is illuminated by soft, natural daylight, casting gentle shadows and contributing to a realistic and calm cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "DAC3YQgLv5E", |
| "video_url": "https://www.youtube.com/watch?v=DAC3YQgLv5E", |
| "start_time": 49.06666666666667, |
| "end_time": 54.108333333333334, |
| "start_frame": 1472, |
| "end_frame": 1623, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "4jIdNRp-Ba8", |
| "video_url": "https://www.youtube.com/watch?v=4jIdNRp-Ba8", |
| "start_time": 665.7, |
| "end_time": 670.7416666666667, |
| "start_frame": 19971, |
| "end_frame": 20122, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures a young woman with short blonde hair and round gold-rimmed glasses, seated in what appears to be a home office or studio. She wears a grey cowl-neck sweater and speaks directly into a dark microphone positioned in front of her. The background features a dark teal wall, a wooden shelf holding various books, a potted plant, and a minimalist white abstract art piece. A bright, soft light illuminates her face from the front, while a strong backlight from the right creates a luminous glow around her hair and highlights a large green plant. Her expression shifts from a calm, conversational tone to one of surprise or emphasis, as her eyes widen dramatically and her mouth opens. She gestures with both hands, moving them up and down to underscore her words. The overall aesthetic is a realistic, well-lit cinematic style, conveying an engaging and direct presentation." |
| }, |
| { |
| "reference": { |
| "video_id": "hXNO-hu6UMM", |
| "video_url": "https://www.youtube.com/watch?v=hXNO-hu6UMM", |
| "start_time": 20.26666666666667, |
| "end_time": 25.308333333333337, |
| "start_frame": 486, |
| "end_frame": 607, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "yNE07q8IdWI", |
| "video_url": "https://www.youtube.com/watch?v=yNE07q8IdWI", |
| "start_time": 24.054166666666664, |
| "end_time": 29.09583333333333, |
| "start_frame": 577, |
| "end_frame": 698, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A cheerful, middle-aged woman with long, wavy blonde hair stands in a bright, modern kitchen, addressing the camera directly. She wears a dark blue apron with red trim over a red top, her expression engaging and enthusiastic with a wide smile and expressive eyes. She actively gestures with both hands, palms open, then bringing them down, as she speaks. Behind her, three large windows offer a view of lush green trees, indicating a daytime setting. The kitchen features white countertops, light gray cabinets, and a white subway tile backsplash. Wooden shelves adorned with various kitchen items flank the windows. On the counter in front of her, several glass jars hold white and pink powders, alongside small white bowls and measuring spoons, suggesting a cooking or baking context. The scene is well-lit by natural daylight, creating a fresh and inviting atmosphere. The shot is a medium close-up, capturing her from the waist up, with a realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "fHh7LYf5sbc", |
| "video_url": "https://www.youtube.com/watch?v=fHh7LYf5sbc", |
| "start_time": 157.59166666666667, |
| "end_time": 162.63333333333333, |
| "start_frame": 4728, |
| "end_frame": 4879, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "h37LKKzlDqI", |
| "video_url": "https://www.youtube.com/watch?v=h37LKKzlDqI", |
| "start_time": 590.5916666666667, |
| "end_time": 595.6333333333333, |
| "start_frame": 17718, |
| "end_frame": 17869, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A woman with dark, curly hair and pink-rimmed glasses sits at a wooden desk, facing the camera in a mid-shot. She wears a grey t-shirt and speaks animatedly into a black microphone positioned directly in front of her. Her hands are active, gesturing to emphasize her words; she points with her right hand and then opens both hands in an explanatory gesture. A blue square graphic with \"charles SCHWAB\" in white text appears on the left side of the frame, overlaying the background. Behind her, a white wall features two abstract yellow and black paintings. To her left, a white door is partially visible, and a red couch with pillows sits further back. To her right, a large computer monitor displays a vibrant blue and orange abstract image, surrounded by desktop icons. A green potted plant is situated between her and the monitor. The scene is brightly lit with soft, even lighting, suggesting daytime indoors. The overall aesthetic is a realistic, cinematic style, capturing a casual yet professional setting." |
| }, |
| { |
| "reference": { |
| "video_id": "AoZbhIncgPs", |
| "video_url": "https://www.youtube.com/watch?v=AoZbhIncgPs", |
| "start_time": 448.6333333333333, |
| "end_time": 453.675, |
| "start_frame": 13459, |
| "end_frame": 13610, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "9nHkY9Ed-SU", |
| "video_url": "https://www.youtube.com/watch?v=9nHkY9Ed-SU", |
| "start_time": 33.675000000000004, |
| "end_time": 38.71666666666667, |
| "start_frame": 2021, |
| "end_frame": 2323, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, flowing brown hair sits comfortably in a light-colored armchair, positioned centrally in a medium shot. She wears a stylish black off-the-shoulder top and a delicate necklace. Her facial expressions are animated and engaging as she speaks directly to the camera, her mouth moving clearly. She frequently gestures with both hands, palms open, adding emphasis to her words. The background features a light blue wall adorned with a patterned quilt in shades of pink, grey, and white on the left. To the right, a wooden bookshelf filled with various books and decorative items creates a cozy, lived-in atmosphere. The lighting is soft and even, illuminating her face without harsh shadows, suggesting a bright indoor setting. Her demeanor is calm and conversational, conveying a sense of pleasant interaction. The overall aesthetic is a realistic, cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "7eWfHDN_DLM", |
| "video_url": "https://www.youtube.com/watch?v=7eWfHDN_DLM", |
| "start_time": 140.61363333333333, |
| "end_time": 145.65529999999998, |
| "start_frame": 4214, |
| "end_frame": 4365, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "v4H247XHKV4", |
| "video_url": "https://www.youtube.com/watch?v=v4H247XHKV4", |
| "start_time": 1145.8112333333336, |
| "end_time": 1150.8529000000003, |
| "start_frame": 34340, |
| "end_frame": 34491, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Black woman with long, dark, wavy hair sits in a bright, modern indoor setting, captured in a medium close-up shot at eye level. She wears a vibrant, multi-colored patterned sundress with thin straps and a delicate silver necklace with a small pendant. Her expression is engaged and communicative, with wide, focused eyes and an open mouth as she speaks directly to the camera. She frequently gestures with her right hand, palm open, to emphasize her points. The background features a clean white wall adorned with a subtle abstract painting in cool tones, a large window with sheer white curtains allowing soft daylight to illuminate the scene, and a portion of a grey upholstered sofa to her right. The lighting is bright and even, suggesting daytime, creating a clear and realistic cinematic aesthetic. Her body language conveys a sense of calm and direct interaction." |
| }, |
| { |
| "reference": { |
| "video_id": "naJ-YOfTBMc", |
| "video_url": "https://www.youtube.com/watch?v=naJ-YOfTBMc", |
| "start_time": 47.641666666666666, |
| "end_time": 52.68333333333333, |
| "start_frame": 1143, |
| "end_frame": 1264, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "mIo0FcJTTPk", |
| "video_url": "https://www.youtube.com/watch?v=mIo0FcJTTPk", |
| "start_time": 20.26666666666667, |
| "end_time": 25.308333333333337, |
| "start_frame": 486, |
| "end_frame": 607, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot frames a middle-aged man with short, dark hair and fair skin, wearing a light blue striped button-up shirt. He stands in an indoor setting, directly addressing the camera with a serious and focused expression, his eyes wide and engaged. His mouth moves articulately as he speaks, and his right hand performs subtle, illustrative gestures near his chest, emphasizing his points. The background features a dark grey wall on the left, partially revealing a television screen and a small decorative item. To the right, a lighter wall includes a prominent white window frame and a modern floor lamp with three glowing, amber-colored light fixtures. Bright, soft lighting illuminates the scene, casting gentle highlights on his face and shirt, indicating a clear daytime setting. The aesthetic is a realistic, cinematic style, presenting a direct and engaging portrait." |
| }, |
| { |
| "reference": { |
| "video_id": "7fmmmnrGyBc", |
| "video_url": "https://www.youtube.com/watch?v=7fmmmnrGyBc", |
| "start_time": 427.15996666666666, |
| "end_time": 432.20163333333335, |
| "start_frame": 12802, |
| "end_frame": 12953, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "m1AQtLfJ1fo", |
| "video_url": "https://www.youtube.com/watch?v=m1AQtLfJ1fo", |
| "start_time": 254.8578, |
| "end_time": 259.8994666666667, |
| "start_frame": 7638, |
| "end_frame": 7789, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot frames a woman with long, dark hair and clear-rimmed glasses, seated comfortably in a black office chair. She wears a dark blue hoodie, her mouth moving as she speaks, her expression transitioning from a gentle, engaging smile to a more focused, thoughtful demeanor. Her head subtly tilts and nods, conveying an active conversational engagement. Behind her, a minimalist home office environment unfolds: a light-colored wall serves as a backdrop, with a dark computer monitor and stacked notebooks visible on a desk to her left. To her right, a tall, dark bookshelf is densely packed with books and small, eclectic figurines. The scene is bathed in bright, even lighting, likely from a soft, diffused source, creating minimal shadows and a clear, realistic cinematic aesthetic, suggesting a calm daytime setting." |
| }, |
| { |
| "reference": { |
| "video_id": "9CGYmmHZq9Q", |
| "video_url": "https://www.youtube.com/watch?v=9CGYmmHZq9Q", |
| "start_time": 23.599999999999998, |
| "end_time": 28.641666666666666, |
| "start_frame": 708, |
| "end_frame": 859, |
| "fps": 30.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "TV57iuR0SdM", |
| "video_url": "https://www.youtube.com/watch?v=TV57iuR0SdM", |
| "start_time": 183.43333333333334, |
| "end_time": 188.475, |
| "start_frame": 5503, |
| "end_frame": 5654, |
| "fps": 30.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A young Asian woman with long, dark hair, wearing a black and grey varsity-style jacket featuring a \"Spotify\" logo, is seated indoors, speaking directly to the camera. She occupies the center of a medium shot, framed at eye level. Her expression is calm and articulate, with a slight smile as she gestures subtly with her right hand. Behind her, a large window reveals a bright blue sky and distant city buildings, bathed in natural daylight. The sunlight streams in, illuminating the room and casting soft shadows. To her left, on the windowsill, a small brown diffuser and a dark candle are visible. A white bed with a rumpled duvet is partially visible in the soft-focus background to her right. The overall aesthetic is a realistic, cinematic style, with clear, bright lighting. Text overlays \"HR RESPONSE/\" and \"HEARD BACK: FEBRUARY 2019\" are present in the upper left and right corners, respectively." |
| }, |
| { |
| "reference": { |
| "video_id": "9-Mye4gs_ok", |
| "video_url": "https://www.youtube.com/watch?v=9-Mye4gs_ok", |
| "start_time": 375.445, |
| "end_time": 380.4866666666667, |
| "start_frame": 18772, |
| "end_frame": 19024, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Wb9zdImZpeI", |
| "video_url": "https://www.youtube.com/watch?v=Wb9zdImZpeI", |
| "start_time": 487.58666666666664, |
| "end_time": 492.62833333333333, |
| "start_frame": 12190, |
| "end_frame": 12316, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, wavy brown hair and a calm, engaging expression speaks directly to the camera in a medium shot. She wears a ribbed beige turtleneck sweater and subtle gold earrings, with a small lavalier microphone clipped to her collar. Her hands are active as she speaks, initially touching her neck and then gesturing outwards with an open palm, emphasizing her words. The background reveals a bright, minimalist indoor setting with light-colored walls. To her right, a wooden-framed mirror reflects a portion of a well-organized closet or wardrobe filled with clothes on hangers and items on shelves, along with a modern, sculptural white light fixture. The lighting is bright and even, creating a clear, realistic cinematic look, suggesting a daytime setting. Her direct gaze and expressive gestures convey a conversational and informative mood." |
| }, |
| { |
| "reference": { |
| "video_id": "9Ylo83ajy8Y", |
| "video_url": "https://www.youtube.com/watch?v=9Ylo83ajy8Y", |
| "start_time": 4.170733333333334, |
| "end_time": 9.2124, |
| "start_frame": 250, |
| "end_frame": 552, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "BwYn4_fGwSI", |
| "video_url": "https://www.youtube.com/watch?v=BwYn4_fGwSI", |
| "start_time": 832.9015666666668, |
| "end_time": 837.9432333333334, |
| "start_frame": 49924, |
| "end_frame": 50226, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a young woman with long, dark, wavy hair and light eyes, wearing a simple white top and gold jewelry, including hoop earrings and bracelets. She sits in a brightly lit, modern indoor setting, with a plush, light beige ribbed sofa and pillows blurred in the background, creating a soft, inviting atmosphere. Her expression is engaged and thoughtful as she speaks, her lips moving fluidly. She raises her right hand to her temple, then spreads both hands outward with open palms, before bringing her right index finger to her temple again, emphasizing her point. The lighting is soft and even, casting minimal shadows and highlighting her features. The overall aesthetic is a realistic, clean cinematic style, focusing on her expressive gestures and communication." |
| }, |
| { |
| "reference": { |
| "video_id": "uX22GilDf8g", |
| "video_url": "https://www.youtube.com/watch?v=uX22GilDf8g", |
| "start_time": 15.251766666666668, |
| "end_time": 20.293433333333336, |
| "start_frame": 457, |
| "end_frame": 608, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "8ZzQCKMRND8", |
| "video_url": "https://www.youtube.com/watch?v=8ZzQCKMRND8", |
| "start_time": 3216.8802333333333, |
| "end_time": 3221.9219, |
| "start_frame": 96410, |
| "end_frame": 96561, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, wavy brown hair sits on the floor in a bright, minimalist living room, facing the camera directly. She wears a cream-colored sweater adorned with a red, black, and white fair isle pattern. Her expression is calm and engaging as she speaks, her mouth moving articulately. She uses subtle hand gestures to emphasize her points, occasionally raising her right hand with an open palm. The background features a light pink sofa with various knitted items and a patterned cushion, along with a light green cabinet holding a small plant and yellow yarn. Three framed pictures adorn the white wall behind her. The scene is evenly lit with soft, natural light, indicating daytime, creating a clear and inviting atmosphere. The shot is a medium close-up, capturing her from the waist up at an eye-level perspective, conveying a direct and personal connection. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "zE3bQWUVT2U", |
| "video_url": "https://www.youtube.com/watch?v=zE3bQWUVT2U", |
| "start_time": 238.0043333333333, |
| "end_time": 243.04599999999996, |
| "start_frame": 5706, |
| "end_frame": 5827, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "DgWEpGgXT_Y", |
| "video_url": "https://www.youtube.com/watch?v=DgWEpGgXT_Y", |
| "start_time": 14.210999999999995, |
| "end_time": 19.252666666666663, |
| "start_frame": 341, |
| "end_frame": 462, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a middle-aged man with neatly styled reddish-brown hair, speaking directly into a microphone positioned just below his chin. He wears a dark brown leather jacket over a black collared shirt. His face is well-lit by bright, direct frontal lighting, casting subtle shadows that define his features. The background is a deep, blurred blue, punctuated by several vertical rows of out-of-focus, glowing blue lights, creating a soft, atmospheric bokeh effect. As he speaks, his mouth articulates clearly, and his head makes subtle, natural movements, occasionally tilting slightly. His expression is calm and engaged, shifting between a thoughtful look and a slight smile, conveying an earnest and articulate demeanor. The overall aesthetic is a realistic, cinematic studio setting, emphasizing the speaker's presence against a minimalist, yet visually interesting backdrop." |
| }, |
| { |
| "reference": { |
| "video_id": "NNS11UeUanI", |
| "video_url": "https://www.youtube.com/watch?v=NNS11UeUanI", |
| "start_time": 1625.5905333333335, |
| "end_time": 1630.6322000000002, |
| "start_frame": 97438, |
| "end_frame": 97740, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "-_uuPMrdok8", |
| "video_url": "https://www.youtube.com/watch?v=-_uuPMrdok8", |
| "start_time": 855.8681, |
| "end_time": 860.9097666666667, |
| "start_frame": 51301, |
| "end_frame": 51603, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long dark hair, wearing a white fluffy sweater and a headband, is centered in a medium shot, speaking directly to the camera. Her face is animated and expressive, conveying excitement and enthusiasm as she talks, with wide eyes and a slight smile. She holds a book titled \"Fourth Wing\" in her left hand, angled towards the viewer. Her right hand actively gestures as she speaks, first pointing upwards with her index finger, then forming a small circle with her thumb and index finger, and finally making a delicate pinching motion. The background features a brightly lit bookshelf filled with numerous books of various sizes and colors, creating a cozy, intellectual atmosphere. The lighting is soft and even, suggesting an indoor setting during the daytime. The overall aesthetic is a realistic, cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "UCIYs_7GC8A", |
| "video_url": "https://www.youtube.com/watch?v=UCIYs_7GC8A", |
| "start_time": 2040.1682666666668, |
| "end_time": 2045.2099333333335, |
| "start_frame": 61144, |
| "end_frame": 61295, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "f26S_H8jkow", |
| "video_url": "https://www.youtube.com/watch?v=f26S_H8jkow", |
| "start_time": 85.34873333333334, |
| "end_time": 90.39040000000001, |
| "start_frame": 2558, |
| "end_frame": 2709, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A bald man with a neatly trimmed beard and clear-framed glasses sits in a medium shot, speaking directly to the camera. He wears a dark blue zippered hoodie over a white t-shirt. His facial expression is animated and engaged as he articulates his thoughts, his mouth moving clearly. Throughout the segment, his right hand gestures expressively, sweeping outwards with an open palm, then bringing his fingers together, emphasizing his points. The background reveals a cozy, well-lit room, likely a home office or study. Tall, dark bookshelves packed with numerous books flank him on both sides, creating a rich, intellectual atmosphere. A vibrant, colorful poster depicting a fantasy or sci-fi scene hangs on the wall behind him, alongside a trailing green plant. The lighting is bright and even, suggesting an indoor setting during the day, with soft shadows. The overall aesthetic is a realistic, cinematic style, capturing a calm and informative mood." |
| }, |
| { |
| "reference": { |
| "video_id": "lf3Vk06wKSo", |
| "video_url": "https://www.youtube.com/watch?v=lf3Vk06wKSo", |
| "start_time": 424.93063333333333, |
| "end_time": 429.9723, |
| "start_frame": 25470, |
| "end_frame": 25773, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "oAndT4Nk3Yw", |
| "video_url": "https://www.youtube.com/watch?v=oAndT4Nk3Yw", |
| "start_time": 410.90691666666663, |
| "end_time": 415.9485833333333, |
| "start_frame": 24630, |
| "end_frame": 24932, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with distinctive two-toned curly hair, blonde on one side and dark brown on the other, sits in a well-lit indoor setting. She wears glasses perched on her head, an orange knitted sweater over a black turtleneck, and a ring on her left hand. Her expression is cheerful and engaging, marked by a wide smile and animated facial movements as she speaks directly to the camera. Her head nods subtly, and her hands make expressive gestures, emphasizing her words. Behind her, a large window reveals an urban background with buildings and a hint of greenery. To her left, an aloe vera plant in a black pot, a black decorative bottle with a crow stopper, and a small white pumpkin rest on a stack of books, adding a cozy, autumnal touch to the scene. The lighting is bright and natural, suggesting daytime, casting soft, even illumination. The overall aesthetic is a realistic, cinematic style, capturing a friendly and conversational mood in a medium shot." |
| }, |
| { |
| "reference": { |
| "video_id": "WSNsCY6lkOM", |
| "video_url": "https://www.youtube.com/watch?v=WSNsCY6lkOM", |
| "start_time": 1235.1037333333336, |
| "end_time": 1240.1454000000003, |
| "start_frame": 37016, |
| "end_frame": 37167, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "9OKGD0f_fcs", |
| "video_url": "https://www.youtube.com/watch?v=9OKGD0f_fcs", |
| "start_time": 105.58193333333334, |
| "end_time": 110.62360000000001, |
| "start_frame": 6329, |
| "end_frame": 6631, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian woman with long, wavy brown hair and bangs, wearing clear-rimmed glasses, a white t-shirt, and an open white button-up shirt, stands in a modern indoor setting. She wears multiple delicate gold necklaces, including one with a heart pendant. The background features a bright, light-colored wall on the left and a darker, neutral-toned wall on the right, with linear ceiling lights visible above. She looks directly at the camera, speaking with a calm and engaged expression. Her mouth moves as she articulates words, and her right hand subtly gestures, briefly touching her shirt before resting. The lighting is bright and even, illuminating her face clearly without harsh shadows, creating a well-lit and inviting atmosphere. The shot is a medium close-up, capturing her upper torso and face from an eye-level perspective, presenting a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "u7gRnJa6ids", |
| "video_url": "https://www.youtube.com/watch?v=u7gRnJa6ids", |
| "start_time": 1090.6895000000002, |
| "end_time": 1095.731166666667, |
| "start_frame": 65376, |
| "end_frame": 65678, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "EOBZXH7SVRY", |
| "video_url": "https://www.youtube.com/watch?v=EOBZXH7SVRY", |
| "start_time": 525.2381833333334, |
| "end_time": 530.27985, |
| "start_frame": 31483, |
| "end_frame": 31785, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with voluminous, tightly coiled, light brown curly hair and dark, expressive eyes is captured in a medium close-up shot, seated in an indoor setting. She wears a soft, textured, beige off-the-shoulder top, revealing her collarbones. The background features a minimalist white wall, with a subtle white picture frame visible in the upper right corner. A white headboard and several light-colored, possibly satin, pillows are visible behind and beside her, indicating a cozy bedroom environment. Her facial expression is thoughtful and composed, conveying a sense of earnestness as she articulates her words, her lips moving distinctly. Her gaze occasionally shifts slightly to the side, then returns to the viewer. The scene is brightly and evenly lit, likely by soft natural light or diffused artificial sources, casting minimal shadows and highlighting her features with a gentle glow. The aesthetic is realistic and cinematic, creating an intimate and reflective mood." |
| }, |
| { |
| "reference": { |
| "video_id": "zKJQFwec_as", |
| "video_url": "https://www.youtube.com/watch?v=zKJQFwec_as", |
| "start_time": 418.1009166666666, |
| "end_time": 423.1425833333333, |
| "start_frame": 10024, |
| "end_frame": 10145, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "CiHQlL-Twd8", |
| "video_url": "https://www.youtube.com/watch?v=CiHQlL-Twd8", |
| "start_time": 70.92075, |
| "end_time": 75.96241666666667, |
| "start_frame": 1700, |
| "end_frame": 1821, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A medium shot captures a woman with long, dark hair, dressed in a vibrant red long-sleeved dress, seated in a modern, brightly lit living room. She wears subtle gold jewelry, including a necklace and earrings, and a small lavalier microphone is clipped to her dress. She holds a wine glass containing a light-colored beverage in her left hand. Her expression is friendly and engaging, with a warm smile as she speaks directly to the camera. She actively gestures with her right hand, emphasizing her words, while her head subtly nods. In the background, two softly lit Christmas trees adorned with warm fairy lights add a festive, cozy atmosphere to the otherwise minimalist white interior, featuring white sofas and clean lines. The lighting is soft and even, suggesting daytime, creating a cheerful and inviting cinematic mood." |
| }, |
| { |
| "reference": { |
| "video_id": "-x2PntEOtQg", |
| "video_url": "https://www.youtube.com/watch?v=-x2PntEOtQg", |
| "start_time": 64.67073333333333, |
| "end_time": 69.7124, |
| "start_frame": 1938, |
| "end_frame": 2089, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "HQUWdUCWeq0", |
| "video_url": "https://www.youtube.com/watch?v=HQUWdUCWeq0", |
| "start_time": 386.0689166666666, |
| "end_time": 391.1105833333333, |
| "start_frame": 9256, |
| "end_frame": 9377, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a man from the chest up, centered against a smooth, warm mustard-yellow background. He has short, dark hair and a neatly trimmed beard, wearing a black t-shirt beneath a light beige, textured cardigan. A ring adorns his left hand, and a watch is visible on his right wrist. The man speaks directly to the camera, his mouth articulating words clearly. He uses expressive hand gestures, opening and closing his palms and moving his hands up and down to emphasize his points, while his head makes subtle, natural movements. His facial expression is calm and engaged, conveying a thoughtful and explanatory demeanor. Soft, even lighting illuminates him from the front, creating minimal shadows and a clear, professional look. The aesthetic is realistic and cinematic, typical of an interview or presentation, with a 'Harvard Business Review' logo subtly placed in the top right corner." |
| }, |
| { |
| "reference": { |
| "video_id": "tnZpBQQv3dg", |
| "video_url": "https://www.youtube.com/watch?v=tnZpBQQv3dg", |
| "start_time": 94.04074999999999, |
| "end_time": 99.08241666666666, |
| "start_frame": 2255, |
| "end_frame": 2376, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "lVn9tQ9fvLQ", |
| "video_url": "https://www.youtube.com/watch?v=lVn9tQ9fvLQ", |
| "start_time": 335.09999999999997, |
| "end_time": 340.14166666666665, |
| "start_frame": 8042, |
| "end_frame": 8163, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot presents a woman with long, dark hair, dressed in a black t-shirt and a silver butterfly necklace, speaking directly to the viewer. She is seated in an office, with a rich wooden bookshelf densely packed with various books forming a prominent background. Below the shelves, light grey filing cabinet drawers are visible, adding to the professional environment. The woman maintains a calm and focused expression, her lips moving articulately as she speaks. She uses her right hand to gesture, making a precise pinching motion with her thumb and index finger, seemingly to illustrate a specific detail or concept. The scene is brightly and evenly lit, suggesting an indoor setting during the day, with soft shadows contributing to a realistic cinematic aesthetic. Her direct gaze and clear communication convey an instructional and engaging mood." |
| }, |
| { |
| "reference": { |
| "video_id": "f6yAY1oZUOA", |
| "video_url": "https://www.youtube.com/watch?v=f6yAY1oZUOA", |
| "start_time": 582.82, |
| "end_time": 587.8616666666667, |
| "start_frame": 14571, |
| "end_frame": 14697, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "8qOMTqedPrk", |
| "video_url": "https://www.youtube.com/watch?v=8qOMTqedPrk", |
| "start_time": 56.74, |
| "end_time": 61.781666666666666, |
| "start_frame": 1418, |
| "end_frame": 1545, |
| "fps": 25.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A middle-aged man with medium-length brown hair and a neatly trimmed grey beard is featured in a medium close-up, speaking directly to the camera. He is dressed in a light blue collared shirt layered under a rich brown corduroy jacket. His facial expression is calm and thoughtful, maintaining a steady, direct gaze, as his mouth articulates words with subtle, natural movements. The indoor setting is softly lit by natural light streaming through a large, multi-paned window behind him. Beyond the window, a blurred backdrop of vibrant green foliage and tree trunks suggests a lush, sunlit outdoor environment. The soft illumination creates gentle highlights on his features and clothing, contributing to a warm and inviting atmosphere. The realistic cinematic style emphasizes his earnest communication." |
| }, |
| { |
| "reference": { |
| "video_id": "yTy8OeCioZg", |
| "video_url": "https://www.youtube.com/watch?v=yTy8OeCioZg", |
| "start_time": 402.6183333333333, |
| "end_time": 407.65999999999997, |
| "start_frame": 10065, |
| "end_frame": 10192, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "wvbfpR7XOwQ", |
| "video_url": "https://www.youtube.com/watch?v=wvbfpR7XOwQ", |
| "start_time": 38.17136666666667, |
| "end_time": 43.213033333333335, |
| "start_frame": 1144, |
| "end_frame": 1295, |
| "fps": 29.97002997002997, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A man with short, dark curly hair and black over-ear headphones stands centered, singing passionately into a sleek silver studio microphone suspended above him. He wears a white polo shirt adorned with a repeating, abstract red and white pattern. His eyes are often closed or half-closed, conveying deep concentration and emotion as his mouth opens and closes with the lyrics. His right hand makes subtle, rhythmic gestures, with fingers gently curling and extending, while his left hand remains slightly lower, also moving with the rhythm. The background is a smooth, gradient warm beige, creating a minimalist and focused studio environment. Soft, diffused lighting illuminates the scene evenly, casting gentle shadows that define his features without harshness. The medium shot, taken from an eye-level perspective, captures his upper torso and the microphone, emphasizing his engaged and calm performance. The aesthetic is realistic and cinematic, highlighting the intimate act of vocal recording." |
| }, |
| { |
| "reference": { |
| "video_id": "ElXfPsnL0Bw", |
| "video_url": "https://www.youtube.com/watch?v=ElXfPsnL0Bw", |
| "start_time": 65.31666666666666, |
| "end_time": 70.35833333333333, |
| "start_frame": 1568, |
| "end_frame": 1689, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "OgqtSEP83NU", |
| "video_url": "https://www.youtube.com/watch?v=OgqtSEP83NU", |
| "start_time": 586.2750000000001, |
| "end_time": 591.3166666666667, |
| "start_frame": 17588, |
| "end_frame": 17740, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with dark hair pulled back into a ponytail and wearing a light grey ribbed t-shirt is centered in a medium close-up shot. She has visible freckles, dark eyebrows, and light eye makeup, accentuated by pink lipstick and gold hoop earrings. She looks directly into the camera with a calm, confident, and engaging expression. Her mouth moves articulately as she speaks, accompanied by subtle, natural head movements that emphasize her words. The background is a bright, minimalist indoor setting with light-colored walls. To the left, a grid of small, framed black and white photos adorns the wall, while a white dresser on the right holds a colorful abstract painting and a decorative item. The scene is brightly and evenly lit, casting soft shadows and creating a clear, realistic cinematic aesthetic, suggesting a well-lit daytime environment." |
| }, |
| { |
| "reference": { |
| "video_id": "q1Vms3_QMpI", |
| "video_url": "https://www.youtube.com/watch?v=q1Vms3_QMpI", |
| "start_time": 5.141666666666667, |
| "end_time": 10.183333333333334, |
| "start_frame": 308, |
| "end_frame": 611, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "O4YQVSEsfwE", |
| "video_url": "https://www.youtube.com/watch?v=O4YQVSEsfwE", |
| "start_time": 11.141666666666667, |
| "end_time": 16.183333333333334, |
| "start_frame": 668, |
| "end_frame": 971, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, straight brown hair and bright blue eyes, centered in the frame. She wears a light green knitted sweater. Her expression is joyful and engaging, with a wide, open-mouthed smile and an enthusiastic gaze directed straight at the viewer. As she speaks, her mouth moves animatedly, and she gestures expressively with both hands, palms open and fingers slightly splayed, moving them up and down in front of her chest. Her head occasionally tilts slightly, adding to her dynamic presentation. The background is a softly blurred home office setting, featuring white bookshelves filled with books and various decorative items, along with a dark desk and computer monitor visible on the left. The lighting is bright and even, illuminating her face without harsh shadows, suggesting a clear daytime setting. The overall aesthetic is a realistic, clean cinematic style, conveying a warm and inviting atmosphere." |
| }, |
| { |
| "reference": { |
| "video_id": "YWMb0Z8OX40", |
| "video_url": "https://www.youtube.com/watch?v=YWMb0Z8OX40", |
| "start_time": 87.80833333333334, |
| "end_time": 92.85000000000001, |
| "start_frame": 2634, |
| "end_frame": 2786, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "vFtD3WTEBQ0", |
| "video_url": "https://www.youtube.com/watch?v=vFtD3WTEBQ0", |
| "start_time": 15.024999999999999, |
| "end_time": 20.066666666666666, |
| "start_frame": 451, |
| "end_frame": 602, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with long, wavy blonde hair and bright red lipstick, seated in a home library or office. She wears a dark green sweater adorned with a subtle pattern and a delicate gold pendant necklace. Her gaze is direct and engaging, looking straight into the camera as she speaks, her mouth articulating words clearly. She occasionally gestures with her hands, adding emphasis to her speech. Behind her, two tall, white bookshelves are meticulously filled with a vibrant array of books, organized by color, creating a rich, textured backdrop. A small stack of books rests on a surface to her right. The lighting is bright and even, suggesting an indoor setting with soft, diffused light that minimizes harsh shadows. Her expression is calm and friendly, conveying an approachable and conversational mood. The overall aesthetic is a realistic, cinematic portrayal of a personal space." |
| }, |
| { |
| "reference": { |
| "video_id": "xYAm0r6Qs34", |
| "video_url": "https://www.youtube.com/watch?v=xYAm0r6Qs34", |
| "start_time": 69.50266666666667, |
| "end_time": 74.54433333333334, |
| "start_frame": 1666, |
| "end_frame": 1787, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "fF8X5_-mJ5k", |
| "video_url": "https://www.youtube.com/watch?v=fF8X5_-mJ5k", |
| "start_time": 1112.743125, |
| "end_time": 1117.7847916666667, |
| "start_frame": 26679, |
| "end_frame": 26800, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, dark hair and subtle makeup, wearing a black collared shirt and a delicate gold necklace. She occupies the center of the frame, speaking directly to the viewer. Her facial expressions shift from a thoughtful, slightly pensive look with a subtle head tilt to a broad, engaging smile, conveying a conversational and approachable mood. In the background, a bright, organized indoor setting is visible. White bookshelves filled with a diverse collection of books line the wall behind her, creating a colorful backdrop. To the right, a dark blue sofa is partially visible, with a black dog peacefully sleeping on it. Two colorful posters adorn the wall above the sofa. The scene is evenly lit with soft, diffused light, casting minimal shadows and creating a clear, realistic cinematic aesthetic, suggesting a bright daytime environment." |
| }, |
| { |
| "reference": { |
| "video_id": "dTL2NCZlIU0", |
| "video_url": "https://www.youtube.com/watch?v=dTL2NCZlIU0", |
| "start_time": 657.6, |
| "end_time": 662.6416666666667, |
| "start_frame": 15782, |
| "end_frame": 15903, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "MKs6Hjm3g8s", |
| "video_url": "https://www.youtube.com/watch?v=MKs6Hjm3g8s", |
| "start_time": 720.8083333333334, |
| "end_time": 725.85, |
| "start_frame": 17299, |
| "end_frame": 17420, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with light brown hair and glasses sits in a medium shot, facing the camera within a brightly lit indoor setting. She wears a dark grey hoodie with \"SAN DIEGO\" emblazoned across the chest and a small black microphone clipped to it. Behind her, a white bookshelf filled with numerous books and decorative items stands against a light-colored wall, adorned with a green vine garland. To her right, a dark television screen rests on a wooden cabinet. The woman actively gestures with her hands as she speaks, initially pointing with her right index finger, then spreading both palms outward, and subsequently bringing them together in a series of fluid, expressive motions. Her facial expressions are calm and engaged, conveying a sense of articulate explanation. The scene is illuminated by soft, even daylight, casting minimal shadows and contributing to a clear, realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "eQ3vNdhZYXw", |
| "video_url": "https://www.youtube.com/watch?v=eQ3vNdhZYXw", |
| "start_time": 279.4816666666666, |
| "end_time": 284.5233333333333, |
| "start_frame": 13974, |
| "end_frame": 14226, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "WAIS4kO61a4", |
| "video_url": "https://www.youtube.com/watch?v=WAIS4kO61a4", |
| "start_time": 409.95635, |
| "end_time": 414.9980166666667, |
| "start_frame": 24573, |
| "end_frame": 24875, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot frames a man with short dark hair, dressed in a cream cable-knit sweater, seated against a vibrant backdrop of bookshelves. The shelves are meticulously arranged, displaying a diverse collection of books with colorful spines and decorative covers, creating a rich, textured environment. The man is actively speaking, his mouth forming words, and his eyes occasionally glance downwards before returning to an engaged, direct gaze. His facial expression is calm and conversational, conveying a sense of thoughtful communication. Soft, even lighting illuminates the scene, casting no harsh shadows and highlighting the realistic textures of his sweater and the book spines. A glimpse of a soft blue blanket or pillow is visible to his right, adding a subtle touch of domesticity. The overall aesthetic is a realistic, cinematic portrayal of an individual sharing thoughts in a personal, book-filled space." |
| }, |
| { |
| "reference": { |
| "video_id": "QaEo5y1IdkM", |
| "video_url": "https://www.youtube.com/watch?v=QaEo5y1IdkM", |
| "start_time": 525.5916333333333, |
| "end_time": 530.6333, |
| "start_frame": 15752, |
| "end_frame": 15903, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "YLTE8vraQP0", |
| "video_url": "https://www.youtube.com/watch?v=YLTE8vraQP0", |
| "start_time": 803.8696333333334, |
| "end_time": 808.9113, |
| "start_frame": 24092, |
| "end_frame": 24243, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark hair and a light-colored knitted sweater sits in a well-lit indoor setting, speaking directly to the camera. She wears a delicate necklace with a small pendant. Her facial expressions are animated and engaged as she articulates words, with her mouth moving continuously. Her hands make subtle, expressive gestures to emphasize her points. Behind her, a tall white bookshelf is packed with numerous colorful books, creating a vibrant backdrop. To her right, a cozy, light-colored armchair holds two plush toys: a white, ghost-like figure and a black and orange pumpkin. The lighting is soft and even, casting no harsh shadows, suggesting a bright daytime or professionally lit environment. The shot is a medium close-up, capturing her upper torso and the immediate surroundings, presented in a realistic cinematic style. Her demeanor is calm and friendly, conveying an informative and conversational tone." |
| }, |
| { |
| "reference": { |
| "video_id": "HVB36ll6-T8", |
| "video_url": "https://www.youtube.com/watch?v=HVB36ll6-T8", |
| "start_time": 322.47535, |
| "end_time": 327.5170166666667, |
| "start_frame": 19329, |
| "end_frame": 19631, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "0zHQ-XyZSFU", |
| "video_url": "https://www.youtube.com/watch?v=0zHQ-XyZSFU", |
| "start_time": 609.4253833333333, |
| "end_time": 614.46705, |
| "start_frame": 36529, |
| "end_frame": 36831, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young person with short, dark hair and clear-rimmed glasses is centered in a medium close-up shot, speaking directly to the camera. They wear a maroon hoodie and have a calm, conversational expression, with their mouth moving as they talk and their head occasionally shifting slightly. The background features two tall, light-colored wooden bookshelves filled with numerous books of various colors, creating a cozy, intellectual atmosphere. A white ghost-shaped mug sits on the left shelf, and a dark, industrial-style lamp is visible on the shelf behind their head. On the right side of the frame, a book cover titled \"A Talent for Murder\" by Peter Swanson, featuring a red background with blood splatters, is digitally superimposed. The scene is brightly and evenly lit, suggesting an indoor daytime setting with a realistic cinematic aesthetic. The overall mood is informative and engaging." |
| }, |
| { |
| "reference": { |
| "video_id": "NZoGRM6pDSU", |
| "video_url": "https://www.youtube.com/watch?v=NZoGRM6pDSU", |
| "start_time": 840.485, |
| "end_time": 845.5266666666666, |
| "start_frame": 42024, |
| "end_frame": 42276, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "FnTLwvl0Ngg", |
| "video_url": "https://www.youtube.com/watch?v=FnTLwvl0Ngg", |
| "start_time": 1262.6416666666669, |
| "end_time": 1267.6833333333336, |
| "start_frame": 63132, |
| "end_frame": 63384, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with light brown hair and round glasses sits in a brightly lit room, facing the camera in a medium shot. She wears a white t-shirt featuring a colorful \"LEVI STRAUSS & CO.\" logo. Behind her, white bookshelves are densely packed with numerous books and various decorative objects, including plush toys and small figurines. To her right, a beige three-tiered rolling cart is also filled with books. The woman speaks directly to the viewer, her mouth moving articulately. She uses expressive hand gestures, bringing her hands together in front of her chest, then spreading them wide, and then clasping them again, emphasizing her words. Her facial expression is friendly and engaged, with a slight smile, conveying a calm and approachable demeanor. The lighting is soft and even, illuminating the scene clearly, suggesting a daytime setting. The overall aesthetic is a realistic, cinematic portrayal of a casual indoor setting." |
| }, |
| { |
| "reference": { |
| "video_id": "D1OKFdgxRNA", |
| "video_url": "https://www.youtube.com/watch?v=D1OKFdgxRNA", |
| "start_time": 252.27833333333334, |
| "end_time": 257.32, |
| "start_frame": 12614, |
| "end_frame": 12866, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "FkKuRh4Omwk", |
| "video_url": "https://www.youtube.com/watch?v=FkKuRh4Omwk", |
| "start_time": 384.23999999999995, |
| "end_time": 389.28166666666664, |
| "start_frame": 19212, |
| "end_frame": 19464, |
| "fps": 50.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A bald man with a grey beard and black-rimmed glasses sits at a dark desk, directly addressing the camera. He wears a plain black t-shirt. The background is a dimly lit studio space, featuring soft blue and warm orange accent lights that create a dramatic, professional atmosphere. A key light illuminates the man's face, casting subtle shadows that define his features. He actively gestures with his hands as he speaks, initially spreading his palms wide in an open, explanatory manner. He then brings his hands together, pressing his palms and fingers, before making small, precise movements to emphasize his words. His mouth is open, conveying active speech, and his expression is focused and communicative, suggesting he is explaining a concept or providing instructions. The shot is a medium close-up, capturing his upper torso and hands, emphasizing his gestures and facial expressions. The aesthetic is realistic and cinematic, with sharp focus and controlled lighting." |
| }, |
| { |
| "reference": { |
| "video_id": "jRjVW16ZS3Y", |
| "video_url": "https://www.youtube.com/watch?v=jRjVW16ZS3Y", |
| "start_time": 514.7666666666667, |
| "end_time": 519.8083333333333, |
| "start_frame": 15443, |
| "end_frame": 15594, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "e4ywBfDAiAc", |
| "video_url": "https://www.youtube.com/watch?v=e4ywBfDAiAc", |
| "start_time": 234.18, |
| "end_time": 239.22166666666666, |
| "start_frame": 5854, |
| "end_frame": 5981, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with dark skin and long, dark braided hair, styled in two pigtails, is centered in a medium close-up shot. She wears a light pink sleeveless top and a delicate gold necklace, with subtle makeup highlighting her eyes and lips. She speaks directly to the camera, her lips articulating words, and frequently smiles, revealing her teeth. Her head occasionally tilts, and her hands make subtle, expressive gestures, moving up and outwards as she talks. Her expression is engaging and friendly, conveying a calm and approachable demeanor. The background features two framed posters depicting cosmic and urban scenes, a white YouTube play button plaque, and a stack of books. The wall behind her is bathed in a vibrant purple ambient light, contrasting with the bright front lighting on her face. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "BH712Lzts5Q", |
| "video_url": "https://www.youtube.com/watch?v=BH712Lzts5Q", |
| "start_time": 543.625, |
| "end_time": 548.6666666666666, |
| "start_frame": 16309, |
| "end_frame": 16460, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "mfll_jh8NKs", |
| "video_url": "https://www.youtube.com/watch?v=mfll_jh8NKs", |
| "start_time": 327.46666666666664, |
| "end_time": 332.5083333333333, |
| "start_frame": 9824, |
| "end_frame": 9975, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark, curly hair and stylish gold-rimmed glasses, featuring purple-tinted lenses, is seated in a bright, minimalist bedroom. She wears a form-fitting, long-sleeved light green athletic top and matching leggings, accented by distinctive white fluffy cuffs on her wrists. The background reveals a crisp white wall, a large bed with pristine white bedding, and dark wooden furniture, including a wardrobe and a headboard. To her right, a large mirror framed with lights reflects a partial view of the room. The woman faces the camera directly, speaking with an engaged and confident expression. Her mouth is open as she articulates words, and her right hand gestures subtly downwards and forward, emphasizing her points before retracting. The scene is illuminated by soft, even natural light, likely from an unseen window, casting minimal shadows and creating a clean, realistic cinematic aesthetic. Her direct gaze and expressive body language convey an informative and assured demeanor." |
| }, |
| { |
| "reference": { |
| "video_id": "Vo6mv8OGCXs", |
| "video_url": "https://www.youtube.com/watch?v=Vo6mv8OGCXs", |
| "start_time": 647.9138333333333, |
| "end_time": 652.9554999999999, |
| "start_frame": 15534, |
| "end_frame": 15655, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "TYItz3wOO28", |
| "video_url": "https://www.youtube.com/watch?v=TYItz3wOO28", |
| "start_time": 399.2487499999999, |
| "end_time": 404.2904166666666, |
| "start_frame": 9572, |
| "end_frame": 9693, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a man with short, styled brown hair and light stubble, wearing a brown polo shirt. He sits facing the camera, making direct eye contact with a calm and engaging expression as he speaks. His mouth moves clearly, and he frequently uses hand gestures, bringing his hands together and apart in front of him to emphasize his points. The background is a softly blurred modern interior, featuring a light wooden bookshelf filled with books and decorative items, including a framed picture and a green plant. A large, abstract artwork with teal and dark blue tones is visible on the wall behind him. The lighting is bright and even, casting soft shadows and creating a clean, professional aesthetic. The overall style is realistic and cinematic, focusing on the speaker in a well-composed indoor setting." |
| }, |
| { |
| "reference": { |
| "video_id": "l1c5RfkvDJ4", |
| "video_url": "https://www.youtube.com/watch?v=l1c5RfkvDJ4", |
| "start_time": 262.5955666666666, |
| "end_time": 267.6372333333333, |
| "start_frame": 7870, |
| "end_frame": 8021, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "DRxWFLB3XZU", |
| "video_url": "https://www.youtube.com/watch?v=DRxWFLB3XZU", |
| "start_time": 201.30429999999998, |
| "end_time": 206.34596666666664, |
| "start_frame": 6033, |
| "end_frame": 6184, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Black woman is captured in a medium close-up shot, standing outdoors against the backdrop of a beige mobile home. The residence features distinctive red shutters on its windows and a white door to the right. She wears a black headband, a dark long-sleeved shirt, and a cozy, two-tone fuzzy jacket in shades of pink and light pink. Her long, straight dark hair frames her face, falling over her shoulders. She maintains direct eye contact with the camera, speaking articulately with a calm and engaged expression, her mouth moving and head nodding subtly as she conveys her message. The scene is bathed in bright, natural daylight, casting soft, defined shadows and highlighting the vibrant green grass in the foreground. Distant trees are visible under a clear, expansive blue sky, contributing to a realistic cinematic aesthetic set during midday or early afternoon. Her demeanor appears thoughtful and communicative." |
| }, |
| { |
| "reference": { |
| "video_id": "LVPqMjwMoTE", |
| "video_url": "https://www.youtube.com/watch?v=LVPqMjwMoTE", |
| "start_time": 718.8129583333333, |
| "end_time": 723.8546249999999, |
| "start_frame": 17234, |
| "end_frame": 17355, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "kGOCI73G4ho", |
| "video_url": "https://www.youtube.com/watch?v=kGOCI73G4ho", |
| "start_time": 1149.1494583333333, |
| "end_time": 1154.191125, |
| "start_frame": 27552, |
| "end_frame": 27673, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with dark hair, dressed in a black sleeveless top, stands centrally in a brightly lit, minimalist room, captured in a medium shot from the waist up. She maintains direct eye contact with the viewer, her expression animated and engaging. Her background features a clean white wall adorned with an eclectic arrangement of framed artwork, including a vintage-style painting and several botanical prints. She holds a small black microphone to her mouth with her right hand while her left hand gestures expressively, emphasizing her words with fluid movements. Her facial expression conveys enthusiasm and confidence as she speaks. The lighting is soft and even, illuminating the scene without harsh shadows, creating a clear and inviting atmosphere. A white sofa with plush pillows is partially visible in the lower left foreground, adding to the cozy, domestic setting. The overall aesthetic is a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "TRNvdYCMbwU", |
| "video_url": "https://www.youtube.com/watch?v=TRNvdYCMbwU", |
| "start_time": 307.6833333333333, |
| "end_time": 312.72499999999997, |
| "start_frame": 7384, |
| "end_frame": 7505, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "mIYGeOUlnIw", |
| "video_url": "https://www.youtube.com/watch?v=mIYGeOUlnIw", |
| "start_time": 481.0471333333333, |
| "end_time": 486.0888, |
| "start_frame": 14417, |
| "end_frame": 14568, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian woman with long, dark hair and a light blue long-sleeved top is centered in a mid-shot, looking directly at the camera. She wears a delicate gold necklace with a small green pendant. Her expression is calm and articulate as she speaks, her lips moving clearly and her head making subtle, natural movements. The background reveals a modern, well-lit apartment interior. To her left, a white brick wall features two framed abstract artworks in warm tones, above a light gray sofa with patterned cushions. To her right, a contemporary kitchen area is visible, featuring dark countertops, wooden upper cabinets, and stainless steel appliances like a refrigerator and microwave. A wooden dining table with chairs is partially seen on the far right. The lighting is bright and even, suggesting daytime, creating a clear and realistic cinematic aesthetic. The overall mood is professional and engaging." |
| }, |
| { |
| "reference": { |
| "video_id": "XEmWV6t4TwE", |
| "video_url": "https://www.youtube.com/watch?v=XEmWV6t4TwE", |
| "start_time": 108.59166666666668, |
| "end_time": 113.63333333333335, |
| "start_frame": 5430, |
| "end_frame": 5682, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "ypGyTUoACDw", |
| "video_url": "https://www.youtube.com/watch?v=ypGyTUoACDw", |
| "start_time": 1320.38, |
| "end_time": 1325.4216666666669, |
| "start_frame": 66019, |
| "end_frame": 66271, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark hair and a black sleeveless top sits in a bright, modern room, facing the camera. She speaks into a prominent black microphone positioned directly in front of her. Behind her, large windows reveal a blurred city skyline under a clear sky, with a stark white wall to her left. To her right, a white flip chart stands, displaying the word \"GOALS\" written in bold red capital letters. She maintains eye contact with the camera, her expression calm and engaging, with a slight smile. Her hands rest on a table, occasionally making subtle, expressive gestures as she articulates her words. The scene is bathed in soft, natural daylight, creating a clean and professional aesthetic. The medium shot captures her upper body, conveying a direct and approachable tone in a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "RmZXBI64tTE", |
| "video_url": "https://www.youtube.com/watch?v=RmZXBI64tTE", |
| "start_time": 502.67499999999995, |
| "end_time": 507.71666666666664, |
| "start_frame": 15080, |
| "end_frame": 15232, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "cRppwIaR3pA", |
| "video_url": "https://www.youtube.com/watch?v=cRppwIaR3pA", |
| "start_time": 829.3000000000001, |
| "end_time": 834.3416666666667, |
| "start_frame": 24879, |
| "end_frame": 25030, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark, wavy hair and a ribbed olive green t-shirt occupies the center of a medium close-up shot. She sits in a brightly lit, minimalist bedroom, characterized by white walls, a white bed with crisp linens, and a modern white chair visible in the background. A light-colored desk with a monitor is partially seen on the left, while a tall, dark floor lamp stands near the bed on the right. The woman speaks directly to the camera, her mouth articulating words, and her eyes occasionally glance upwards as if in thought or recollection. Her expression appears reflective and earnest. Strong natural light streams in from the right side of the frame, creating distinct shadows and highlights across the room and on her face, suggesting a clear daytime setting. The overall aesthetic is realistic and clean, with a calm, intimate atmosphere." |
| }, |
| { |
| "reference": { |
| "video_id": "Xuf4w17b2L0", |
| "video_url": "https://www.youtube.com/watch?v=Xuf4w17b2L0", |
| "start_time": 273.24787499999996, |
| "end_time": 278.28954166666665, |
| "start_frame": 6551, |
| "end_frame": 6672, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "eH5QAdnVWsc", |
| "video_url": "https://www.youtube.com/watch?v=eH5QAdnVWsc", |
| "start_time": 51.623374999999996, |
| "end_time": 56.66504166666666, |
| "start_frame": 1238, |
| "end_frame": 1359, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A young woman with long, wavy brown hair and bangs sits on the floor, facing the camera in a medium close-up shot. She wears a crisp white collared shirt layered under a dark grey cable-knit vest. Her expression is calm and pleasant, with a gentle smile playing on her lips as she speaks, her eyes engaging directly with the viewer. She occasionally blinks and makes subtle head movements, conveying an approachable demeanor. The background features a tastefully decorated room with deep olive green walls. To her left, a dark brown leather armchair is draped with a plaid blanket, next to a small side table with books. On her right, a dark metal bookshelf holds various items, including a vintage film reel. Framed artwork adorns the wall behind her. Soft, warm ambient light illuminates the scene, creating a cozy and inviting atmosphere, characteristic of a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "heT5cCRJgHs", |
| "video_url": "https://www.youtube.com/watch?v=heT5cCRJgHs", |
| "start_time": 979.65, |
| "end_time": 984.6916666666666, |
| "start_frame": 29390, |
| "end_frame": 29541, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "8pJt9VzAMUQ", |
| "video_url": "https://www.youtube.com/watch?v=8pJt9VzAMUQ", |
| "start_time": 716.5333333333333, |
| "end_time": 721.5749999999999, |
| "start_frame": 21496, |
| "end_frame": 21647, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Black woman with short, blonde, curly hair and white earbuds is centered in a medium close-up shot, speaking directly to the camera. She wears a black turtleneck under a beige tweed-like jacket, exuding a chic and composed demeanor. Her lips move expressively as she talks, and her head bobs slightly, conveying an engaging and cheerful mood. A warm smile plays on her face, reflecting confidence and approachability. The background reveals a bright, modern bathroom with light-colored walls. To the left, a brown, clear-pocketed toiletry bag hangs on a white door, filled with various items. Behind her, a dark-framed shower stall is visible, and a large window on the right allows ample natural light to flood the scene, creating a clear, well-lit atmosphere with soft shadows. The overall aesthetic is a realistic, cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "L8TrMiaNlzM", |
| "video_url": "https://www.youtube.com/watch?v=L8TrMiaNlzM", |
| "start_time": 1231.3333333333335, |
| "end_time": 1236.3750000000002, |
| "start_frame": 36940, |
| "end_frame": 37091, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "y5Kcn1C-DKA", |
| "video_url": "https://www.youtube.com/watch?v=y5Kcn1C-DKA", |
| "start_time": 607.5666666666667, |
| "end_time": 612.6083333333333, |
| "start_frame": 14582, |
| "end_frame": 14703, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a middle-aged man with neatly styled, salt-and-pepper hair and a well-groomed, short beard, set against an entirely dark, minimalist background. He is dressed in a dark, textured collared shirt, suggesting a casual yet professional demeanor. Soft, directional key lighting illuminates his face from the front-left, creating subtle highlights on his forehead and cheekbones, while gentle shadows define the contours of his jawline and neck. His eyes, a warm brown, are bright and engaged, looking slightly off-camera to the right. As he speaks, his mouth forms a genuine, open-mouthed smile, revealing his teeth and conveying a friendly, approachable expression. His head makes subtle, natural movements, emphasizing his calm and engaged communication. The realistic cinematic style focuses intimately on his expressive face, creating an atmosphere of direct and personal interaction within a controlled studio environment." |
| }, |
| { |
| "reference": { |
| "video_id": "KEoiCXMgRHU", |
| "video_url": "https://www.youtube.com/watch?v=KEoiCXMgRHU", |
| "start_time": 425.90037499999994, |
| "end_time": 430.9420416666666, |
| "start_frame": 10211, |
| "end_frame": 10332, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "X87Q05jOjcY", |
| "video_url": "https://www.youtube.com/watch?v=X87Q05jOjcY", |
| "start_time": 84.185375, |
| "end_time": 89.22704166666666, |
| "start_frame": 2018, |
| "end_frame": 2139, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young East Asian woman with shoulder-length dark brown hair and a light blue ribbed v-neck top is framed in a medium close-up shot. She looks directly into the camera, speaking with subtle, natural head movements and articulate mouth gestures. Her face features light makeup, including soft blush and a muted pink lip color, contributing to a composed and engaging expression. The background is softly blurred, revealing a warm, inviting indoor environment. To the left, a glass door or window shows distant, out-of-focus city lights, suggesting an evening or nighttime setting. On the right, a minimalist floor lamp with a glowing Edison-style bulb casts a warm, soft glow. The overall lighting is dim but warm, creating gentle shadows that subtly define her facial contours. The aesthetic is realistic and cinematic, conveying a personal and direct address to the viewer in a cozy, intimate atmosphere." |
| }, |
| { |
| "reference": { |
| "video_id": "FUKTjbW1qFo", |
| "video_url": "https://www.youtube.com/watch?v=FUKTjbW1qFo", |
| "start_time": 11.508299999999998, |
| "end_time": 16.549966666666666, |
| "start_frame": 345, |
| "end_frame": 496, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "sx2ghcP61qk", |
| "video_url": "https://www.youtube.com/watch?v=sx2ghcP61qk", |
| "start_time": 406.35999999999996, |
| "end_time": 411.40166666666664, |
| "start_frame": 20318, |
| "end_frame": 20570, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young East Asian man with short dark hair and round glasses sits at a clean white desk in a brightly lit, modern indoor setting. He wears a casual grey t-shirt with a small black microphone clipped to the collar. The background features blurred shelves filled with various objects, including camera lenses, bottles, and a white pegboard with hanging items, suggesting a tech or creative studio environment. The man looks directly at the camera, speaking calmly and informatively. His hands are active, holding a small, cylindrical white and red device. He demonstrates its function by twisting or pulling a part of the object with his fingers, his movements precise and deliberate. Several other tech gadgets, including camera lenses, wireless earbuds, and a small yellow and black device, are neatly arranged on the desk in front of him. The lighting is bright and even, casting soft shadows and contributing to a clean, professional aesthetic. The shot is a medium close-up, capturing his upper body and the immediate desk area." |
| }, |
| { |
| "reference": { |
| "video_id": "mKbvJoVNe98", |
| "video_url": "https://www.youtube.com/watch?v=mKbvJoVNe98", |
| "start_time": 85.9, |
| "end_time": 90.94166666666668, |
| "start_frame": 2577, |
| "end_frame": 2728, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "CGujnKm-c-w", |
| "video_url": "https://www.youtube.com/watch?v=CGujnKm-c-w", |
| "start_time": 172.425, |
| "end_time": 177.46666666666667, |
| "start_frame": 5173, |
| "end_frame": 5324, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian man with short dark hair and gold-rimmed glasses sits in a medium shot, facing the camera directly. He wears a black t-shirt and a dark wristwatch. The background reveals a warm, inviting indoor setting with a light-colored sofa on the left and dark brown curtains on the right. A glowing lamp casts soft, warm light, creating a cozy atmosphere. The man actively gestures with his hands as he speaks, his mouth moving in sync with his words. He raises his right index finger to emphasize a point, then brings his hands together, rubbing his palms. His facial expression is animated and engaged, conveying a sense of explanation or discussion, with a brief, subtle smile appearing. The lighting suggests an evening or nighttime scene, contributing to a realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "87Lm2uU1iDc", |
| "video_url": "https://www.youtube.com/watch?v=87Lm2uU1iDc", |
| "start_time": 456.32499999999993, |
| "end_time": 461.3666666666666, |
| "start_frame": 13690, |
| "end_frame": 13841, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "x8FOIwoZCnI", |
| "video_url": "https://www.youtube.com/watch?v=x8FOIwoZCnI", |
| "start_time": 85.29833333333333, |
| "end_time": 90.34, |
| "start_frame": 2132, |
| "end_frame": 2258, |
| "fps": 25.0, |
| "width": 1280, |
| "height": 720 |
| }, |
| "target_caption": "A young Asian man, dressed in a black polo shirt with green and white trim, sits centrally in a grey office chair, addressing the camera directly. He maintains a calm and informative expression, articulating words with clear mouth movements and occasionally making subtle, illustrative gestures with his right hand. The background features a plain light grey wall, with a dark bookshelf partially visible on the left, holding a violin case and various colorful folders. The shot is a medium close-up, captured from an eye-level perspective. Bright, even lighting illuminates the scene, casting soft, minimal shadows and creating a clean, professional aesthetic, indicative of daytime. A static white text overlay occupies the bottom left of the frame, displaying \"Bill Gates\" and \"Bill & Melinda Gates Foundation Trust.\" The overall aesthetic is realistic and modern, conveying a focused and engaging presentation." |
| }, |
| { |
| "reference": { |
| "video_id": "i5cn9xdWOzA", |
| "video_url": "https://www.youtube.com/watch?v=i5cn9xdWOzA", |
| "start_time": 512.5666666666667, |
| "end_time": 517.6083333333333, |
| "start_frame": 15377, |
| "end_frame": 15528, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "2Lv9OhESpw0", |
| "video_url": "https://www.youtube.com/watch?v=2Lv9OhESpw0", |
| "start_time": 230.62499999999997, |
| "end_time": 235.66666666666663, |
| "start_frame": 13837, |
| "end_frame": 14140, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young East Asian woman, with long, straight dark hair and wearing a black dress adorned with small red floral patterns, is featured in a medium close-up shot. She looks directly into the camera, articulating words with a calm and focused expression. Her mouth moves continuously as she speaks, while her head remains mostly still, with subtle, natural shifts. The background reveals a brightly lit, modern indoor setting with a minimalist aesthetic. A white wall, a light grey sofa with a patterned cushion, and a tall, arched floor lamp are visible on the left. To the right, a white floating shelf unit displays various small bottles and decorative items, alongside a neat stack of books. Chinese characters appear as an overlay on the lower part of the screen. The scene is illuminated by soft, even daylight, creating minimal shadows and contributing to the realistic cinematic style, conveying an informative and composed mood." |
| }, |
| { |
| "reference": { |
| "video_id": "Se9LvevEpZU", |
| "video_url": "https://www.youtube.com/watch?v=Se9LvevEpZU", |
| "start_time": 29.591666666666665, |
| "end_time": 34.63333333333333, |
| "start_frame": 888, |
| "end_frame": 1039, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "gi_FY6GL6yo", |
| "video_url": "https://www.youtube.com/watch?v=gi_FY6GL6yo", |
| "start_time": 293.525, |
| "end_time": 298.56666666666666, |
| "start_frame": 8806, |
| "end_frame": 8957, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures a bald man with round, dark-rimmed glasses, wearing a casual green t-shirt, seated inside a vehicle. He maintains direct eye contact with the camera, speaking with a calm and composed demeanor, his mouth articulating words clearly. Subtle hand gestures accompany his speech. The car's interior, featuring dark upholstery, is visible around him, with a bright window on the left revealing the exterior. Beyond the window, a sun-drenched, rural landscape unfolds, characterized by expansive dry, golden fields and scattered green trees under a clear, bright sky, indicating a daytime setting. White and yellow Chinese text overlays appear dynamically at the top and bottom of the frame, providing additional information. The scene is bathed in bright, natural daylight, casting soft illumination on the man's face and contributing to a realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "c-X8DJye6Gw", |
| "video_url": "https://www.youtube.com/watch?v=c-X8DJye6Gw", |
| "start_time": 214.99166666666667, |
| "end_time": 220.03333333333333, |
| "start_frame": 12900, |
| "end_frame": 13202, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "rQfXYQPYzC8", |
| "video_url": "https://www.youtube.com/watch?v=rQfXYQPYzC8", |
| "start_time": 0.1, |
| "end_time": 5.141666666666667, |
| "start_frame": 3, |
| "end_frame": 154, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian man with short dark hair and glasses is featured in a medium close-up shot, looking directly at the camera with a calm and engaging expression. He wears a light blue denim jacket over a white t-shirt, and his mouth articulates as he speaks. The background reveals a brightly lit indoor setting with white walls and a white pegboard adorned with various small items, including a red box and a purple game controller. A computer monitor displaying a vibrant red and black abstract image is visible behind him, slightly out of focus. The lighting is soft and even, illuminating his face without harsh shadows, suggesting a well-lit room during the day. The overall aesthetic is realistic and cinematic, focusing on the subject's direct address to the viewer." |
| }, |
| { |
| "reference": { |
| "video_id": "rkjLBr2ULcw", |
| "video_url": "https://www.youtube.com/watch?v=rkjLBr2ULcw", |
| "start_time": 63.70346666666667, |
| "end_time": 68.74513333333334, |
| "start_frame": 1909, |
| "end_frame": 2060, |
| "fps": 29.97002997002997, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "Cy_H9evyz3o", |
| "video_url": "https://www.youtube.com/watch?v=Cy_H9evyz3o", |
| "start_time": 98.01760000000002, |
| "end_time": 103.05926666666669, |
| "start_frame": 2938, |
| "end_frame": 3089, |
| "fps": 29.97002997002997, |
| "width": 3840, |
| "height": 2026 |
| }, |
| "target_caption": "A medium close-up shot frames a young East Asian man from the chest up, positioned in a warm, inviting indoor environment. He has neatly styled black hair and wears modern, clear-framed glasses, complementing his black t-shirt. A small, black lavalier microphone is discreetly clipped to his shirt collar. The man's gaze is directed slightly off-camera to the right, and his mouth moves articulately as he speaks, conveying a thoughtful and composed expression. Behind him, soft, light-colored curtains provide a gentle backdrop, with hints of upholstered furniture or a sofa visible, adding to the cozy atmosphere. The scene is illuminated by soft, warm artificial lighting, creating a pleasant glow that highlights his features and casts subtle, natural shadows. The aesthetic style is realistic and cinematic, presenting a clear and engaging portrait of the speaker." |
| }, |
| { |
| "reference": { |
| "video_id": "25bZ2U_23Ag", |
| "video_url": "https://www.youtube.com/watch?v=25bZ2U_23Ag", |
| "start_time": 65.5687, |
| "end_time": 70.61036666666668, |
| "start_frame": 1965, |
| "end_frame": 2116, |
| "fps": 29.97002997002997, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "RrMGGPGkXeY", |
| "video_url": "https://www.youtube.com/watch?v=RrMGGPGkXeY", |
| "start_time": 770.7031666666667, |
| "end_time": 775.7448333333333, |
| "start_frame": 23098, |
| "end_frame": 23249, |
| "fps": 29.97002997002997, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A young East Asian man with short dark hair and glasses is centered in a medium shot, presenting a black mirrorless camera. He wears a light beige hoodie featuring a distinctive yellow graphic. He holds the camera in his left hand, angling it slightly towards the viewer, while his right hand gestures with an extended index finger, pointing towards the device. His facial expression is engaged and communicative as he speaks, conveying an informative tone. The background reveals a modern indoor setting with large windows draped in sheer white curtains, offering a blurred view of lush greenery outside. To the right, a wooden cabinet holds decorative items and a small potted plant. The foreground displays additional camera lenses and another camera body on a light-colored surface. The scene is bathed in bright, soft, diffused lighting, suggesting daytime, creating a clean and professional cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "RNmFk0ETNb4", |
| "video_url": "https://www.youtube.com/watch?v=RNmFk0ETNb4", |
| "start_time": 277.64166666666665, |
| "end_time": 282.68333333333334, |
| "start_frame": 16658, |
| "end_frame": 16961, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "Vl8YgqkaFWU", |
| "video_url": "https://www.youtube.com/watch?v=Vl8YgqkaFWU", |
| "start_time": 851.0833333333334, |
| "end_time": 856.125, |
| "start_frame": 51065, |
| "end_frame": 51368, |
| "fps": 60.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A young Asian woman with shoulder-length dark hair and bangs sits at a polished wooden desk, engaging the viewer with her speech. She wears a crisp white sleeveless top, a delicate necklace with a small black microphone clipped on, and subtle gold bracelets. Her hands are clasped together on the desk, occasionally shifting slightly as she articulates her thoughts, her facial expressions animated and thoughtful. The background is softly lit with light blue curtains, creating a serene backdrop. To her left, a stack of books and a small potted cactus are neatly arranged. On her right, a sleek black PlayStation 2 console stands prominently, its logo glowing faintly blue, beside a vibrant pink and blue neon \"GAME\" sign. The scene is bathed in soft, diffused light, giving it a clean, modern, and inviting cinematic aesthetic. The medium shot captures her upper torso and the well-arranged desk, conveying a calm and friendly mood." |
| }, |
| { |
| "reference": { |
| "video_id": "xAkJPHEzWVE", |
| "video_url": "https://www.youtube.com/watch?v=xAkJPHEzWVE", |
| "start_time": 88.35000000000001, |
| "end_time": 93.39166666666668, |
| "start_frame": 2120, |
| "end_frame": 2241, |
| "fps": 24.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "qLjT5IXauZo", |
| "video_url": "https://www.youtube.com/watch?v=qLjT5IXauZo", |
| "start_time": 406.55833333333334, |
| "end_time": 411.6, |
| "start_frame": 9757, |
| "end_frame": 9878, |
| "fps": 24.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A well-groomed East Asian man, appearing to be in his middle age, is captured in a medium close-up shot, speaking directly to the viewer. He wears a cream-colored long-sleeve shirt with a subtle logo and a gold bracelet on his left wrist. His dark hair is neatly styled. The man's expression is calm and focused as he articulates words, his mouth moving precisely. He actively gestures with his right hand, moving it up and down in a deliberate, illustrative manner, as if explaining a concept or demonstrating a progression. The background is a softly blurred, warm-toned bookshelf filled with numerous books and decorative objects, suggesting a cozy, intellectual home environment. Soft, natural light illuminates the scene, casting gentle shadows and highlighting his features. The overall aesthetic is a realistic, high-definition cinematic style, conveying an engaging and informative mood." |
| }, |
| { |
| "reference": { |
| "video_id": "URMWUzGqekc", |
| "video_url": "https://www.youtube.com/watch?v=URMWUzGqekc", |
| "start_time": 430.5583333333333, |
| "end_time": 435.59999999999997, |
| "start_frame": 12917, |
| "end_frame": 13068, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "jEMFwc_5y4U", |
| "video_url": "https://www.youtube.com/watch?v=jEMFwc_5y4U", |
| "start_time": 721.0166666666668, |
| "end_time": 726.0583333333334, |
| "start_frame": 21631, |
| "end_frame": 21782, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with long, straight brown hair, wearing a black long-sleeved top, standing in a brightly lit, modern kitchen. The background features sleek white cabinets and a built-in oven, suggesting a clean and contemporary domestic setting. She stands behind a counter, with a bright neon yellow plastic bag visible in the lower right corner. The woman is actively speaking, her mouth forming words, and she uses expressive hand gestures to emphasize her points. Her hands move fluidly, opening and closing, palms facing upwards, then bringing her fingertips together. Her facial expression is focused and engaged, conveying a sense of explanation or instruction. The lighting is even and soft, illuminating the scene without harsh shadows, creating a clear and realistic cinematic aesthetic. The overall mood is calm and informative." |
| }, |
| { |
| "reference": { |
| "video_id": "Diurj6LdWGc", |
| "video_url": "https://www.youtube.com/watch?v=Diurj6LdWGc", |
| "start_time": 297.97499999999997, |
| "end_time": 303.01666666666665, |
| "start_frame": 8939, |
| "end_frame": 9090, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "nmW_CrGtiq8", |
| "video_url": "https://www.youtube.com/watch?v=nmW_CrGtiq8", |
| "start_time": 680.6666666666667, |
| "end_time": 685.7083333333334, |
| "start_frame": 20420, |
| "end_frame": 20571, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young Asian woman with long, dark hair, styled with a middle part, is featured in a medium close-up shot, speaking directly to the camera. She wears a striped green and white button-up shirt over a black top. The indoor setting reveals a light wooden door frame on the left and warm-toned wooden cabinets or shelves in the softly blurred background on the right, suggesting a home or office environment. She begins by gesturing with her right hand, then briefly closes her eyes with a thoughtful expression before opening them again, maintaining a calm and articulate demeanor as she continues to speak. Her mouth moves continuously, conveying a clear sense of explanation or instruction. Bright, soft lighting illuminates her from the front, creating a clear and inviting mood. The aesthetic is realistic and cinematic, enhanced by a brown text box with white Chinese characters in the top left and white Chinese subtitles at the bottom of the frame." |
| }, |
| { |
| "reference": { |
| "video_id": "BuV6PHPsPEY", |
| "video_url": "https://www.youtube.com/watch?v=BuV6PHPsPEY", |
| "start_time": 685.3974333333334, |
| "end_time": 690.4391, |
| "start_frame": 20541, |
| "end_frame": 20692, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "1buXSV8zJJo", |
| "video_url": "https://www.youtube.com/watch?v=1buXSV8zJJo", |
| "start_time": 961.4604, |
| "end_time": 966.5020666666667, |
| "start_frame": 28815, |
| "end_frame": 28966, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures a young East Asian woman in a brightly lit indoor setting. She has shoulder-length dark hair and wears a white cardigan over a vibrant pink top, accessorized with small gold earrings. Her gaze is directed straight at the camera, and her lips move as she speaks, conveying a calm and engaging demeanor. Subtle head movements accompany her speech, and she blinks naturally. The background is simple, featuring a light-colored wall and a dark door on the right, while a bed with a pink and white checkered blanket is partially visible on the left. Soft, even front lighting illuminates the scene, creating a clear and inviting atmosphere without harsh shadows. A stylized white speech bubble with black outlines and pink Chinese characters appears on the left side of the frame, adding a graphic element to the realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "3IIgPEBPYms", |
| "video_url": "https://www.youtube.com/watch?v=3IIgPEBPYms", |
| "start_time": 428.25833333333327, |
| "end_time": 433.29999999999995, |
| "start_frame": 12848, |
| "end_frame": 12999, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "H5s_BpN_fxI", |
| "video_url": "https://www.youtube.com/watch?v=H5s_BpN_fxI", |
| "start_time": 354.4916666666666, |
| "end_time": 359.5333333333333, |
| "start_frame": 10635, |
| "end_frame": 10786, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with long, dark hair, wearing a lustrous olive-green satin top and a long, dark beaded necklace. She sits comfortably on a light-colored, patterned couch, positioned in front of a rich, dark wooden bookshelf filled with books. To her left, a glowing white neon sign spells out \"Stacey.\" The lighting is soft and warm, casting gentle highlights on her hair and clothing, suggesting an indoor, cozy atmosphere. She speaks directly to the camera, her mouth forming words, and her right hand occasionally lifts to make subtle gestures, emphasizing her points. Her facial expressions shift from thoughtful and engaged to a slight, pleasant smile towards the end, conveying a calm and approachable demeanor. The overall aesthetic is realistic and cinematic, with clear focus on the subject." |
| }, |
| { |
| "reference": { |
| "video_id": "NR_GsgxqZx0", |
| "video_url": "https://www.youtube.com/watch?v=NR_GsgxqZx0", |
| "start_time": 285.79999999999995, |
| "end_time": 290.84166666666664, |
| "start_frame": 8574, |
| "end_frame": 8725, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "j8l3kDwG_a8", |
| "video_url": "https://www.youtube.com/watch?v=j8l3kDwG_a8", |
| "start_time": 675.825, |
| "end_time": 680.8666666666667, |
| "start_frame": 20275, |
| "end_frame": 20426, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a cheerful East Asian woman against a plain white background, creating a clean, minimalist scene. She has dark, wavy hair pulled back, revealing pearl drop earrings, and wears a black dress adorned with vibrant red and green floral patterns, complemented by a delicate gold necklace. Her face is framed centrally, and she smiles warmly, looking directly into the camera with a friendly and welcoming expression. Her lips move subtly as she speaks, conveying a sense of direct communication. The lighting is bright and even, likely from the front, casting soft, minimal shadows and suggesting an indoor daytime setting. On the right side of the frame, red Chinese characters appear, along with the English text \"Diane in Paris\" and a small golden bell icon. Below her, in the bottom left corner, \"Diane in Paris\" is also displayed in blue and red text. The overall aesthetic is a realistic, clean cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "ybf7reEgsD8", |
| "video_url": "https://www.youtube.com/watch?v=ybf7reEgsD8", |
| "start_time": 468.3666666666666, |
| "end_time": 473.4083333333333, |
| "start_frame": 14051, |
| "end_frame": 14202, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "LqN7HKs_xAI", |
| "video_url": "https://www.youtube.com/watch?v=LqN7HKs_xAI", |
| "start_time": 2479.108333333333, |
| "end_time": 2484.1499999999996, |
| "start_frame": 74373, |
| "end_frame": 74524, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures a woman with long, dark hair, seated in a black office chair, speaking directly to the camera. She wears a light pink, collared jacket over a beige shirt. Her mouth moves as she articulates words, maintaining a calm and engaged expression with a direct gaze. The indoor setting features a wooden bookshelf packed with various books and some boxes on the right side of the frame. An air conditioner is mounted high above the bookshelf. To the left, a light-colored woven screen or room divider adds texture to the background. The scene is brightly and evenly lit, casting soft shadows and creating a clear, realistic cinematic aesthetic. Chinese text overlays are visible in the upper left corner of the frame." |
| }, |
| { |
| "reference": { |
| "video_id": "34wSzXgmBrk", |
| "video_url": "https://www.youtube.com/watch?v=34wSzXgmBrk", |
| "start_time": 1289.341666666667, |
| "end_time": 1294.3833333333337, |
| "start_frame": 32234, |
| "end_frame": 32360, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "kWQsFuwZGJA", |
| "video_url": "https://www.youtube.com/watch?v=kWQsFuwZGJA", |
| "start_time": 560.5400000000001, |
| "end_time": 565.5816666666667, |
| "start_frame": 14014, |
| "end_frame": 14140, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a young woman speaking directly to the camera in a well-lit, cozy living room. She has dark hair and wears a dark grey sweatshirt with subtle gold jewelry, including a circular pendant necklace and hoop earrings. Her expression is calm and engaging as she articulates words, her mouth moving subtly. The background reveals a classic white fireplace mantelpiece on the left, with a dark, empty grate below. To the right, a tall wooden bookshelf filled with books is visible, and further right, a vibrant pink sofa with colorful cushions adds a pop of color. A green ottoman sits in the foreground. Overlaid on the lower right of the screen is a graphic of a white seesaw, with a red '6' on the left side and a green '2' on the right, indicating an imbalance. The scene is bathed in bright, natural daylight, suggesting daytime, with soft, even lighting. The overall aesthetic is realistic and cinematic, typical of a personal vlog." |
| }, |
| { |
| "reference": { |
| "video_id": "KhBWw11iL-4", |
| "video_url": "https://www.youtube.com/watch?v=KhBWw11iL-4", |
| "start_time": 835.5083333333333, |
| "end_time": 840.55, |
| "start_frame": 25065, |
| "end_frame": 25216, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "GOO6hSeWzxE", |
| "video_url": "https://www.youtube.com/watch?v=GOO6hSeWzxE", |
| "start_time": 567.4166666666666, |
| "end_time": 572.4583333333333, |
| "start_frame": 17022, |
| "end_frame": 17174, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, flowing dark brown hair and a light-colored, striped top is positioned centrally in a medium close-up shot. She smiles broadly and speaks directly to the viewer, her mouth articulating words clearly, and her head nodding gently with enthusiasm. Her eyes are bright and friendly, conveying a cheerful and engaging demeanor. Behind her, a well-organized white bookshelf spans the entire background, densely packed with a diverse collection of books in various sizes and vibrant colors, creating a rich, academic atmosphere. The scene is brightly and evenly lit, casting soft illumination on her face and suggesting a clear, indoor daytime setting. To the right, a static graphic overlay showcases the cover of a book titled \"DREADFUL\" by Caitlin Rozakis, featuring a striking gothic design in red, black, and white, with intricate scrollwork. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "0Loy3Hbb3u8", |
| "video_url": "https://www.youtube.com/watch?v=0Loy3Hbb3u8", |
| "start_time": 1599.6778333333336, |
| "end_time": 1604.7195000000004, |
| "start_frame": 47942, |
| "end_frame": 48093, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "s-7x6HVEog4", |
| "video_url": "https://www.youtube.com/watch?v=s-7x6HVEog4", |
| "start_time": 1152.0841666666668, |
| "end_time": 1157.1258333333335, |
| "start_frame": 34528, |
| "end_frame": 34679, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark, wavy hair and light eyes sits comfortably on a beige couch in a bright, minimalist room. She wears a simple white tank top and loose beige pants, with small hoop earrings and a ring on her right hand. The background features a plain light gray wall, a bed with white bedding to the left, and several potted green plants, including a large Monstera deliciosa on the right. She maintains direct eye contact with the camera, speaking calmly and expressively, using subtle hand gestures with her right hand to emphasize her words. Her mouth moves clearly as she articulates. The scene is bathed in soft, natural daylight, casting gentle shadows and highlighting a clean, modern aesthetic. The medium shot captures her from the waist up, conveying a relaxed and conversational mood." |
| }, |
| { |
| "reference": { |
| "video_id": "iJmMWiN8Q00", |
| "video_url": "https://www.youtube.com/watch?v=iJmMWiN8Q00", |
| "start_time": 497.92499999999995, |
| "end_time": 502.96666666666664, |
| "start_frame": 14938, |
| "end_frame": 15089, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "OsuelhkdEBU", |
| "video_url": "https://www.youtube.com/watch?v=OsuelhkdEBU", |
| "start_time": 1399.4750000000001, |
| "end_time": 1404.5166666666669, |
| "start_frame": 41984, |
| "end_frame": 42136, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with short brown hair, wearing a grey turtleneck sweater, seated comfortably in a dark armchair. She is positioned slightly to the left of the frame, facing forward and speaking directly to the viewer. Her hands are clasped and she gestures subtly as she talks, her mouth moving articulately. Her expression is calm and engaged, conveying a sense of thoughtful discussion. The background features a muted green wall with a window partially visible on the left, showing white blinds. To the right, a dark side table holds a golden floor lamp, casting a warm glow. An overlaid graphic of a book cover titled \"JAMES\" by Percival Everett occupies the right third of the screen. The lighting is soft and even, creating a realistic and inviting cinematic aesthetic, suggesting a daytime indoor setting." |
| }, |
| { |
| "reference": { |
| "video_id": "bZnt-JbyVWw", |
| "video_url": "https://www.youtube.com/watch?v=bZnt-JbyVWw", |
| "start_time": 469.3354333333333, |
| "end_time": 474.3771, |
| "start_frame": 14066, |
| "end_frame": 14217, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "absE2CAUgus", |
| "video_url": "https://www.youtube.com/watch?v=absE2CAUgus", |
| "start_time": 1501.1965, |
| "end_time": 1506.2381666666668, |
| "start_frame": 44991, |
| "end_frame": 45142, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, dark brown hair, wearing a light brown turtleneck sweater and a subtle nose ring. She looks directly at the camera, speaking with a calm and engaged expression, her mouth moving articulately. Her eyes occasionally shift slightly as she talks. Behind her, a festive Christmas tree, adorned with various ornaments including red ribbons, golden baubles, and small gnome figures, fills the central background. To the left, a bright window or balcony door allows natural daylight to stream in, illuminating the scene and creating soft highlights on her face. A small plant on a table is visible near the window. To the right, a teal bookshelf filled with board games like \"Catan\" and \"Ticket to Ride\" adds a touch of color and personal detail to the indoor setting. The overall lighting is bright and natural, suggesting daytime, contributing to a warm and inviting atmosphere. The aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "Em7fFsxhz4A", |
| "video_url": "https://www.youtube.com/watch?v=Em7fFsxhz4A", |
| "start_time": 363.09596666666664, |
| "end_time": 368.1376333333333, |
| "start_frame": 10882, |
| "end_frame": 11033, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "iCp6p6xrB6A", |
| "video_url": "https://www.youtube.com/watch?v=iCp6p6xrB6A", |
| "start_time": 243.07296666666667, |
| "end_time": 248.11463333333333, |
| "start_frame": 7285, |
| "end_frame": 7436, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with blonde hair and visible arm tattoos sits comfortably in a patterned armchair, enveloped in a soft, light-colored blanket. She wears a black off-shoulder top adorned with colorful floral patterns and a golden leaf pendant necklace. Behind her, a wall of white bookshelves is densely packed with various books, some featuring intricate covers, interspersed with decorative string lights that cast a warm, inviting glow. The woman holds a book titled \"The Starless Sea\" in her left hand, while her right hand gestures animatedly as she speaks directly to the camera. Her expression is joyful and enthusiastic, marked by a wide, genuine smile and bright eyes. The medium shot, taken at eye level, captures her engaging demeanor and the cozy, book-filled atmosphere, illuminated by soft, warm light that highlights the textures of the books and the string lights. The overall aesthetic is realistic and cinematic, typical of a personal vlog." |
| }, |
| { |
| "reference": { |
| "video_id": "KfyPr7MFlUg", |
| "video_url": "https://www.youtube.com/watch?v=KfyPr7MFlUg", |
| "start_time": 536.6495833333333, |
| "end_time": 541.69125, |
| "start_frame": 12867, |
| "end_frame": 12988, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "RznkTvIdMBE", |
| "video_url": "https://www.youtube.com/watch?v=RznkTvIdMBE", |
| "start_time": 2.0250000000000004, |
| "end_time": 7.066666666666667, |
| "start_frame": 61, |
| "end_frame": 212, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark hair and a nose piercing sits in a black gaming chair, facing the camera directly. She wears a black long-sleeved top and a choker necklace. Her expression is calm and engaging, with a slight smile as she speaks. In her right hand, she holds a small, bright pink, cylindrical object, which she subtly gestures with as she talks. The background features a white bookshelf filled with numerous books of various colors on the left, and a plain white door with a silver handle on the right. The room is brightly and evenly lit, suggesting an indoor setting during the daytime. The shot is a medium close-up, capturing her from the chest up, at an eye-level perspective. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "GcOWWHiOUN4", |
| "video_url": "https://www.youtube.com/watch?v=GcOWWHiOUN4", |
| "start_time": 278.14133333333325, |
| "end_time": 283.18299999999994, |
| "start_frame": 6669, |
| "end_frame": 6790, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "o4MW25Ub94I", |
| "video_url": "https://www.youtube.com/watch?v=o4MW25Ub94I", |
| "start_time": 687.9783333333334, |
| "end_time": 693.02, |
| "start_frame": 17199, |
| "end_frame": 17326, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with short, dark hair and bright red lipstick, wearing a deep red vest over a light pink ruffled blouse. She stands in a brightly lit indoor setting, likely a creative studio or workshop. In the soft-focus background, a warm wooden screen with ornate cutouts and a beige mannequin are visible to her left. To her right, shelves display green plants, and two white sewing machines rest on a desk, hinting at a crafting environment. The woman looks directly at the camera with a cheerful, engaging smile, her eyes sparkling with enthusiasm. She speaks animatedly, her mouth moving clearly, and her hands gesture expressively at chest level, palms facing upwards, emphasizing her points. Her confident body language and lively facial expressions convey a friendly and inviting demeanor. The lighting is bright and even, casting no harsh shadows, contributing to a clear and realistic cinematic aesthetic." |
| }, |
| { |
| "reference": { |
| "video_id": "rOZlSKE5odQ", |
| "video_url": "https://www.youtube.com/watch?v=rOZlSKE5odQ", |
| "start_time": 228.70337499999997, |
| "end_time": 233.74504166666662, |
| "start_frame": 5483, |
| "end_frame": 5604, |
| "fps": 23.976023976023978, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "bziXNEAPzlE", |
| "video_url": "https://www.youtube.com/watch?v=bziXNEAPzlE", |
| "start_time": 142.21833333333336, |
| "end_time": 147.26000000000002, |
| "start_frame": 3555, |
| "end_frame": 3682, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a cheerful woman with brown hair and bangs, pulled back into a ponytail, speaking directly to the camera in a brightly lit indoor setting. She wears a vibrant blue and purple patterned button-up shirt. Her expression is animated, featuring a wide smile that briefly closes her eyes before they open again, conveying enthusiasm. She gestures expressively with her hands, bringing them together in a gentle clapping motion before separating them as she speaks. The background features a white bookshelf filled with books and a small potted succulent, alongside a lush green plant to the right. A window with vertical blinds on the left provides ample natural light, illuminating the scene with a soft, even glow, suggesting daytime. The overall aesthetic is a realistic, clean cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "sUamaIHoE5k", |
| "video_url": "https://www.youtube.com/watch?v=sUamaIHoE5k", |
| "start_time": 728.5777499999999, |
| "end_time": 733.6194166666666, |
| "start_frame": 17468, |
| "end_frame": 17589, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "T1Jt8J9DwJ0", |
| "video_url": "https://www.youtube.com/watch?v=T1Jt8J9DwJ0", |
| "start_time": 742.9807083333333, |
| "end_time": 748.0223749999999, |
| "start_frame": 17814, |
| "end_frame": 17935, |
| "fps": 23.976023976023978, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A young woman with dark hair and fair skin is captured in a medium close-up, seated indoors against a backdrop of soft, warm-toned pillows and a patterned couch. She wears a mustard yellow knit cardigan, revealing a black strap, and accessorizes with a chunky silver chain necklace and large, round earrings. Her dark hair is styled with a decorative clip on the right side. She holds a black vintage-style camcorder in her left hand, its lens pointed slightly downwards. Throughout the segment, she gestures expressively with her right hand, pointing directly towards the viewer and then making a circular motion. Her facial expressions are animated and engaging, with direct eye contact and subtle head movements, conveying a sense of lively communication and emphasis. The lighting is soft and diffused, casting gentle shadows and contributing to a cozy, intimate atmosphere. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "PSeIPlLFhjo", |
| "video_url": "https://www.youtube.com/watch?v=PSeIPlLFhjo", |
| "start_time": 915.3166666666667, |
| "end_time": 920.3583333333333, |
| "start_frame": 21968, |
| "end_frame": 22089, |
| "fps": 24.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target": { |
| "video_id": "0Up_-i1mfyg", |
| "video_url": "https://www.youtube.com/watch?v=0Up_-i1mfyg", |
| "start_time": 512.1833333333334, |
| "end_time": 517.225, |
| "start_frame": 12292, |
| "end_frame": 12413, |
| "fps": 24.0, |
| "width": 3840, |
| "height": 2160 |
| }, |
| "target_caption": "A medium shot captures a man with short brown hair and a light grey t-shirt, positioned centrally, speaking directly into a black microphone. He stands in an indoor setting, likely a home office or studio, with dark walls and two wooden shelves behind him. The shelves display various items: a green potted plant, a framed map, a silver YouTube play button, a small white airplane model, a framed photo, and a stack of books. The man's facial expressions are animated and engaged, conveying enthusiasm as he articulates his words. He frequently uses expressive hand gestures, moving his hands up and down and outward to emphasize points. Bright, even lighting illuminates his face, creating a clear and professional look, while a subtle blue light emanates from the lower left, adding a touch of atmosphere to the dark background. The overall aesthetic is a realistic, cinematic style, focusing on clear communication." |
| }, |
| { |
| "reference": { |
| "video_id": "ntVbDoSKW78", |
| "video_url": "https://www.youtube.com/watch?v=ntVbDoSKW78", |
| "start_time": 603.375, |
| "end_time": 608.4166666666666, |
| "start_frame": 18101, |
| "end_frame": 18252, |
| "fps": 30.0, |
| "width": 2560, |
| "height": 1440 |
| }, |
| "target": { |
| "video_id": "WgTYbwaEEdE", |
| "video_url": "https://www.youtube.com/watch?v=WgTYbwaEEdE", |
| "start_time": 0.1, |
| "end_time": 5.141666666666667, |
| "start_frame": 3, |
| "end_frame": 154, |
| "fps": 30.0, |
| "width": 2560, |
| "height": 1440 |
| }, |
| "target_caption": "A medium close-up shot frames a middle-aged Asian man speaking directly to the camera, positioned in a parking lot. He wears a black t-shirt and has short dark hair, his mouth moving actively as he converses with a calm and neutral expression. Behind him, a large, modern Costco Wholesale store dominates the background, its grey corrugated metal facade featuring the prominent red and blue Costco logo. Several cars are parked in the foreground and mid-ground, partially visible. The sky above is bright with scattered white clouds, indicating a clear day. The scene is bathed in bright, natural daylight, casting soft shadows and creating an even, realistic cinematic look, likely set during midday or early afternoon. The overall atmosphere is bright and open." |
| }, |
| { |
| "reference": { |
| "video_id": "GJVaBtzKDr8", |
| "video_url": "https://www.youtube.com/watch?v=GJVaBtzKDr8", |
| "start_time": 111.41743333333334, |
| "end_time": 116.4591, |
| "start_frame": 6678, |
| "end_frame": 6981, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "grRPSgV4bqo", |
| "video_url": "https://www.youtube.com/watch?v=grRPSgV4bqo", |
| "start_time": 20.26666666666667, |
| "end_time": 25.308333333333337, |
| "start_frame": 607, |
| "end_frame": 758, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot captures an Asian man in his 30s or 40s, positioned centrally against a plain light grey wall. He has short dark hair, wears round spectacles, and is dressed in a black zip-up jacket over a black t-shirt, with a small black lavalier microphone clipped to his jacket. His expression is serious and focused, with slightly furrowed brows, as he speaks directly to the camera. Throughout the segment, his mouth moves continuously, articulating words. His right hand frequently rises into the frame, performing expressive gestures; it opens wide with splayed fingers, then closes partially, moving up and down to emphasize his speech. The lighting is bright and even, casting minimal shadows, suggesting a well-lit indoor environment. A vibrant, multi-colored graphic logo is visible in the top left corner. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "gw2U-Z3Q8IA", |
| "video_url": "https://www.youtube.com/watch?v=gw2U-Z3Q8IA", |
| "start_time": 207.38333333333333, |
| "end_time": 212.42499999999998, |
| "start_frame": 6222, |
| "end_frame": 6373, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "_tf2AHglCyU", |
| "video_url": "https://www.youtube.com/watch?v=_tf2AHglCyU", |
| "start_time": 13.533333333333333, |
| "end_time": 18.575, |
| "start_frame": 406, |
| "end_frame": 557, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, dark hair and a light brown, textured top is centered in a medium close-up shot, speaking directly to the camera. She has a pleasant and engaged expression, with subtle movements of her head and expressive hand gestures as she articulates words. Her eyes blink naturally, conveying a sense of calm and focus. The background reveals a cozy living room setting, featuring teal curtains on the left and a dark wooden door on the right. A window beyond the door shows glimpses of green foliage, suggesting a daytime scene with ample natural light. Patterned sofas with cushions are visible on either side, adding to the domestic atmosphere. The lighting is soft and even, casting gentle shadows and highlighting her features. The overall aesthetic is realistic and cinematic, capturing a direct and personal interaction." |
| }, |
| { |
| "reference": { |
| "video_id": "OZu9jIA8JeE", |
| "video_url": "https://www.youtube.com/watch?v=OZu9jIA8JeE", |
| "start_time": 490.6583333333333, |
| "end_time": 495.7, |
| "start_frame": 24533, |
| "end_frame": 24785, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1074 |
| }, |
| "target": { |
| "video_id": "q4ISMYGjGoI", |
| "video_url": "https://www.youtube.com/watch?v=q4ISMYGjGoI", |
| "start_time": 97.16000000000001, |
| "end_time": 102.20166666666668, |
| "start_frame": 4858, |
| "end_frame": 5110, |
| "fps": 50.0, |
| "width": 1920, |
| "height": 1074 |
| }, |
| "target_caption": "A young man with dark hair and a focused expression sits at a desk, engaging directly with the camera in a medium shot. He wears a black jacket over a light blue collared shirt, with a blue lanyard visible. His hands are actively gesturing as he speaks, emphasizing his points with subtle movements and a slight head nod. The background features a warm peach-colored wall, creating a soft, inviting atmosphere. To his left, a stack of books, a pink teddy bear, and a calculator are neatly arranged on the desk, suggesting a study or office environment. The lighting is bright and even, casting minimal shadows and highlighting the man's features. The overall aesthetic is realistic and cinematic, conveying a sense of direct communication and instruction. The scene is calm and focused, with the man's body language indicating a thoughtful and informative demeanor." |
| }, |
| { |
| "reference": { |
| "video_id": "hCVjBduQC54", |
| "video_url": "https://www.youtube.com/watch?v=hCVjBduQC54", |
| "start_time": 460.59336666666667, |
| "end_time": 465.63503333333335, |
| "start_frame": 13804, |
| "end_frame": 13955, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "haK-WQyq63I", |
| "video_url": "https://www.youtube.com/watch?v=haK-WQyq63I", |
| "start_time": 257.65729999999996, |
| "end_time": 262.69896666666665, |
| "start_frame": 7722, |
| "end_frame": 7873, |
| "fps": 29.97002997002997, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A confident woman with blonde highlights and red lipstick sits in a plush, light-colored armchair, addressing the camera directly. She wears a dark blue ribbed dress, a gold necklace, and earrings, with her nails painted red. Her right hand gestures expressively as she speaks, while her left hand rests calmly in her lap. The setting is an elegant indoor space, featuring a prominent fireplace with a white mantelpiece and a reddish-brown marble surround, flanked by rich wooden paneling. On the mantel, decorative items like golden vases and crystals are visible. To the left, a white bookshelf holds a YouTube play button award. The overall lighting is bright and even, creating a professional and inviting atmosphere. The medium shot captures her engaging demeanor and the sophisticated backdrop, conveying a sense of articulate communication in a refined environment with a realistic cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "PqNq_cMJK9U", |
| "video_url": "https://www.youtube.com/watch?v=PqNq_cMJK9U", |
| "start_time": 498.4583333333333, |
| "end_time": 503.5, |
| "start_frame": 14954, |
| "end_frame": 15105, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "xu9eBdFflsI", |
| "video_url": "https://www.youtube.com/watch?v=xu9eBdFflsI", |
| "start_time": 381.66666666666663, |
| "end_time": 386.7083333333333, |
| "start_frame": 11450, |
| "end_frame": 11601, |
| "fps": 30.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A young woman with long, light brown hair, parted in the middle, is centered in a medium close-up shot, looking directly into the camera. She wears a dark, graphic t-shirt and maintains a calm, engaged expression. Her mouth moves subtly as she speaks, and her head occasionally tilts slightly, conveying a natural conversational tone. The background reveals a modern living space with light gray walls. To her left, a white fireplace mantel is visible, and a green potted plant sits on the floor. To her right, a dark flat-screen television rests on a white stand, and a light wooden desk with a framed picture on the wall behind it. The scene is brightly and evenly lit, suggesting daytime, with soft shadows. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "Zkhdf1Koog8", |
| "video_url": "https://www.youtube.com/watch?v=Zkhdf1Koog8", |
| "start_time": 181.26, |
| "end_time": 186.30166666666665, |
| "start_frame": 4532, |
| "end_frame": 4658, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "KFYvG05MQqY", |
| "video_url": "https://www.youtube.com/watch?v=KFYvG05MQqY", |
| "start_time": 796.7916666666666, |
| "end_time": 801.8333333333333, |
| "start_frame": 47808, |
| "end_frame": 48110, |
| "fps": 60.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium close-up shot frames a woman with long, dark brown hair, dressed in a deep blue V-neck blouse, speaking directly to the camera. Her expression is calm and engaging, with her mouth moving as she articulates words. She uses expressive hand gestures, initially opening her palms outwards, then bringing her hands closer together in a conversational manner. A small black lavalier microphone is clipped to her top, and her fingernails are painted red. The background reveals a bright, modern indoor setting. To her left, a white bookshelf filled with books and a decorative box is visible. To her right, an abstract painting with muted earthy tones hangs on a white wall. A patterned pillow with geometric shapes in pink and teal rests on a surface below the painting. The lighting is soft and even, creating a clear, inviting atmosphere. The overall aesthetic is a realistic, cinematic style." |
| }, |
| { |
| "reference": { |
| "video_id": "GhUIdRxP3WY", |
| "video_url": "https://www.youtube.com/watch?v=GhUIdRxP3WY", |
| "start_time": 0.1, |
| "end_time": 5.141666666666667, |
| "start_frame": 6, |
| "end_frame": 308, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "U-AQpDR_yuI", |
| "video_url": "https://www.youtube.com/watch?v=U-AQpDR_yuI", |
| "start_time": 1300.2154833333334, |
| "end_time": 1305.2571500000001, |
| "start_frame": 77935, |
| "end_frame": 78237, |
| "fps": 59.94005994005994, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A medium shot captures a woman with long, light brown hair, wearing a dark, patterned long-sleeved top, speaking directly to the camera. She holds a light blue book titled \"Oliver Twist\" in her left hand, presenting it towards the viewer. Her expression is calm and engaging, with a slight smile as she articulates words. Behind her, a white bookshelf filled with various books and decorative items creates a studious backdrop. To her left, a colorful arcade machine featuring Mario characters adds a playful element to the room. The lighting is bright and even, illuminating the scene without harsh shadows, suggesting a well-lit indoor environment during the day. Her eyes briefly widen for emphasis as she speaks, conveying a moment of mild surprise or strong point. The overall aesthetic is realistic and cinematic." |
| }, |
| { |
| "reference": { |
| "video_id": "8laYlyAFd0o", |
| "video_url": "https://www.youtube.com/watch?v=8laYlyAFd0o", |
| "start_time": 52.22, |
| "end_time": 57.26166666666666, |
| "start_frame": 1306, |
| "end_frame": 1432, |
| "fps": 25.0, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target": { |
| "video_id": "HOUuvfkrogk", |
| "video_url": "https://www.youtube.com/watch?v=HOUuvfkrogk", |
| "start_time": 403.16884807584154, |
| "end_time": 408.2105147425082, |
| "start_frame": 9666, |
| "end_frame": 9787, |
| "fps": 23.976052840932073, |
| "width": 1920, |
| "height": 1080 |
| }, |
| "target_caption": "A woman with dark hair pulled back neatly is centered in a medium close-up shot, speaking directly into a black microphone on a stand. She wears a bright yellow quarter-zip sweatshirt and a chunky gold chain necklace. Her hands are actively gesturing, palms open and fingers splayed, as she articulates her words with clear mouth movements. Her facial expression is engaged and thoughtful, conveying a calm and confident demeanor. The background features a warm, inviting indoor setting with a light-colored wall. Two framed landscape paintings, a tall golden floor lamp, and a green potted plant are visible behind her, adding to the homely atmosphere. Soft, warm lighting illuminates the scene, casting gentle shadows and highlighting her features and the golden accents. The overall aesthetic is a realistic cinematic look, with natural colors and a clear focus on the subject." |
| } |
| ] |
| } |
