{
  "model_name": "RemoteCLIP",
  "model_type": "remoteclip",
  "architectures": [
    "RemoteCLIP"
  ],
  "framework": "PyTorch",
  "domain": "earth-science",
  "task": "remote-sensing-image-text-retrieval",
  "implementation": {
    "entry_point": "model/remoteclip.py",
    "scope": "compact image-text contrastive RemoteCLIP reproduction"
  },
  "architecture": {
    "family": "dual-encoder vision-language model",
    "input_format": "image-text NPZ pairs",
    "image_channels": 3,
    "image_size": 32,
    "vocabulary_size": 64,
    "context_length": 8,
    "embed_dim": 32,
    "vision_width": 32,
    "text_width": 32,
    "text_layers": 2,
    "text_heads": 4,
    "training_objective": "bidirectional InfoNCE"
  },
  "data": {
    "datasets": [
      "RSITMD",
      "RSICD",
      "UCM-Captions"
    ],
    "official_repo": "ChenDelong1999/RemoteCLIP",
    "protocol": "synthetic_remoteclip",
    "synthetic_train_samples": 32,
    "synthetic_test_samples": 8
  },
  "metrics": [
    "image_to_text_r1",
    "image_to_text_r5",
    "text_to_image_r1",
    "text_to_image_r5",
    "mean_recall"
  ],
  "configuration_sources": [
    "conf/config.yaml",
    "model/remoteclip.py"
  ]
}