{
 "id": "OpenGVLab/OmniCorpus-YT",
 "owner": "OpenGVLab",
 "name": "OmniCorpus-YT",
 "downloads": 448,
 "likes": 16,
 "last_modified": "2025-03-20T12:44:21.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "video-text-to-text",
  "visual-question-answering",
  "image-to-text"
 ],
 "citation": "@inproceedings{li2024omnicorpus,\n  title={OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text},\n  author={Li, Qingyun and Chen, Zhe and Wang, Weiyun and Wang, Wenhai and Ye, Shenglong and Jin, Zhenjiang and others},\n  booktitle={The Thirteenth International Conference on Learning Representations},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "1a35a3e6d1614aead05c11d6f1aae83f7b893c1c",
 "stated_evidence": "https://huggingface.co/datasets/OpenGVLab/OmniCorpus-YT/blob/1a35a3e6d1614aead05c11d6f1aae83f7b893c1c/README.md",
 "file_evidence": "https://huggingface.co/datasets/OpenGVLab/OmniCorpus-YT/tree/1a35a3e6d1614aead05c11d6f1aae83f7b893c1c",
 "card_nc": false
}