{
 "id": "OpenGVLab/InternVideo2_Vid_Text",
 "owner": "OpenGVLab",
 "name": "InternVideo2_Vid_Text",
 "downloads": 23,
 "likes": 15,
 "last_modified": "2024-07-10T14:26:45.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "feature-extraction"
 ],
 "citation": "@article{wang2024internvideo2,\n  title={Internvideo2: Scaling video foundation models for multimodal video understanding},\n  author={Wang, Yi and Li, Kunchang and Li, Xinhao and Yu, Jiashuo and He, Yinan and Chen, Guo and Pei, Baoqi and Zheng, Rongkun and Xu, Jilan and Wang, Zun and others},\n  journal={arXiv preprint arXiv:2403.15377},\n  year={2024}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "4ade67001ff63d0f65c0e32fef950246e88471b3",
 "stated_evidence": "https://huggingface.co/datasets/OpenGVLab/InternVideo2_Vid_Text/blob/4ade67001ff63d0f65c0e32fef950246e88471b3/README.md",
 "file_evidence": "https://huggingface.co/datasets/OpenGVLab/InternVideo2_Vid_Text/tree/4ade67001ff63d0f65c0e32fef950246e88471b3",
 "card_nc": false
}