{
 "id": "shijiezhou/VLM4D",
 "owner": "shijiezhou",
 "name": "VLM4D",
 "downloads": 2884,
 "likes": 4,
 "last_modified": "2026-07-03T04:48:53.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "video-text-to-text"
 ],
 "citation": "@inproceedings{zhou2025vlm4d,\n    title={VLM4D: Towards Spatiotemporal Awareness in Vision Language Models},\n    author={Zhou, Shijie and Vilesov, Alexander and He, Xuehai and Wan, Ziyu and Zhang, Shuwang and Nagachandra, Aditya and Chang, Di and Chen, Dongdong and Wang, Eric Xin and Kadambi, Achuta},\n    booktitle={Proceedings of the IEEE/CVF international conference on computer vision},\n    pages={8600--8612},\n    year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "9562dc8608cf9715f979ed0c6a5409a11b3978ca",
 "stated_evidence": "https://huggingface.co/datasets/shijiezhou/VLM4D/blob/9562dc8608cf9715f979ed0c6a5409a11b3978ca/README.md",
 "file_evidence": "https://huggingface.co/datasets/shijiezhou/VLM4D/tree/9562dc8608cf9715f979ed0c6a5409a11b3978ca",
 "card_nc": false
}