{
 "id": "yingsen/internvid-tg",
 "owner": "yingsen",
 "name": "internvid-tg",
 "downloads": 2366,
 "likes": 2,
 "last_modified": "2025-08-01T13:51:35.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "video-text-to-text"
 ],
 "citation": "@article{zeng2025distime,\n  title={DisTime: Distribution-based Time Representation for Video Large Language Models},\n  author={Zeng, Yingsen and Huang, Zepeng and Zhong, Yujie and Feng, Chengjian and Hu, Jie and Ma, Lin and Liu, Yang},\n  journal={arXiv preprint arXiv:2505.24329},\n  year={2025}\n}\n\n@article{wang2023internvid,\n  title={InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation},\n  author={Wang, Yi and He, Yinan and Li, Yizhuo and Li, Kunchang and Yu, Jiashuo and Ma, Xin and Chen, Xinyuan and Wang, Yaohui and Luo, Ping and Liu, Ziwei and Wang, Yali and Wang, Limin and Qiao, Yu},\n  journal={arXiv preprint arXiv:2307.06942},\n  year={2023}\n}",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "71d160cf589da0261f14dab1863d371e4aa25dd6",
 "stated_evidence": "https://huggingface.co/datasets/yingsen/internvid-tg/blob/71d160cf589da0261f14dab1863d371e4aa25dd6/README.md",
 "file_evidence": "https://huggingface.co/datasets/yingsen/internvid-tg/tree/71d160cf589da0261f14dab1863d371e4aa25dd6",
 "card_nc": false
}