{
 "id": "HIT-TMG/VideoVista-2",
 "owner": "HIT-TMG",
 "name": "VideoVista-2",
 "downloads": 1085,
 "likes": 4,
 "last_modified": "2026-10-12T01:41:16.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "video-text-to-text"
 ],
 "citation": "@ARTICLE{li_videovista,\n  author={Li, Yunxin and Chen, Xinyu and Xu, Zhenran and Wang, Qi and Ma, Yicheng and Liu, Jin and Chen, Kai and Pan, Youcheng and Ding, Yuxin and Wang, Zhefeng and Huai, Baoxing and Hu, Baotian and Zhang, Min},\n  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, \n  title={VideoVista: Benchmarking Diverse and Complex Video-Language Interaction for MLLMs}, \n  year={2026},\n  pages={1-10},\n  keywords={Video Question Answering;Video Evaluation Benchmarks;Video Understanding and Reasoning;Multimodal LLMs},\n  doi={10.1109/TPAMI.2026.3741941}}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "0f305e437f7b70040a72bb7b25fb0985b8977b72",
 "stated_evidence": "https://huggingface.co/datasets/HIT-TMG/VideoVista-2/blob/0f305e437f7b70040a72bb7b25fb0985b8977b72/README.md",
 "file_evidence": "https://huggingface.co/datasets/HIT-TMG/VideoVista-2/tree/0f305e437f7b70040a72bb7b25fb0985b8977b72",
 "card_nc": false
}