{
 "id": "EmbodiedCity/UrbanVideo-Bench",
 "owner": "EmbodiedCity",
 "name": "UrbanVideo-Bench",
 "downloads": 2888,
 "likes": 9,
 "last_modified": "2026-08-07T03:33:09.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering"
 ],
 "citation": "@inproceedings{zhao-etal-2025-urbanvideo,\n    title = \"{U}rban{V}ideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces\",\n    author = \"Zhao, Baining  and\n      Fang, Jianjie  and\n      Dai, Zichao  and\n      Wang, Ziyou  and\n      Zha, Jirong  and\n      Zhang, Weichen  and\n      Gao, Chen  and\n      Wang, Yue  and\n      Cui, Jinqiang  and\n      Chen, Xinlei  and\n      Li, Yong\",\n    editor = \"Che, Wanxiang  and\n      Nabende, Joyce  and\n      Shutova, Ekaterina  and\n      Pilehvar, Mohammad Taher\",\n    booktitle = \"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)\",\n    month = jul,\n    year = \"2025\",\n    address = \"Vienna, Austria\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.acl-long.1558/\",\n    doi = \"10.18653/v1/2025.acl-long.1558\",\n    pages = \"32400--32423\",\n    ISBN = \"979-8-89176-251-0\"\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "aa423951ec896a9c744fcb0d6ec0ff190de92f7d",
 "stated_evidence": "https://huggingface.co/datasets/EmbodiedCity/UrbanVideo-Bench/blob/aa423951ec896a9c744fcb0d6ec0ff190de92f7d/README.md",
 "file_evidence": "https://huggingface.co/datasets/EmbodiedCity/UrbanVideo-Bench/tree/aa423951ec896a9c744fcb0d6ec0ff190de92f7d",
 "card_nc": false
}