{
 "id": "dongqi-me/VISTA",
 "owner": "dongqi-me",
 "name": "VISTA",
 "downloads": 2134,
 "likes": 5,
 "last_modified": "2025-08-03T03:58:17.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "manual",
 "tasks": [
  "summarization",
  "text-generation"
 ],
 "citation": "@inproceedings{liu-etal-2025-talk,\n    title = \"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations\",\n    author = \"Liu, Dongqi  and\n      Whitehouse, Chenxi  and\n      Yu, Xi  and\n      Mahon, Louis  and\n      Saxena, Rohit  and\n      Zhao, Zheng  and\n      Qiu, Yifu  and\n      Lapata, Mirella  and\n      Demberg, Vera\",\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.310/\",\n    pages = \"6187--6210\",\n    ISBN = \"979-8-89176-251-0\",\n    abstract = \"Transforming recorded videos into concise and accurate textual summaries is a growing challenge in multimodal learning. This paper introduces VISTA, a dataset specifically designed for video-to-text summarization in scientific domains. VISTA contains 18,599 recorded AI conference presentations paired with their corresponding paper abstracts. We benchmark the performance of state-of-the-art large models and apply a plan-based framework to better capture the structured nature of abstracts. Both human and automated evaluations confirm that explicit planning enhances summary quality and factual consistency. However, a c",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "39c60afff185fbefe80b685898cf073da0fd92ab",
 "stated_evidence": "https://huggingface.co/datasets/dongqi-me/VISTA/blob/39c60afff185fbefe80b685898cf073da0fd92ab/README.md",
 "file_evidence": "https://huggingface.co/datasets/dongqi-me/VISTA/tree/39c60afff185fbefe80b685898cf073da0fd92ab",
 "card_nc": false
}