{
 "id": "inesriahi/valor32k-avqa-v2",
 "owner": "inesriahi",
 "name": "valor32k-avqa-v2",
 "downloads": 936,
 "likes": 0,
 "last_modified": "2026-06-17T12:53:34.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering",
  "visual-question-answering",
  "multiple-choice",
  "video-text-to-text"
 ],
 "citation": "@inproceedings{riahi2025valor32k,\n  author    = {Riahi, Ines and Radman, Abduljalil and Guo, Zixin and Hedjam, Rachid and Laaksonen, Jorma},\n  title     = {Valor32k-AVQA v2.0: Open-Ended Audio-Visual Question Answering Dataset and Benchmark},\n  booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},\n  series    = {MM '25},\n  year      = {2025},\n  pages     = {13097--13103},\n  publisher = {Association for Computing Machinery},\n  address   = {New York, NY, USA},\n  location  = {Dublin, Ireland},\n  isbn      = {9798400720352},\n  doi       = {10.1145/3746027.3758261},\n  url       = {https://doi.org/10.1145/3746027.3758261}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "1b916bd15c19302f319ee6dd1206c7555bb19d76",
 "stated_evidence": "https://huggingface.co/datasets/inesriahi/valor32k-avqa-v2/blob/1b916bd15c19302f319ee6dd1206c7555bb19d76/README.md",
 "file_evidence": "https://huggingface.co/datasets/inesriahi/valor32k-avqa-v2/tree/1b916bd15c19302f319ee6dd1206c7555bb19d76",
 "card_nc": false
}