{
 "id": "Joysw909/AVQA",
 "owner": "Joysw909",
 "name": "AVQA",
 "downloads": 4213,
 "likes": 2,
 "last_modified": "2025-11-15T10:42:53.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering"
 ],
 "citation": "@inproceedings{yang2022avqa,\n  author = {Pinci Yang and Xin Wang and Xuguang Duan and Hong Chen and Runze Hou and Cong Jin and Wenwu Zhu},\n  title = {{AVQA: A Dataset for Audio-Visual Question Answering on Videos}},\n  booktitle = {Proceedings of the 30th ACM International Conference on Multimedia (MM '22)},\n  pages = {12 pages},\n  year = {2022},\n  address = {Lisboa, Portugal},\n  publisher = {ACM},\n  url = {https://doi.org/10.1145/3503161.3548291}\n}\n\n\n@article{li2025reinforcement,\n  title={Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering},\n  author={Li, Gang and Liu, Jizhong and Dinkel, Heinrich and Niu, Yadong and Zhang, Junbo and Luan, Jian},\n  journal={arXiv preprint arXiv:2503.11197},\n  year={2025},\n  url={https://github.com/xiaomi-research/r1-aqa; https://huggingface.co/mispeech/r1-aqa}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "9508c74bb202fa7d7ab6a9c329dd66d7ecca970e",
 "stated_evidence": "https://huggingface.co/datasets/Joysw909/AVQA/blob/9508c74bb202fa7d7ab6a9c329dd66d7ecca970e/README.md",
 "file_evidence": "https://huggingface.co/datasets/Joysw909/AVQA/tree/9508c74bb202fa7d7ab6a9c329dd66d7ecca970e",
 "card_nc": false
}