{"url":"/dataset/music-avqa","name":"MUSIC-AVQA","full_name":null,"description_markdown":"The large-scale MUSIC-AVQA dataset of musical performance contains 45,867 question-answer pairs, distributed in 9,288 videos for over 150 hours. All QA pairs types are divided into 3 modal scenarios, which contain 9 question types and 33 question templates. Finally, as an open-ended problem of our AVQA tasks, all 42 kinds of answers constitute a set for selection.","description_withheld":null,"homepage":"http://gewu-lab.github.io/MUSIC-AVQA/","introduced_date":"2022-03-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-to-answer-questions-in-dynamic-audio","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","first_author":"Guangyao Li","url":null},"license":{"name":"MIT","url":"https://github.com/GeWu-Lab/MUSIC-AVQA/blob/main/LICENSE"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Scene Understanding","url":"/task/scene-understanding","datasets_with_task":"/datasets/task/scene-understanding"},{"name":"Audio-visual Question Answering","url":"/task/audio-visual-question-answering","datasets_with_task":"/datasets/task/audio-visual-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MUSIC-AVQA"],"data_loaders":[{"repo":"https://github.com/GeWu-Lab/MUSIC-AVQA","url":"https://gewu-lab.github.io/MUSIC-AVQA/","frameworks":["pytorch"]}],"num_papers_in_archive":51,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-visual-question-answering-on-music-avqa","task":"Audio-visual Question Answering","dataset_variant":"MUSIC-AVQA","rows":6,"metrics":["Acc"],"first_row_in_archive_order":{"model":"VAST","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","metrics":{"Acc":"80.7"},"code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/cad-contextual-multi-modal-alignment-for","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","date":"2023-10-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":42,"samples_ran":15,"samples_unverified":27,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vision-transformers-are-parameter-efficient","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","date":"2022-12-15","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-to-answer-questions-in-dynamic-audio","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2022-03-26","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":48,"samples_ran":16,"samples_unverified":32,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}