{"url":"/dataset/music-avqa-v2-0","name":"MUSIC-AVQA v2.0","full_name":null,"description_markdown":"MUSIC-AVQA v2.0 balances the original MUSIC-AVQA dataset in each QA category and sub-category. This balance results in a more reliable benchmark than the original MUSIC-AVQA dataset. See more details at paper \"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering\" published at WACV 2024.","description_withheld":null,"homepage":"https://github.com/DragonLiu1995/MUSIC-AVQA-v2.0","introduced_date":"2024-09-01","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Audio-visual Question Answering","url":"/task/audio-visual-question-answering","datasets_with_task":"/datasets/task/audio-visual-question-answering"},{"name":"AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)","url":"/task/audio-visual-question-answering-music-avqa-v2","datasets_with_task":"/datasets/task/audio-visual-question-answering-music-avqa-v2"}],"languages":[],"variants":["MUSIC-AVQA v2.0"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-visual-question-answering-music-avqa-v2","task":"AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)","dataset_variant":"MUSIC-AVQA v2.0","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Meerkat","paper":"/paper/meerkat-audio-visual-large-language-model-for","metrics":{"Accuracy":"79.15"},"code_links":[{"title":"schowdhury671/meerkat","url":"https://github.com/schowdhury671/meerkat"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/question-aware-gaussian-experts-for-audio","title":"Question-Aware Gaussian Experts for Audio-Visual Question Answering","date":"2025-03-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/meerkat-audio-visual-large-language-model-for","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","date":"2024-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":8,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tackling-data-bias-in-music-avqa-crafting-a","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","date":"2023-10-10","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":18,"samples_ran":9,"samples_unverified":9,"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."}