{"url":"/task/audio-visual-question-answering","name":"Audio-visual Question Answering","slug":"audio-visual-question-answering","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":27,"papers_with_code":19,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/audio-visual-question-answering-on-music-avqa","slug":"audio-visual-question-answering-on-music-avqa","dataset":"MUSIC-AVQA","dataset_url":"/dataset/music-avqa","rows_in_archive":6,"metrics":["Acc"],"first_row_in_archive_order":{"model":"VAST","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","paper_url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_date":"2023-05-29","arxiv_id":"2305.18500","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}],"syntology":{"n":42,"n_ran":15,"n_unverified":27,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/music-avqa","name":"MUSIC-AVQA","full_name":"","num_papers_in_archive":51},{"url":"/dataset/music-avqa-v2-0","name":"MUSIC-AVQA v2.0","full_name":"","num_papers_in_archive":5}],"subtasks":[{"url":"/task/audio-visual-question-answering-music-avqa-v2","name":"AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":19,"of":19,"tagged_in_all":27,"items":[{"url":"/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","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":15,"n_unverified":27,"n_pointer_only":0}},{"url":"/paper/fortisavqa-and-maven-a-benchmark-dataset-and","title":"FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning","date":"2025-04-01","arxiv_id":"2504.00487","repositories_listed":1,"syntology":null},{"url":"/paper/pave-patching-and-adapting-video-large","title":"PAVE: Patching and Adapting Video Large Language Models","date":"2025-03-25","arxiv_id":"2503.19794","repositories_listed":1,"syntology":null},{"url":"/paper/question-aware-gaussian-experts-for-audio","title":"Question-Aware Gaussian Experts for Audio-Visual Question Answering","date":"2025-03-06","arxiv_id":"2503.04459","repositories_listed":1,"syntology":null},{"url":"/paper/avqacl-a-novel-benchmark-for-audio-visual","title":"AVQACL: A Novel Benchmark for Audio-Visual Question Answering Continual Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/boosting-audio-visual-question-answering-via","title":"Boosting Audio Visual Question Answering via Key Semantic-Aware Cues","date":"2024-07-30","arxiv_id":"2407.20693","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/learning-trimodal-relation-for-avqa-with","title":"Learning Trimodal Relation for AVQA with Missing Modality","date":"2024-07-23","arxiv_id":"2407.16171","repositories_listed":1,"syntology":{"n":24,"n_ran":20,"n_unverified":4,"n_pointer_only":3}},{"url":"/paper/towards-multilingual-audio-visual-question","title":"Towards Multilingual Audio-Visual Question Answering","date":"2024-06-13","arxiv_id":"2406.09156","repositories_listed":1,"syntology":null},{"url":"/paper/look-listen-and-answer-overcoming-biases-for","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","date":"2024-04-18","arxiv_id":"2404.12020","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/answering-diverse-questions-via-text-attached","title":"Answering Diverse Questions via Text Attached with Key Audio-Visual Clues","date":"2024-03-11","arxiv_id":"2403.06679","repositories_listed":1,"syntology":null},{"url":"/paper/cat-enhancing-multimodal-large-language-model","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2024-03-07","arxiv_id":"2403.04640","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/object-aware-adaptive-positivity-learning-for","title":"Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering","date":"2023-12-20","arxiv_id":"2312.12816","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/progressive-spatio-temporal-perception-for","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","date":"2023-08-10","arxiv_id":"2308.05421","repositories_listed":1,"syntology":null},{"url":"/paper/target-aware-spatio-temporal-reasoning-via","title":"Target-Aware Spatio-Temporal Reasoning via Answering Questions in Dynamics Audio-Visual Scenarios","date":"2023-05-21","arxiv_id":"2305.12397","repositories_listed":1,"syntology":null},{"url":"/paper/valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","repositories_listed":1,"syntology":null},{"url":"/paper/vision-transformers-are-parameter-efficient","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","date":"2022-12-15","arxiv_id":"2212.07983","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/learning-to-answer-questions-in-dynamic-audio","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2022-03-26","arxiv_id":"2203.14072","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/pano-avqa-grounded-audio-visual-question-1","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","date":"2021-10-11","arxiv_id":"2110.05122","repositories_listed":1,"syntology":null},{"url":"/paper/pano-avqa-grounded-audio-visual-question","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360deg Videos","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}