{"url":"/task/audio-visual-question-answering-avqa","name":"Audio-Visual Question Answering (AVQA)","slug":"audio-visual-question-answering-avqa","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":20,"papers_with_code":15,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/avqa","name":"AVQA","full_name":"","num_papers_in_archive":3}],"subtasks":[],"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":15,"of":15,"tagged_in_all":20,"items":[{"url":"/paper/one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"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/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/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/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/hierarchical-conditional-relation-networks","title":"Hierarchical Conditional Relation Networks for Video Question Answering","date":"2020-02-25","arxiv_id":"2002.10698","repositories_listed":1,"syntology":null}],"syntology_records":7,"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"}}