{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/look-listen-and-answer-overcoming-biases-for","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","arxiv_id":"2404.12020","date":"2024-04-18","proceeding":null,"authors":["Jie Ma","Min Hu","Pinghui Wang","Wangchun Sun","Lingyun Song","Hongbin Pei","Jun Liu","Youtian Du"],"abstract":"Audio-Visual Question Answering (AVQA) is a complex multi-modal reasoning task, demanding intelligent systems to accurately respond to natural language queries based on audio-video input pairs. Nevertheless, prevalent AVQA approaches are prone to overlearning dataset biases, resulting in poor robustness. Furthermore, current datasets may not provide a precise diagnostic for these methods. To tackle these challenges, firstly, we propose a novel dataset, MUSIC-AVQA-R, crafted in two steps: rephrasing questions within the test split of a public dataset (MUSIC-AVQA) and subsequently introducing distribution shifts to split questions. The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions. Secondly, we propose a robust architecture that utilizes a multifaceted cycle collaborative debiasing strategy to overcome bias learning. Experimental results show that this architecture achieves state-of-the-art performance on MUSIC-AVQA-R, notably obtaining a significant improvement of 9.32%. Extensive ablation experiments are conducted on the two datasets mentioned to analyze the component effectiveness within the debiasing strategy. Additionally, we highlight the limited robustness of existing multi-modal QA methods through the evaluation on our dataset. We also conduct experiments combining various baselines with our proposed strategy on two datasets to verify its plug-and-play capability. Our dataset and code are available at https://github.com/reml-group/MUSIC-AVQA-R.","url_abs":"https://arxiv.org/abs/2404.12020v3","url_pdf":"https://arxiv.org/pdf/2404.12020v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"look-listen-and-answer-overcoming-biases-for","repo_url":"https://github.com/reml-group/music-avqa-r","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"audio-visual-question-answering-avqa","task_name":"Audio-Visual Question Answering (AVQA)"},{"task_slug":"audio-visual-question-answering","task_name":"Audio-visual Question Answering"},{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[{"slug":"music-avqa-r","name":"MUSIC-AVQA-R","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.12020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12020"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/reml-group/MUSIC-AVQA-R","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/reml-group/music-avqa-r","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"community":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"6b93ebdfa2d4b35a","entry":"batch_organize","repo":"gewu-lab/music-avqa","repo_kind":"community","path":"net_grd_avst/main_avst.py","file_url":"https://github.com/gewu-lab/music-avqa/blob/HEAD/net_grd_avst/main_avst.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6b93ebdfa2d4b35a"}},{"code_sha256_prefix":"bb9defc2e7b23f89","entry":"grad_mul_const","repo":"reml-group/MUSIC-AVQA-R","repo_kind":"official","path":"utils.py","file_url":"https://github.com/reml-group/MUSIC-AVQA-R/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb9defc2e7b23f89"}},{"code_sha256_prefix":"73f55fb868a26848","entry":"test","repo":"gewu-lab/music-avqa","repo_kind":"community","path":"net_grd_avst/main_avst.py","file_url":"https://github.com/gewu-lab/music-avqa/blob/HEAD/net_grd_avst/main_avst.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73f55fb868a26848"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}