{"id":"https://openalex.org/W4410118247","doi":"https://doi.org/10.1109/tnnls.2025.3562085","title":"Counterfactual Dual-Bias VQA: A Multimodality Debias Learning for Robust Visual Question Answering","display_name":"Counterfactual Dual-Bias VQA: A Multimodality Debias Learning for Robust Visual Question Answering","publication_year":2025,"publication_date":"2025-05-06","ids":{"openalex":"https://openalex.org/W4410118247","doi":"https://doi.org/10.1109/tnnls.2025.3562085","pmid":"https://pubmed.ncbi.nlm.nih.gov/40327476"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3562085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3562085","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091545406","display_name":"Boyue Wang","orcid":"https://orcid.org/0000-0002-2677-8342"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyue Wang","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2677-8342","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107269433","display_name":"Xiaoqian Ju","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqian Ju","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015817857","display_name":"Junbin Gao","orcid":"https://orcid.org/0000-0001-9803-0256"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Junbin Gao","raw_affiliation_strings":["Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9803-0256","affiliations":[{"raw_affiliation_string":"Discipline of Business Analytics, The University of Sydney Business School, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014727866","display_name":"Xiaoyan Li","orcid":"https://orcid.org/0000-0003-1536-4264"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Li","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1536-4264","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027329007","display_name":"Yongli Hu","orcid":"https://orcid.org/0000-0003-0440-438X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongli Hu","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0440-438X","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020527092","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0003-3121-1823"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3121-1823","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, School of Information Science and Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82073236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"36","issue":"9","first_page":"16366","last_page":"16378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9639999866485596,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7305784225463867},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6639368534088135},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.6611801981925964},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6017530560493469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44032400846481323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.359978049993515},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.321003794670105},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12905526161193848},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11859992146492004},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10465201735496521},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07174673676490784}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7305784225463867},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6639368534088135},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.6611801981925964},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6017530560493469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44032400846481323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.359978049993515},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.321003794670105},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12905526161193848},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11859992146492004},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10465201735496521},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07174673676490784}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3562085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3562085","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40327476","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40327476","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1098515591","display_name":null,"funder_award_id":"62272015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G583279621","display_name":null,"funder_award_id":"2023YFC3304601","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6152166824","display_name":null,"funder_award_id":"92370102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6212863906","display_name":null,"funder_award_id":"U21B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2745461083","https://openalex.org/W2793127982","https://openalex.org/W2962858109","https://openalex.org/W2963073614","https://openalex.org/W2963260436","https://openalex.org/W2963622213","https://openalex.org/W2963644680","https://openalex.org/W2963800628","https://openalex.org/W2963890019","https://openalex.org/W2963954913","https://openalex.org/W2964935470","https://openalex.org/W2970019270","https://openalex.org/W2970231061","https://openalex.org/W2987123286","https://openalex.org/W3034287395","https://openalex.org/W3035517717","https://openalex.org/W3087338569","https://openalex.org/W3104788521","https://openalex.org/W3154781046","https://openalex.org/W3177934633","https://openalex.org/W3195541832","https://openalex.org/W3198817488","https://openalex.org/W3201068857","https://openalex.org/W3204924011","https://openalex.org/W3216470601","https://openalex.org/W4210518188","https://openalex.org/W4283258232","https://openalex.org/W4307501835","https://openalex.org/W4320188728","https://openalex.org/W4379929708","https://openalex.org/W4382119268","https://openalex.org/W4385574019","https://openalex.org/W4386065611","https://openalex.org/W4386066382","https://openalex.org/W4386160115","https://openalex.org/W4388189274","https://openalex.org/W4391216149","https://openalex.org/W4392523432","https://openalex.org/W4393033612","https://openalex.org/W4393252595","https://openalex.org/W4405867840"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W4205899436","https://openalex.org/W2066431708","https://openalex.org/W4384133558","https://openalex.org/W3025615835","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3028847759","https://openalex.org/W2393688264"],"abstract_inverted_index":{"Visual":[0],"question":[1,19,55,125,143],"answering":[2],"(VQA)":[3],"models":[4],"often":[5,24],"face":[6],"two":[7],"language":[8,89,138,197],"bias":[9,67,90,106,198],"challenges.":[10],"First,":[11],"they":[12,38],"tend":[13],"to":[14,20,61,72,102,135,152,164,189,195,212,221],"rely":[15],"solely":[16],"on":[17,42,229,252],"the":[18,22,29,36,43,54,74,77,88,104,154,170,173,179,186,191,200,206,209,223,230,234,249,253,261],"predict":[21],"answer,":[23],"overlooking":[25],"relevant":[26,153],"information":[27],"in":[28,108,199],"accompanying":[30],"images.":[31],"Second,":[32],"even":[33],"when":[34],"considering":[35],"question,":[37],"may":[39,84],"focus":[40],"only":[41],"wh-words,":[44],"neglecting":[45],"other":[46],"crucial":[47],"keywords":[48,151],"that":[49,120,158],"could":[50],"enhance":[51,73],"interpretability":[52],"and":[53,124,142,150,181,215],"sensitivity.":[56],"Existing":[57],"debiasing":[58],"methods":[59],"attempt":[60],"address":[62],"this":[63,82,93],"by":[64],"training":[65],"a":[66,97,116,218],"model":[68,101,119,137,161,211,263],"using":[69,178],"question-only":[70],"inputs":[71],"robustness":[75],"of":[76,172,208,237,248,260],"target":[78,109,174,201,224],"VQA":[79,110,175,202,225,254],"model.":[80,193,226,242],"However,":[81],"approach":[83,113],"not":[85],"fully":[86,136],"capture":[87],"present.":[91],"In":[92],"article,":[94],"we":[95,133,168,204,244],"propose":[96],"multimodality":[98],"counterfactual":[99,126,144,240],"dual-bias":[100,118,160,192,210,241],"mitigate":[103,196],"linguistic":[105],"issue":[107],"models.":[111],"Our":[112],"involves":[114],"designing":[115],"shared-parameterized":[117],"incorporates":[121],"both":[122],"visual":[123,141],"samples":[127],"as":[128,185],"inputs.":[129],"By":[130],"doing":[131],"so,":[132],"aim":[134],"biases,":[139],"with":[140],"samples,":[145],"respectively,":[146],"emphasizing":[147],"important":[148],"objects":[149],"answers.":[155],"To":[156],"ensure":[157],"our":[159,238],"behaves":[162],"similarly":[163],"an":[165,246],"ordinary":[166],"model,":[167,176,203],"freeze":[169,205],"parameters":[171,207],"meanwhile":[177],"cross-entropy":[180],"Kullback-Leibler":[182],"(KL)":[183],"divergence":[184],"loss":[187,220],"function":[188],"train":[190],"Subsequently,":[194],"generate":[213],"pseudo-labels":[214],"then":[216],"incorporate":[217],"margin":[219],"re-train":[222],"Experimental":[227],"results":[228],"VQA-CP":[231],"datasets":[232],"demonstrate":[233],"superior":[235],"effectiveness":[236],"proposed":[239,262],"Additionally,":[243],"conduct":[245],"analysis":[247],"unsatisfactory":[250],"performance":[251],"v2":[255],"dataset.":[256],"The":[257],"origin":[258],"code":[259],"is":[264],"available":[265],"at":[266],"https://github.com/Arrow2022jv/MCD.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}