{"id":"https://openalex.org/W7118494768","doi":"https://doi.org/10.1109/tmm.2026.3651122","title":"Integrating Object Interaction Self-Attention and GAN-Based Debiasing for Visual Question Answering","display_name":"Integrating Object Interaction Self-Attention and GAN-Based Debiasing for Visual Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7118494768","doi":"https://doi.org/10.1109/tmm.2026.3651122"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651122","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5100782897","display_name":"Zhifei Li","orcid":"https://orcid.org/0000-0003-0443-0094"},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifei Li","raw_affiliation_strings":["School of Computer Science, Hubei University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-0443-0094","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026510056","display_name":"Feng Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Qiu","raw_affiliation_strings":["School of Computer Science, Hubei University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0003-2034-3473","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122298033","display_name":"Yiran Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiran Wang","raw_affiliation_strings":["School of Computer Science, Hubei University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0006-2271-4540","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054113658","display_name":"Yujing Xia","orcid":"https://orcid.org/0000-0002-9477-7042"},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Xia","raw_affiliation_strings":["School of Computer Science, Hubei University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0008-2988-2525","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122066633","display_name":"Kui Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Xiao","raw_affiliation_strings":["School of Computer Science, Hubei University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7784-7689","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Miao Zhang","orcid":"https://orcid.org/0000-0002-8952-215X"},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Zhang","raw_affiliation_strings":["School of Computer Science, Hubei University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-8952-215X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122159151","display_name":"Yan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["School of Computer Science, Hubei University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6045-5208","affiliations":[{"raw_affiliation_string":"School of Computer Science, Hubei University, Wuhan, China","institution_ids":["https://openalex.org/I75900474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75900474"],"apc_list":null,"apc_paid":null,"fwci":9.8969,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94233039,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"28","issue":null,"first_page":"3228","last_page":"3241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9923999905586243,"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":0.9923999905586243,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0019000000320374966,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0013000000035390258,"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/debiasing","display_name":"Debiasing","score":0.9785000085830688},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7840999960899353},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6276000142097473},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.600600004196167},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41749998927116394},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.358599990606308},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9785000085830688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8737000226974487},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7840999960899353},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6276000142097473},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.600600004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145999789237976},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43869999051094055},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41749998927116394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3718999922275543},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3240000009536743},{"id":"https://openalex.org/C2780154230","wikidata":"https://www.wikidata.org/wiki/Q513420","display_name":"Undo","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651122","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.709575355052948}],"awards":[{"id":"https://openalex.org/G7517784107","display_name":null,"funder_award_id":"62207011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8207167207","display_name":null,"funder_award_id":"62377009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8472328015","display_name":null,"funder_award_id":"62407013","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"presents":[4,50],"a":[5,51,84],"unique":[6],"challenge":[7],"by":[8,30],"requiring":[9],"models":[10,24],"to":[11,18,35,43,63,74,104,123],"understand":[12],"and":[13,40,46,60,108,120,137,157,169],"reason":[14],"about":[15],"visual":[16,90,119],"content":[17],"answer":[19],"questions":[20,45],"accurately.":[21],"Existing":[22],"VQA":[23,65,129,174],"often":[25],"struggle":[26],"with":[27,149],"biases":[28,127,171],"introduced":[29],"the":[31,89,93,102,125,134,150,162],"training":[32],"data,":[33],"leading":[34],"over-reliance":[36],"on":[37,133],"superficial":[38],"patterns":[39],"inadequate":[41],"generalization":[42],"diverse":[44],"images.":[47],"This":[48],"paper":[49],"novel":[52],"model,":[53],"IOG-VQA,":[54],"which":[55],"integrates":[56],"Object":[57],"Interaction":[58],"Self-Attention":[59],"GAN-Based":[61],"Debiasing":[62],"enhance":[64],"model":[66,73,103,144],"performance.":[67],"The":[68],"self-attention":[69],"mechanism":[70],"allows":[71],"our":[72,143],"capture":[75],"complex":[76],"interactions":[77,168],"between":[78],"objects":[79],"within":[80],"an":[81],"image,":[82],"providing":[83],"more":[85,106],"comprehensive":[86],"understanding":[87],"of":[88,164],"context.":[91],"Meanwhile,":[92],"GAN-based":[94],"debiasing":[95],"framework":[96],"generates":[97],"unbiased":[98],"data":[99,159],"distributions,":[100],"helping":[101],"learn":[105],"robust":[107],"generalizable":[109],"features.":[110],"By":[111],"leveraging":[112],"these":[113],"two":[114],"components,":[115],"IOG-VQA":[116],"effectively":[117],"combines":[118],"textual":[121],"information":[122],"address":[124],"inherent":[126],"in":[128,154,172],"datasets.":[130],"Extensive":[131],"experiments":[132],"VQA-CP":[135,138],"v1":[136],"v2":[139],"datasets":[140],"demonstrate":[141],"that":[142],"shows":[145],"excellent":[146],"performance":[147],"compared":[148],"existing":[151],"methods,":[152],"particularly":[153],"handling":[155],"biased":[156],"imbalanced":[158],"distributions":[160],"highlighting":[161],"importance":[163],"addressing":[165],"both":[166],"object":[167],"dataset":[170],"advancing":[173],"tasks.":[175],"Our":[176],"code":[177],"is":[178],"available":[179],"at":[180],"<uri":[181],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[182],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/HubuKG/IOG-VQA</uri>.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-25T06:01:18.069262","created_date":"2026-01-08T00:00:00"}
