{"id":"https://openalex.org/W4392111461","doi":"https://doi.org/10.3390/jimaging10030056","title":"Collaborative Modality Fusion for Mitigating Language Bias in Visual Question Answering","display_name":"Collaborative Modality Fusion for Mitigating Language Bias in Visual Question Answering","publication_year":2024,"publication_date":"2024-02-23","ids":{"openalex":"https://openalex.org/W4392111461","doi":"https://doi.org/10.3390/jimaging10030056","pmid":"https://pubmed.ncbi.nlm.nih.gov/38535137"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging10030056","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging10030056","pdf_url":"https://www.mdpi.com/2313-433X/10/3/56/pdf?version=1708699597","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/10/3/56/pdf?version=1708699597","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101185232","display_name":"Qiwen Lu","orcid":"https://orcid.org/0000-0003-4747-7175"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiwen Lu","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng 475001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng 475001, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062618254","display_name":"Shengbo Chen","orcid":"https://orcid.org/0000-0002-9026-8128"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shengbo Chen","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng 475001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng 475001, China","institution_ids":["https://openalex.org/I173899330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012689262","display_name":"Xiaoke Zhu","orcid":"https://orcid.org/0000-0002-0664-1832"},"institutions":[{"id":"https://openalex.org/I173899330","display_name":"Henan University","ror":"https://ror.org/003xyzq10","country_code":"CN","type":"education","lineage":["https://openalex.org/I173899330"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoke Zhu","raw_affiliation_strings":["School of Computer and Information Engineering, Henan University, Kaifeng 475001, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Henan University, Kaifeng 475001, China","institution_ids":["https://openalex.org/I173899330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062618254"],"corresponding_institution_ids":["https://openalex.org/I173899330"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":1.0219,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75243704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"10","issue":"3","first_page":"56","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9969000220298767,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9929999709129333,"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/leverage","display_name":"Leverage (statistics)","score":0.797649621963501},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7973405122756958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7840583324432373},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.644325852394104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.644282341003418},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6357075572013855},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6262534260749817},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.605938196182251},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.506369948387146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5015225410461426},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48377725481987},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32761096954345703}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.797649621963501},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7973405122756958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840583324432373},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.644325852394104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.644282341003418},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6357075572013855},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6262534260749817},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.605938196182251},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.506369948387146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5015225410461426},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48377725481987},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32761096954345703},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging10030056","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging10030056","pdf_url":"https://www.mdpi.com/2313-433X/10/3/56/pdf?version=1708699597","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:38535137","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38535137","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":"Journal of imaging","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10971294","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10971294","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10971294/pdf/jimaging-10-00056.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:979991ba55314bf3bf5091679b93b44b","is_oa":true,"landing_page_url":"https://doaj.org/article/979991ba55314bf3bf5091679b93b44b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 10, Iss 3, p 56 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/jimaging10030056","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging10030056","pdf_url":"https://www.mdpi.com/2313-433X/10/3/56/pdf?version=1708699597","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392111461.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2063036810","https://openalex.org/W2123024445","https://openalex.org/W2151096985","https://openalex.org/W2619383789","https://openalex.org/W2944668088","https://openalex.org/W2955124656","https://openalex.org/W2963260436","https://openalex.org/W2970019270","https://openalex.org/W2983256121","https://openalex.org/W3005680577","https://openalex.org/W3034287395","https://openalex.org/W3035517717","https://openalex.org/W3035561630","https://openalex.org/W3154781046","https://openalex.org/W3175344799","https://openalex.org/W3177934633","https://openalex.org/W3202778561","https://openalex.org/W3205659620","https://openalex.org/W3213504576","https://openalex.org/W4205261319","https://openalex.org/W4213057961","https://openalex.org/W4226181025","https://openalex.org/W4288438155","https://openalex.org/W4289421997","https://openalex.org/W4320003009","https://openalex.org/W4320188728","https://openalex.org/W4324358447","https://openalex.org/W4328120750","https://openalex.org/W4376138432","https://openalex.org/W4385756461","https://openalex.org/W6678470764","https://openalex.org/W6754733129","https://openalex.org/W6803578320"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Language":[0],"bias":[1,58],"stands":[2],"as":[3,61],"a":[4,35,47,68,75,125],"noteworthy":[5],"concern":[6],"in":[7,37,130],"visual":[8],"question":[9],"answering":[10],"(VQA),":[11],"wherein":[12],"models":[13,29],"tend":[14],"to":[15,34,41,79,94],"rely":[16],"on":[17,103,135],"spurious":[18],"correlations":[19],"between":[20,83],"questions":[21],"and":[22,90,111],"answers":[23],"for":[24,99],"prediction.":[25,72,100],"This":[26],"prevents":[27],"the":[28,62,92,118],"from":[30,67],"effectively":[31],"generalizing,":[32],"leading":[33],"decrease":[36],"performance.":[38],"In":[39,55],"order":[40],"address":[42],"this":[43],"bias,":[44],"we":[45],"propose":[46],"novel":[48],"modality":[49,70],"fusion":[50,89],"collaborative":[51,76],"de-biasing":[52],"algorithm":[53],"(CoD).":[54],"our":[56,121],"approach,":[57],"is":[59],"considered":[60],"model's":[63],"neglect":[64],"of":[65,120,133],"information":[66],"particular":[69],"during":[71],"We":[73],"employ":[74],"training":[77],"approach":[78],"facilitate":[80],"mutual":[81],"modeling":[82],"different":[84,114],"modalities,":[85],"achieving":[86],"efficient":[87],"feature":[88],"enabling":[91],"model":[93,128],"fully":[95],"leverage":[96],"multimodal":[97],"knowledge":[98],"Our":[101],"experiments":[102],"various":[104],"datasets,":[105],"including":[106],"VQA-CP":[107,136],"v2,":[108,110],"VQA":[109],"VQA-VS,":[112],"using":[113],"validation":[115],"strategies,":[116],"demonstrate":[117],"effectiveness":[119],"approach.":[122],"Notably,":[123],"employing":[124],"basic":[126],"baseline":[127],"resulted":[129],"an":[131],"accuracy":[132],"60.14%":[134],"v2.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}