{"id":"https://openalex.org/W4385768191","doi":"https://doi.org/10.24963/ijcai.2023/457","title":"An Empirical Study on the Language Modal in Visual Question Answering","display_name":"An Empirical Study on the Language Modal in Visual Question Answering","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768191","doi":"https://doi.org/10.24963/ijcai.2023/457"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/457","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/457","pdf_url":"https://www.ijcai.org/proceedings/2023/0457.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0457.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066682332","display_name":"Daowan Peng","orcid":"https://orcid.org/0000-0001-5208-3811"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daowan Peng","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323842","display_name":"Wei Wei","orcid":"https://orcid.org/0000-0003-4488-0102"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":["Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory, School of Computer Science and Technology, Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017626590","display_name":"Xian-Ling Mao","orcid":"https://orcid.org/0000-0001-6795-2311"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian-Ling Mao","raw_affiliation_strings":["Department of Computer Science and Technology, Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715195","display_name":"Yuanyuan Fu","orcid":"https://orcid.org/0009-0007-6581-4194"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Fu","raw_affiliation_strings":["Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Ping An Property&Casualty Insurance Company of China, Ltd","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL); Ping An Property&Casualty Insurance Company of China, Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Ping An Property&Casualty Insurance Company of China, Ltd","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL); Ping An Property&Casualty Insurance Company of China, Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052720613","display_name":"Dangyang Chen","orcid":"https://orcid.org/0000-0001-8693-7803"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dangyang Chen","raw_affiliation_strings":["Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","Ping An Property&Casualty Insurance Company of China, Ltd","Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL); Ping An Property&Casualty Insurance Company of China, Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)","institution_ids":[]},{"raw_affiliation_string":"Ping An Property&Casualty Insurance Company of China, Ltd","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL); Ping An Property&Casualty Insurance Company of China, Ltd","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4855,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71952475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4109","last_page":"4117"},"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":0.9976999759674072,"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":0.9879000186920166,"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":0.810027003288269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7851355075836182},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6330221891403198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6326436996459961},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6316955089569092},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5809780955314636},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5688778162002563},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5548059344291687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5467251539230347},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5248047113418579},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4902556240558624},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.46988821029663086},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4401092231273651},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.10206696391105652},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.10155794024467468},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09803509712219238},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09647402167320251}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.810027003288269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851355075836182},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6330221891403198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6326436996459961},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6316955089569092},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5809780955314636},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5688778162002563},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5548059344291687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5467251539230347},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5248047113418579},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4902556240558624},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.46988821029663086},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4401092231273651},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.10206696391105652},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.10155794024467468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09803509712219238},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09647402167320251},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/457","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/457","pdf_url":"https://www.ijcai.org/proceedings/2023/0457.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/457","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/457","pdf_url":"https://www.ijcai.org/proceedings/2023/0457.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G6095425281","display_name":null,"funder_award_id":"62276110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8878491478","display_name":null,"funder_award_id":"62172039","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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768191.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2157331557","https://openalex.org/W2481240925","https://openalex.org/W2489434015","https://openalex.org/W2563399268","https://openalex.org/W2741631785","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2946299408","https://openalex.org/W2963115613","https://openalex.org/W2963521239","https://openalex.org/W2963644680","https://openalex.org/W2963954913","https://openalex.org/W2965628639","https://openalex.org/W2966683369","https://openalex.org/W2969876226","https://openalex.org/W2970019270","https://openalex.org/W2970231061","https://openalex.org/W2983256121","https://openalex.org/W2997072136","https://openalex.org/W3016211260","https://openalex.org/W3035517717","https://openalex.org/W3035561630","https://openalex.org/W3090449556","https://openalex.org/W3099884329","https://openalex.org/W3110388292","https://openalex.org/W3154781046","https://openalex.org/W3167814535","https://openalex.org/W3170243808","https://openalex.org/W3172438304","https://openalex.org/W3173220247","https://openalex.org/W3177934633","https://openalex.org/W3192587235","https://openalex.org/W3193402170","https://openalex.org/W3202778561","https://openalex.org/W3213504576","https://openalex.org/W3214685499","https://openalex.org/W4226258784","https://openalex.org/W4285414077","https://openalex.org/W4285605365","https://openalex.org/W4289243726","https://openalex.org/W4289421997","https://openalex.org/W4312341105","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4362554880","https://openalex.org/W4281684980","https://openalex.org/W4386875279","https://openalex.org/W2171721708","https://openalex.org/W4390963114","https://openalex.org/W4375957588","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Generalization":[0],"beyond":[1],"in-domain":[2,28],"experience":[3],"to":[4,32,48,150],"out-of-distribution":[5,119,173],"data":[6],"is":[7,95],"of":[8,55,73,80,99,164],"paramount":[9],"significance":[10],"in":[11,43,102,168],"the":[12,33,40,53,118,122,137,152,162,172],"AI":[13],"domain.":[14],"Of":[15],"late,":[16],"state-of-the-art":[17],"Visual":[18],"Question":[19],"Answering":[20],"(VQA)":[21],"models":[22,109],"have":[23],"shown":[24],"impressive":[25],"performance":[26,60,116,170],"on":[27,58,75,117,155,171,187],"data,":[29],"partially":[30],"due":[31],"language":[34,56,156],"prior":[35,88],"bias":[36,89,101],"which,":[37],"however,":[38],"hinders":[39],"generalization":[41],"ability":[42],"practice.":[44],"This":[45],"paper":[46],"attempts":[47],"provide":[49],"new":[50],"insights":[51,183],"into":[52,136],"influence":[54,98],"modality":[57],"VQA":[59,108],"from":[61,87],"an":[62],"empirical":[63],"study":[64,179],"perspective.":[65],"To":[66],"achieve":[67],"this,":[68],"we":[69],"conducted":[70],"a":[71,96,126],"series":[72],"experiments":[74,82],"six":[76],"models.":[77],"The":[78,158],"results":[79,143,160],"these":[81,141],"revealed":[83],"that,":[84],"1)":[85],"apart":[86],"caused":[90],"by":[91],"question":[92],"types,":[93],"there":[94],"notable":[97],"postfix-related":[100],"inducing":[103],"biases,":[104],"and":[105,121,144],"2)":[106],"training":[107],"with":[110],"word-sequence-related":[111],"variant":[112],"questions":[113],"demonstrated":[114,161],"improved":[115],"benchmark,":[120,174],"LXMERT":[123],"even":[124],"achieved":[125],"10-point":[127],"gain":[128],"without":[129],"adopting":[130],"any":[131],"debiasing":[132],"methods.":[133],"We":[134,176],"delved":[135],"underlying":[138],"reasons":[139],"behind":[140],"experimental":[142,159],"put":[145],"forward":[146],"some":[147],"simple":[148],"proposals":[149],"reduce":[151],"models'":[153],"dependency":[154],"priors.":[157],"effectiveness":[163],"our":[165],"proposed":[166],"method":[167],"improving":[169],"VQA-CPv2.":[175],"hope":[177],"this":[178],"can":[180],"inspire":[181],"novel":[182],"for":[184],"future":[185],"research":[186],"designing":[188],"bias-reduction":[189],"approaches.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}