{"id":"https://openalex.org/W3170243808","doi":"https://doi.org/10.1109/icme51207.2021.9428098","title":"Learning Content and Context with Language Bias for Visual Question Answering","display_name":"Learning Content and Context with Language Bias for Visual Question Answering","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3170243808","doi":"https://doi.org/10.1109/icme51207.2021.9428098","mag":"3170243808"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-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/A5072105113","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0002-3763-5080"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Yang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006378862","display_name":"Feng Su","orcid":"https://orcid.org/0000-0002-8426-9634"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Su Feng","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681030","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-7725-8040"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103007496","display_name":"Huawei Shen","orcid":"https://orcid.org/0000-0003-1204-4820"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei Shen","raw_affiliation_strings":["Insitute of Computing Technology, Chinese Academy of Science"],"affiliations":[{"raw_affiliation_string":"Insitute of Computing Technology, Chinese Academy of Science","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739561","display_name":"Guoqing Wang","orcid":"https://orcid.org/0000-0003-1157-0909"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Wang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007360513","display_name":"Bin Jiang","orcid":"https://orcid.org/0000-0002-5840-9664"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Jiang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072105113"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":1.3565,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.82955172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9954000115394592,"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":0.9891999959945679,"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":0.8406566381454468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.792553186416626},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7079697251319885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5861085653305054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5614094734191895},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5225362777709961},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.517138659954071},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4787282645702362},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4710398018360138},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4632699489593506},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44196581840515137},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4305300712585449},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3900764584541321},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32477515935897827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06792736053466797}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8406566381454468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792553186416626},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7079697251319885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5861085653305054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5614094734191895},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5225362777709961},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.517138659954071},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4787282645702362},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4710398018360138},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4632699489593506},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44196581840515137},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4305300712585449},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3900764584541321},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32477515935897827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06792736053466797},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428098","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428098","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2946299408","https://openalex.org/W2955124656","https://openalex.org/W2962884579","https://openalex.org/W2963140463","https://openalex.org/W2963609017","https://openalex.org/W2963954913","https://openalex.org/W2983256121","https://openalex.org/W2997072136","https://openalex.org/W3034287395","https://openalex.org/W3035017890","https://openalex.org/W3035243232","https://openalex.org/W3035517717","https://openalex.org/W3177934633","https://openalex.org/W4289421997","https://openalex.org/W6754733129","https://openalex.org/W6763000187","https://openalex.org/W6764756247","https://openalex.org/W6779283709"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,110],"a":[5,56,87,106],"challenging":[6],"multi-modal":[7],"task":[8],"to":[9,20,46,66,94,112],"answer":[10,27,67],"questions":[11,28,68],"about":[12],"an":[13],"image.":[14],"Many":[15],"works":[16],"concentrate":[17],"on":[18,70,84,96,124,135],"how":[19],"reduce":[21,113],"language":[22,33,37,75],"bias":[23,38],"which":[24,62],"makes":[25],"models":[26,45,65],"ignoring":[29],"visual":[30],"content":[31,99],"and":[32,72,81,91,100,119],"context.":[34],"However,":[35],"reducing":[36],"also":[39],"weakens":[40],"the":[41,114,132],"ability":[42],"of":[43,86,116],"VQA":[44,64,89],"learn":[47],"context":[48,103],"prior.":[49],"To":[50],"address":[51],"this":[52],"issue,":[53],"we":[54],"propose":[55],"novel":[57],"learning":[58],"strategy":[59],"named":[60],"CCB,":[61],"forces":[63,92],"relying":[69],"Content":[71,80],"Context":[73,82],"with":[74],"Bias.":[76],"Specifically,":[77],"CCB":[78,130],"establishes":[79],"branches":[83],"top":[85],"base":[88],"model":[90],"them":[93],"focus":[95],"local":[97],"key":[98],"global":[101],"effective":[102],"respectively.":[104],"Moreover,":[105],"joint":[107],"loss":[108],"function":[109],"proposed":[111],"importance":[115],"biased":[117],"samples":[118],"retain":[120],"their":[121],"beneficial":[122],"influence":[123],"answering":[125],"questions.":[126],"Experiments":[127],"show":[128],"that":[129],"outperforms":[131],"state-of-the-art":[133],"methods":[134],"VQA-CP":[136],"v2.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}