{"id":"https://openalex.org/W2963150162","doi":"https://doi.org/10.1109/iccv.2017.202","title":"Multi-modal Factorized Bilinear Pooling with Co-attention Learning for Visual Question Answering","display_name":"Multi-modal Factorized Bilinear Pooling with Co-attention Learning for Visual Question Answering","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2963150162","doi":"https://doi.org/10.1109/iccv.2017.202","mag":"2963150162"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2017.202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","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/A5061025828","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0001-8407-1137"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhou Yu","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, Hangzhou Dianzi University, P. R. China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, Hangzhou Dianzi University, P. R. China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050817770","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-1922-7283"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Key Laboratory of Complex Systems Modeling and Simulation, Hangzhou Dianzi University, P. R. China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Complex Systems Modeling and Simulation, Hangzhou Dianzi University, P. R. China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728564","display_name":"Jianping Fan","orcid":"https://orcid.org/0000-0002-4923-0910"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianping Fan","raw_affiliation_strings":["Department of Computer Science, University of North Carolina at Charlotte, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of North Carolina at Charlotte, USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"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":"Dacheng Tao","raw_affiliation_strings":["FEIT, The University of Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"FEIT, The University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061025828"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":21.3551,"has_fulltext":false,"cited_by_count":709,"citation_normalized_percentile":{"value":0.99548053,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1839","last_page":"1848"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.8791321516036987},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.7729966640472412},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692172527313232},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6007868647575378},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5326622724533081},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.502082109451294},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4965510964393616},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48935431241989136},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4858786463737488},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48115217685699463},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4490990936756134},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43891578912734985},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4234466254711151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32921352982521057},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1160200834274292}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8791321516036987},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.7729966640472412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692172527313232},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6007868647575378},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5326622724533081},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.502082109451294},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4965510964393616},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48935431241989136},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4858786463737488},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48115217685699463},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4490990936756134},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43891578912734985},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4234466254711151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32921352982521057},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1160200834274292},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv.2017.202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2017.202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1947481528","https://openalex.org/W1996219872","https://openalex.org/W2064675550","https://openalex.org/W2104657103","https://openalex.org/W2112193096","https://openalex.org/W2142192571","https://openalex.org/W2151498684","https://openalex.org/W2151750630","https://openalex.org/W2155893237","https://openalex.org/W2174492417","https://openalex.org/W2190656909","https://openalex.org/W2194775991","https://openalex.org/W2231285690","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2288052783","https://openalex.org/W2293453011","https://openalex.org/W2295739661","https://openalex.org/W2340874616","https://openalex.org/W2412393473","https://openalex.org/W2439787475","https://openalex.org/W2463565445","https://openalex.org/W2546696630","https://openalex.org/W2551829638","https://openalex.org/W2741903908","https://openalex.org/W2949197413","https://openalex.org/W2963143606","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963398599","https://openalex.org/W2963477107","https://openalex.org/W2963579811","https://openalex.org/W2963656855","https://openalex.org/W2963668159","https://openalex.org/W2963917086","https://openalex.org/W2963954913","https://openalex.org/W2964023275","https://openalex.org/W2964118342","https://openalex.org/W2964138017","https://openalex.org/W2964303913","https://openalex.org/W4298392976","https://openalex.org/W6629028937","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6682086655","https://openalex.org/W6682508104","https://openalex.org/W6692004142","https://openalex.org/W6697449767","https://openalex.org/W6715144786","https://openalex.org/W6719057275"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2950524887","https://openalex.org/W2883502031","https://openalex.org/W2261271299","https://openalex.org/W2963066927","https://openalex.org/W4280638452","https://openalex.org/W3111811104","https://openalex.org/W4380083739","https://openalex.org/W4285020665","https://openalex.org/W4322208588"],"abstract_inverted_index":{"Visual":[0],"question":[1,118,138],"answering":[2],"(VQA)":[3],"is":[4],"challenging":[5],"because":[6],"it":[7],"requires":[8],"a":[9,35,87,122,149,154],"simultaneous":[10],"understanding":[11],"of":[12,17,23],"both":[13,134],"the":[14,20,30,135,141,164,175],"visual":[15],"content":[16,22],"images":[18,31],"and":[19,32,38,40,69,96,117,137],"textual":[21],"questions.":[24],"The":[25],"approaches":[26],"used":[27],"to":[28,41,58,94,131],"represent":[29],"questions":[33,39],"in":[34,49,78,103,148],"fine-grained":[36,115],"manner":[37],"fuse":[42],"these":[43],"multimodal":[44,81],"features":[45],"play":[46],"key":[47],"roles":[48],"performance.":[50],"Bilinear":[51,90],"pooling":[52,92,112],"based":[53],"models":[54,62],"have":[55],"been":[56],"shown":[57],"outperform":[59],"traditional":[60],"linear":[61],"for":[63,106,157],"VQA,":[64],"but":[65],"their":[66,76],"high-dimensional":[67],"representations":[68],"high":[70],"computational":[71],"complexity":[72],"may":[73],"seriously":[74],"limit":[75],"applicability":[77],"practice.":[79],"For":[80,114],"feature":[82],"fusion,":[83],"here":[84],"we":[85,120],"develop":[86,121],"Multi-modal":[88],"Factorized":[89],"(MFB)":[91],"approach":[93,144],"efficiently":[95],"effectively":[97],"combine":[98],"multi-modal":[99],"features,":[100],"which":[101],"results":[102,161],"superior":[104],"performance":[105,173],"VQA":[107,177],"compared":[108],"with":[109,145,167],"other":[110],"bilinear":[111],"approaches.":[113],"image":[116,136],"representation,":[119],"`co-attention'":[123],"mechanism":[124],"using":[125],"an":[126],"end-to-end":[127],"deep":[128],"network":[129,151],"architecture":[130,152],"jointly":[132],"learn":[133],"attentions.":[139],"Combining":[140],"proposed":[142],"MFB":[143,166],"co-attention":[146,168],"learning":[147],"new":[150,171],"provides":[153],"unified":[155],"model":[156,169],"VQA.":[158],"Our":[159],"experimental":[160],"demonstrate":[162],"that":[163],"single":[165],"achieves":[170],"state-of-theart":[172],"on":[174],"real-world":[176],"dataset.":[178],"Code":[179],"available":[180],"at":[181],"https://github.com/yuzcccc/mfb.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":61},{"year":2024,"cited_by_count":97},{"year":2023,"cited_by_count":96},{"year":2022,"cited_by_count":107},{"year":2021,"cited_by_count":113},{"year":2020,"cited_by_count":99},{"year":2019,"cited_by_count":84},{"year":2018,"cited_by_count":47},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}