{"id":"https://openalex.org/W2963976294","doi":"https://doi.org/10.1109/cvpr.2018.00640","title":"Visual Question Generation as Dual Task of Visual Question Answering","display_name":"Visual Question Generation as Dual Task of Visual Question Answering","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2963976294","doi":"https://doi.org/10.1109/cvpr.2018.00640","mag":"2963976294"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2018.00640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"type":"preprint","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/A5100610029","display_name":"Yikang Li","orcid":"https://orcid.org/0000-0003-4666-9642"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yikang Li","raw_affiliation_strings":["1The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"1The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018181","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674"},"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":"Nan Duan","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033444412","display_name":"Bolei Zhou","orcid":"https://orcid.org/0000-0003-4030-0684"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bolei Zhou","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032558155","display_name":"Xiao Chu","orcid":"https://orcid.org/0000-0001-9844-6841"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Chu","raw_affiliation_strings":["1The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"1The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"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":"Wanli Ouyang","raw_affiliation_strings":["University of Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444820","display_name":"Xiaogang Wang","orcid":"https://orcid.org/0000-0002-7929-5889"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaogang Wang","raw_affiliation_strings":["1The Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"1The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100701572","display_name":"Ming Zhou","orcid":"https://orcid.org/0000-0002-2551-2964"},"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":"Ming Zhou","raw_affiliation_strings":["Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100610029"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":15.7376968,"has_fulltext":false,"cited_by_count":174,"citation_normalized_percentile":{"value":0.98777881,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6116","last_page":"6124"},"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":0.9898999929428101,"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":0.9441277980804443},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7819582223892212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7207332849502563},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6296816468238831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5591776967048645},{"id":"https://openalex.org/keywords/invertible-matrix","display_name":"Invertible matrix","score":0.5449016690254211},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3661925792694092},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3651088774204254},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14918386936187744}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.9441277980804443},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7819582223892212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207332849502563},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6296816468238831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591776967048645},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.5449016690254211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3661925792694092},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3651088774204254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14918386936187744},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2018.00640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W182831726","https://openalex.org/W1486649854","https://openalex.org/W1522301498","https://openalex.org/W1530781137","https://openalex.org/W1574901103","https://openalex.org/W1889081078","https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133512280","https://openalex.org/W2142192571","https://openalex.org/W2154652894","https://openalex.org/W2155027007","https://openalex.org/W2190656909","https://openalex.org/W2194775991","https://openalex.org/W2412400526","https://openalex.org/W2463565445","https://openalex.org/W2532034655","https://openalex.org/W2546938941","https://openalex.org/W2560730294","https://openalex.org/W2561296180","https://openalex.org/W2561715562","https://openalex.org/W2605736949","https://openalex.org/W2607059968","https://openalex.org/W2624022918","https://openalex.org/W2732016772","https://openalex.org/W2949197413","https://openalex.org/W2950761309","https://openalex.org/W2962793481","https://openalex.org/W2963191264","https://openalex.org/W2963351776","https://openalex.org/W2963383024","https://openalex.org/W2963560969","https://openalex.org/W2963649796","https://openalex.org/W2963668159","https://openalex.org/W2963717374","https://openalex.org/W2963758027","https://openalex.org/W2964121744","https://openalex.org/W2964136408","https://openalex.org/W2964236999","https://openalex.org/W6610616021","https://openalex.org/W6629028937","https://openalex.org/W6631190155","https://openalex.org/W6631910717","https://openalex.org/W6639432524","https://openalex.org/W6682631176","https://openalex.org/W6683204974","https://openalex.org/W6687239747","https://openalex.org/W6687483927","https://openalex.org/W6691503852","https://openalex.org/W6719057275","https://openalex.org/W6728881024","https://openalex.org/W6729383884","https://openalex.org/W6730662052","https://openalex.org/W6739136287","https://openalex.org/W6746311623","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2805599431","https://openalex.org/W2961085424","https://openalex.org/W2361152157","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W207304934","https://openalex.org/W2970044932","https://openalex.org/W4377703168","https://openalex.org/W1560657467","https://openalex.org/W2153711059"],"abstract_inverted_index":{"Visual":[0],"question":[1,6,45,52,116],"answering":[2,53],"(VQA)":[3],"and":[4,66,75,108,121,129,147],"visual":[5],"generation":[7,46],"(VQG)":[8],"are":[9,19],"two":[10,85],"trending":[11],"topics":[12],"in":[13],"the":[14,37,56,103,123,127,135,139],"computer":[15],"vision,":[16],"but":[17],"they":[18],"usually":[20],"explored":[21],"separately":[22],"despite":[23],"their":[24],"intrinsic":[25],"complementary":[26],"relationship.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31],"propose":[32],"an":[33],"end-to-end":[34],"unified":[35],"model,":[36],"Invertible":[38],"Question":[39],"Answering":[40],"Network":[41],"(iQAN),":[42],"to":[43,54],"introduce":[44],"as":[47,93,119],"a":[48,99],"dual":[49,77,90,158],"task":[50,78],"of":[51,102,138,166],"improve":[55,163],"VQA":[57,74,143,169],"performance.":[58],"With":[59],"our":[60,70,88,96,132,156],"proposed":[61,89,157],"invertible":[62],"bilinear":[63],"fusion":[64],"module":[65],"parameter":[67],"sharing":[68],"scheme,":[69],"iQAN":[71,112,133],"can":[72,113,161],"accomplish":[73],"its":[76],"VQG":[79],"simultaneously.":[80],"By":[81],"jointly":[82],"trained":[83],"on":[84,126],"tasks":[86],"with":[87],"regularizes":[91],"(termed":[92],"Dual":[94],"Training),":[95],"model":[97,164],"has":[98],"better":[100],"understanding":[101],"interactions":[104],"among":[105],"images,":[106],"questions":[107],"answers.":[109],"After":[110],"training,":[111],"take":[114],"either":[115],"or":[117],"answer":[118],"input,":[120],"output":[122],"counterpart.":[124],"Evaluated":[125],"CLEVR":[128],"VQA2":[130],"datasets,":[131],"improves":[134],"top-1":[136],"accuracy":[137],"prior":[140],"art":[141],"MUTAN":[142],"method":[144],"by":[145],"1.33%":[146],"0.88%":[148],"(absolute":[149],"increase)":[150],"respectiely.":[151],"We":[152],"also":[153],"show":[154],"that":[155],"training":[159],"framework":[160],"consistently":[162],"performances":[165],"many":[167],"popular":[168],"architectures":[170],"<sup":[171],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[173],".":[174]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":1}],"updated_date":"2026-01-15T23:16:33.117629","created_date":"2025-10-10T00:00:00"}