{"id":"https://openalex.org/W4285280022","doi":"https://doi.org/10.1109/tcsvt.2022.3189242","title":"Knowledge-Based Visual Question Generation","display_name":"Knowledge-Based Visual Question Generation","publication_year":2022,"publication_date":"2022-07-12","ids":{"openalex":"https://openalex.org/W4285280022","doi":"https://doi.org/10.1109/tcsvt.2022.3189242"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3189242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3189242","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5049131355","display_name":"Jiayuan Xie","orcid":"https://orcid.org/0000-0002-6833-7879"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Xie","raw_affiliation_strings":["School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103013773","display_name":"Wenhao Fang","orcid":"https://orcid.org/0009-0001-2082-6649"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Fang","raw_affiliation_strings":["School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Guangzhou, China","Pazhou Laboratory, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1767-789X","affiliations":[{"raw_affiliation_string":"School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"Pazhou Laboratory, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061381102","display_name":"Qingbao Huang","orcid":"https://orcid.org/0000-0001-7691-347X"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingbao Huang","raw_affiliation_strings":["School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Guangzhou, China","School of Electrical Engineering, the Guangxi Key Laboratory of Multimedia Communications and Network Technology, and the Institute of Artificial Intelligence, Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0000-0001-7691-347X","affiliations":[{"raw_affiliation_string":"School of Software Engineering and the Key Laboratory of Big Data and Intelligent Robot, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electrical Engineering, the Guangxi Key Laboratory of Multimedia Communications and Network Technology, and the Institute of Artificial Intelligence, Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-3370-471X","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.447,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90429676,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":"11","first_page":"7547","last_page":"7558"},"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":0.9905999898910522,"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":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.8202742338180542},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5957040786743164},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.577839732170105},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5588194131851196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5454673171043396},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5428317785263062},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5204070806503296},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.47343114018440247},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.325093150138855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202742338180542},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5957040786743164},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.577839732170105},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5588194131851196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5454673171043396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5428317785263062},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5204070806503296},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.47343114018440247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.325093150138855},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3189242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3189242","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1473307615","display_name":null,"funder_award_id":"2022GXNSFAA035627","funder_id":"https://openalex.org/F4320322768","funder_display_name":"Natural Science Foundation of Guangxi Province"},{"id":"https://openalex.org/G2820940073","display_name":null,"funder_award_id":"x2rjD2220050","funder_id":"https://openalex.org/F4320323430","funder_display_name":"Central University of Technology"},{"id":"https://openalex.org/G8189774080","display_name":null,"funder_award_id":"62076100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8718620462","display_name":null,"funder_award_id":"2020B0101100002","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322768","display_name":"Natural Science Foundation of Guangxi Province","ror":null},{"id":"https://openalex.org/F4320323430","display_name":"Central University of Technology","ror":"https://ror.org/033z08192"},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W627986001","https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2073587810","https://openalex.org/W2101105183","https://openalex.org/W2116341502","https://openalex.org/W2133459682","https://openalex.org/W2151035455","https://openalex.org/W2160204597","https://openalex.org/W2250539671","https://openalex.org/W2521114121","https://openalex.org/W2560730294","https://openalex.org/W2561296180","https://openalex.org/W2561529111","https://openalex.org/W2808021740","https://openalex.org/W2887991371","https://openalex.org/W2898071615","https://openalex.org/W2962749469","https://openalex.org/W2963087285","https://openalex.org/W2963187678","https://openalex.org/W2963351776","https://openalex.org/W2963477107","https://openalex.org/W2963976294","https://openalex.org/W2964065333","https://openalex.org/W2964303913","https://openalex.org/W2964324871","https://openalex.org/W2981165461","https://openalex.org/W3009992206","https://openalex.org/W3019023591","https://openalex.org/W3034787499","https://openalex.org/W3047995861","https://openalex.org/W3092692431","https://openalex.org/W3106925514","https://openalex.org/W3136792391","https://openalex.org/W3173771949","https://openalex.org/W3195155620","https://openalex.org/W3206904785","https://openalex.org/W4245367419","https://openalex.org/W6620100662","https://openalex.org/W6631190155","https://openalex.org/W6634232107","https://openalex.org/W6639432524","https://openalex.org/W6682086655","https://openalex.org/W6686883664","https://openalex.org/W6752944286"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297","https://openalex.org/W2062212388"],"abstract_inverted_index":{"Visual":[0],"question":[1,26,51],"generation":[2,52],"task":[3],"aims":[4],"to":[5,35,40,62,76,100,123,129,159,163],"generate":[6,63,164],"meaningful":[7],"questions":[8],"about":[9],"an":[10,13,120],"image":[11,24],"targeting":[12],"answer.":[14,147],"Existing":[15],"methods":[16],"focus":[17],"on":[18,168],"the":[19,23,84,94,97,101,105,125,130,133,139,146,169,176,180],"visual":[20,36,50,57,67,102,152],"concepts":[21,58,153],"in":[22,38,83,104],"for":[25,115],"generation.":[27],"However,":[28],"humans":[29],"inevitably":[30],"use":[31],"their":[32],"knowledge":[33,61,95,112,127,156],"related":[34,99,128],"objects":[37,103],"images":[39],"construct":[41],"questions.":[42,64,165],"In":[43],"this":[44,116],"paper,":[45],"we":[46,69,91,118],"propose":[47],"a":[48,71,160],"knowledge-based":[49],"model":[53,75,178],"that":[54,108,138,175],"can":[55,142],"integrate":[56],"and":[59,154,171],"non-visual":[60,89,155],"To":[65,86],"obtain":[66,77,87],"concepts,":[68],"utilize":[70],"pre-trained":[72],"object":[73,82],"detection":[74],"object-level":[78,149],"features":[79],"of":[80],"each":[81],"image.":[85,106],"useful":[88],"knowledge,":[90,135],"first":[92],"retrieve":[93],"from":[96,132],"knowledge-base":[98],"Considering":[107],"not":[109],"all":[110],"retrieved":[111,134],"is":[113],"helpful":[114],"task,":[117],"introduce":[119],"answer-aware":[121],"module":[122,162],"capture":[124],"candidate":[126],"answer":[131],"which":[136],"ensures":[137],"generated":[140],"content":[141],"be":[143],"targeted":[144],"at":[145],"Finally,":[148],"representations":[150],"containing":[151],"are":[157],"sent":[158],"decoder":[161],"Extensive":[166],"experiments":[167],"FVQA":[170],"KBVQA":[172],"datasets":[173],"show":[174],"proposed":[177],"outperforms":[179],"state-of-the-art":[181],"models.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}