{"id":"https://openalex.org/W3019617850","doi":"https://doi.org/10.1109/jstsp.2020.2989701","title":"Learning to Recognize Visual Concepts for Visual Question Answering With Structural Label Space","display_name":"Learning to Recognize Visual Concepts for Visual Question Answering With Structural Label Space","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3019617850","doi":"https://doi.org/10.1109/jstsp.2020.2989701","mag":"3019617850"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2020.2989701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2020.2989701","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","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/A5001133932","display_name":"Difei Gao","orcid":"https://orcid.org/0000-0001-8494-3492"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Difei Gao","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8494-3492","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614962","display_name":"Ruiping Wang","orcid":"https://orcid.org/0000-0003-1830-2595"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiping Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1830-2595","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050297728","display_name":"Shiguang Shan","orcid":"https://orcid.org/0000-0002-8348-392X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiguang Shan","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8348-392X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083420537","display_name":"Xilin Chen","orcid":"https://orcid.org/0000-0003-3024-4404"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3024-4404","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7693,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.70382871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"14","issue":"3","first_page":"494","last_page":"505"},"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":0.9991999864578247,"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":0.9962999820709229,"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/question-answering","display_name":"Question answering","score":0.8227245807647705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6781768798828125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5642651915550232},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5458160638809204},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.477030485868454},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4238862693309784},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.355776846408844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.333782434463501}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8227245807647705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6781768798828125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5642651915550232},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5458160638809204},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.477030485868454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4238862693309784},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.355776846408844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.333782434463501},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2020.2989701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2020.2989701","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2722639632","display_name":null,"funder_award_id":"61922080","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3848188706","display_name":null,"funder_award_id":"U19B2036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5852522933","display_name":"\u5f00\u653e\u573a\u666f\u4e2d\u5927\u89c4\u6a21\u7269\u4f53\u8bc6\u522b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61772500","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":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1575833922","https://openalex.org/W1620204465","https://openalex.org/W1933349210","https://openalex.org/W2027869746","https://openalex.org/W2063862666","https://openalex.org/W2081580037","https://openalex.org/W2117225622","https://openalex.org/W2143042756","https://openalex.org/W2157331557","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2560730294","https://openalex.org/W2570343428","https://openalex.org/W2597425697","https://openalex.org/W2613718673","https://openalex.org/W2734498959","https://openalex.org/W2737766105","https://openalex.org/W2753474648","https://openalex.org/W2760103357","https://openalex.org/W2916723116","https://openalex.org/W2938082352","https://openalex.org/W2962685807","https://openalex.org/W2962716332","https://openalex.org/W2962779575","https://openalex.org/W2963082899","https://openalex.org/W2963143606","https://openalex.org/W2963150697","https://openalex.org/W2963191264","https://openalex.org/W2963223524","https://openalex.org/W2963224792","https://openalex.org/W2963383024","https://openalex.org/W2963644680","https://openalex.org/W2963668159","https://openalex.org/W2963770662","https://openalex.org/W2963907629","https://openalex.org/W2963954913","https://openalex.org/W2964118342","https://openalex.org/W2964138017","https://openalex.org/W4289421997","https://openalex.org/W4297749157","https://openalex.org/W6634232107","https://openalex.org/W6636378376","https://openalex.org/W6677731448","https://openalex.org/W6680823260","https://openalex.org/W6719057275","https://openalex.org/W6738893770","https://openalex.org/W6740674931","https://openalex.org/W6740863234","https://openalex.org/W6743792510","https://openalex.org/W6743842864","https://openalex.org/W6748270630","https://openalex.org/W6754733129","https://openalex.org/W6761069331"],"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/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"Solving":[0],"visual":[1,10,16,83,117,192,291],"question":[2],"answering":[3],"(VQA)":[4],"task":[5],"requires":[6],"recognizing":[7],"many":[8],"diverse":[9],"concepts":[11,17,25,54,65],"as":[12,85],"the":[13,68,86,104,138,141,162,169,191,202,207,216,261,268,279,290,296,299],"answer.":[14],"These":[15],"contain":[18],"rich":[19],"structural":[20,157,281],"semantic":[21,58,105,187,245],"meanings,":[22],"e.g.,":[23,223],"some":[24,35],"in":[26,88,100,131,143,152,171,194],"VQA":[27,134,195,300],"are":[28,38,175],"highly":[29],"related":[30,230,237],"(e.g.,":[31,41],"red":[32,42],"&":[33,43],"blue),":[34],"of":[36,70,107,140,164,186,206,221,244,256,298],"them":[37],"less":[39],"relevant":[40,64,219,250,264],"standing).":[44],"It":[45],"is":[46,126,228],"very":[47],"natural":[48],"for":[49,249],"humans":[50],"to":[51,60,81,128,136,160,177,181,200,214,231,252,259,266],"efficiently":[52,288],"learn":[53,289],"by":[55],"utilizing":[56],"their":[57,182],"meanings":[59,106],"concentrate":[61],"on":[62,273],"distinguishing":[63],"and":[66,102,204,258,284,294],"eliminate":[67],"disturbance":[69],"irrelevant":[71],"concepts.":[72],"However,":[73],"previous":[74],"works":[75],"usually":[76],"use":[77],"a":[78,89,115,155],"simple":[79],"MLP":[80],"output":[82],"concept":[84,292],"answer":[87,144],"flat":[90],"label":[91,158,173,282],"space":[92,159,174,283],"that":[93,278],"treats":[94],"all":[95],"labels":[96,142,170],"equally,":[97],"causing":[98],"limitations":[99],"representing":[101],"using":[103],"labels.":[108],"To":[109],"address":[110],"this":[111],"issue,":[112],"we":[113,147],"propose":[114],"novel":[116,156],"recognition":[118,293],"module":[119,286],"named":[120],"Dynamic":[121],"Concept":[122],"Recognizer":[123],"(DCR),":[124],"which":[125],"easy":[127],"be":[129],"plugged":[130],"an":[132],"attention-based":[133],"model,":[135],"utilize":[137],"semantics":[139,165],"prediction.":[145],"Concretely,":[146],"introduce":[148],"two":[149],"key":[150],"features":[151],"DCR:":[153],"1)":[154],"depict":[161],"difference":[163],"between":[166,218,263],"concepts,":[167,222],"where":[168],"new":[172],"assigned":[176],"different":[178],"groups":[179,220,251],"according":[180],"meanings.":[183],"This":[184,242],"type":[185,243],"information":[188,246],"helps":[189,247],"decompose":[190],"recognizer":[193],"into":[196],"multiple":[197],"specialized":[198],"sub-recognizers":[199,248,265],"improve":[201],"capacity":[203],"efficiency":[205],"recognizer.":[208],"2)":[209],"A":[210],"feature":[211],"attention":[212],"mechanism":[213],"capture":[215],"similarity":[217],"human-related":[224],"group":[225,238],"\u201cchef,":[226],"waiter\u201d":[227],"more":[229],"\u201cswimming,":[232],"running,":[233],"etc.\u201d":[234],"than":[235],"scene":[236],"\u201csunny,":[239],"rainy,":[240],"etc.\u201d.":[241],"adaptively":[253],"share":[254,260],"part":[255],"modules":[257],"knowledge":[262],"facilitate":[267],"learning":[269],"procedure.":[270],"Extensive":[271],"experiments":[272],"several":[274],"datasets":[275],"have":[276],"shown":[277],"proposed":[280],"DCR":[285],"can":[287],"benefit":[295],"performance":[297],"model.":[301]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}