{"id":"https://openalex.org/W4280635869","doi":"https://doi.org/10.1109/icme52920.2022.9859766","title":"Joint Learning of Object Graph and Relation Graph for Visual Question Answering","display_name":"Joint Learning of Object Graph and Relation Graph for Visual Question Answering","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4280635869","doi":"https://doi.org/10.1109/icme52920.2022.9859766"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859766","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5100348632","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-7712-0890"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University,China","School of Electronic and Computer Engineering, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342504","display_name":"Xu Li","orcid":"https://orcid.org/0009-0004-7507-4669"},"institutions":[{"id":"https://openalex.org/I4210159958","display_name":"Cognitive Research (United States)","ror":"https://ror.org/04s361q55","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159958"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["Baidu Research,Cognitive Computing Lab,China","Cognitive Computing Lab, Baidu Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,Cognitive Computing Lab,China","institution_ids":["https://openalex.org/I98301712","https://openalex.org/I4210159958"]},{"raw_affiliation_string":"Cognitive Computing Lab, Baidu Research, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015585821","display_name":"Belhal Karimi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159958","display_name":"Cognitive Research (United States)","ror":"https://ror.org/04s361q55","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159958"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Belhal Karimi","raw_affiliation_strings":["Baidu Research,Cognitive Computing Lab,China","Cognitive Computing Lab, Baidu Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,Cognitive Computing Lab,China","institution_ids":["https://openalex.org/I98301712","https://openalex.org/I4210159958"]},{"raw_affiliation_string":"Cognitive Computing Lab, Baidu Research, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332984","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0002-9765-4523"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University,China","Peng Cheng Laboratory, Shenzhen, China","School of Electronic and Computer Engineering, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101074936","display_name":"Mingming Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159958","display_name":"Cognitive Research (United States)","ror":"https://ror.org/04s361q55","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159958"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Mingming Sun","raw_affiliation_strings":["Baidu Research,Cognitive Computing Lab,China","Cognitive Computing Lab, Baidu Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research,Cognitive Computing Lab,China","institution_ids":["https://openalex.org/I98301712","https://openalex.org/I4210159958"]},{"raw_affiliation_string":"Cognitive Computing Lab, Baidu Research, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1797,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85632143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"06"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9983000159263611,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980999827384949,"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/interpretability","display_name":"Interpretability","score":0.7024768590927124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6999184489250183},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6580499410629272},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.512948215007782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5114046931266785},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.48075196146965027},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4731025695800781},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.45525866746902466},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4251711964607239},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3849060535430908},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3479422926902771},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25429677963256836}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7024768590927124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6999184489250183},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6580499410629272},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.512948215007782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5114046931266785},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.48075196146965027},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4731025695800781},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.45525866746902466},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4251711964607239},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3849060535430908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3479422926902771},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25429677963256836},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/icme52920.2022.9859766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859766","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4279305079","display_name":null,"funder_award_id":"2019B1515120049,2020Blll1340056","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2250539671","https://openalex.org/W2463565445","https://openalex.org/W2528417318","https://openalex.org/W2788405243","https://openalex.org/W2896457183","https://openalex.org/W2948519073","https://openalex.org/W2950898568","https://openalex.org/W2963466731","https://openalex.org/W2966608828","https://openalex.org/W2987086322","https://openalex.org/W2998356391","https://openalex.org/W3004349648","https://openalex.org/W3035017890","https://openalex.org/W3089709427","https://openalex.org/W3119150707","https://openalex.org/W3198659451","https://openalex.org/W4285723986","https://openalex.org/W4287728378","https://openalex.org/W4288286281","https://openalex.org/W4297749157","https://openalex.org/W6690815549","https://openalex.org/W6719057275","https://openalex.org/W6748193433","https://openalex.org/W6748270630","https://openalex.org/W6755207826","https://openalex.org/W6765591853","https://openalex.org/W6766545348","https://openalex.org/W6774617867","https://openalex.org/W6780471797","https://openalex.org/W6783795341","https://openalex.org/W6788354309"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"Modeling":[0],"visual":[1],"question":[2],"answering":[3],"(VQA)":[4],"through":[5],"scene":[6,52,83,91],"graphs":[7,95],"can":[8,74],"significantly":[9],"improve":[10],"the":[11,90,114,120,128,139,162],"reasoning":[12,23],"accuracy":[13],"and":[14,56,101,145,157],"interpretability.":[15],"However,":[16],"existing":[17],"models":[18,44],"answer":[19],"poorly":[20],"for":[21],"complex":[22],"questions":[24],"with":[25,96,123],"attributes":[26],"or":[27,34],"relations,":[28],"which":[29,73,112,126],"causes":[30],"false":[31],"attribute":[32,57,124],"selection":[33],"missing":[35],"relation":[36,55],"in":[37,51],"Figure":[38],"1(a).":[39],"It":[40],"is":[41],"because":[42],"these":[43],"cannot":[45],"balance":[46],"all":[47],"kinds":[48],"of":[49,161],"information":[50,140],"graphs,":[53],"neglecting":[54],"information.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,87,104],"introduce":[63],"a":[64,76,106,134],"novel":[65],"Dual":[66],"Message-passing":[67],"enhanced":[68],"Graph":[69],"Neural":[70],"Net-work":[71],"(DM-GNN),":[72],"obtain":[75],"balanced":[77],"represen-tation":[78],"by":[79],"properly":[80],"encoding":[81],"multi-scale":[82],"graph":[84,92],"infor-mation.":[85],"Specifically,":[86],"(i)":[88],"transform":[89],"into":[93],"two":[94],"diversified":[97],"focuses":[98],"on":[99,151],"objects":[100],"relations;":[102],"Then":[103],"design":[105],"dual":[107],"structure":[108],"to":[109,137],"encode":[110],"them,":[111],"in-creases":[113],"weights":[115,129],"from":[116,130],"relations":[117,144],"(ii)":[118],"fuse":[119],"encoder":[121],"out-put":[122],"features,":[125],"increases":[127],"attributes;":[131],"(iii)":[132],"propose":[133],"message-passing":[135],"mechanism":[136],"en-hance":[138],"transfer":[141],"between":[142],"objects,":[143],"attributes.":[146],"We":[147],"conduct":[148],"extensive":[149],"experiments":[150],"datasets":[152],"in-cluding":[153],"GQA,":[154],"VG,":[155],"motif-VG":[156],"achieve":[158],"new":[159],"state":[160],"art.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}