{"id":"https://openalex.org/W3037773948","doi":"https://doi.org/10.1109/tpami.2020.3004830","title":"MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network","display_name":"MRA-Net: Improving VQA Via Multi-Modal Relation Attention Network","publication_year":2020,"publication_date":"2020-06-25","ids":{"openalex":"https://openalex.org/W3037773948","doi":"https://doi.org/10.1109/tpami.2020.3004830","mag":"3037773948","pmid":"https://pubmed.ncbi.nlm.nih.gov/32750794"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2020.3004830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3004830","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5063303076","display_name":"Liang Peng","orcid":"https://orcid.org/0000-0002-0576-1429"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Peng","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","Institute of Electronic and Information Engineering, University of Electronic Science and Technology of China (UESTC), Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-5070-4511","affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Institute of Electronic and Information Engineering, University of Electronic Science and Technology of China (UESTC), Guangdong, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037117576","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0002-9318-0084"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Huang","raw_affiliation_strings":["University of Queensland, St Lucia, QLD, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9738-4949","affiliations":[{"raw_affiliation_string":"University of Queensland, St Lucia, QLD, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0207,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.97987933,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"44","issue":"1","first_page":"318","last_page":"329"},"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":0.9969000220298767,"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":0.9936000108718872,"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":0.7715834379196167},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7416378259658813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7236117124557495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6659850478172302},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5805399417877197},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.49981260299682617},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.47955843806266785},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4511137306690216},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4460311532020569},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4305555522441864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4148152768611908},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1989598572254181}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7715834379196167},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7416378259658813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236117124557495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6659850478172302},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5805399417877197},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49981260299682617},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47955843806266785},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4511137306690216},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4460311532020569},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4305555522441864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4148152768611908},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1989598572254181},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2020.3004830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2020.3004830","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:32750794","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32750794","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3623292902","display_name":null,"funder_award_id":"61632007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5133417063","display_name":null,"funder_award_id":"2018AAA0102200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6438814647","display_name":null,"funder_award_id":"ZYGX2019Z015","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2546696630","https://openalex.org/W2560730294","https://openalex.org/W2591669147","https://openalex.org/W2593190442","https://openalex.org/W2597425697","https://openalex.org/W2732016772","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2755385356","https://openalex.org/W2765440071","https://openalex.org/W2766237723","https://openalex.org/W2777602943","https://openalex.org/W2803620531","https://openalex.org/W2807935099","https://openalex.org/W2807941860","https://openalex.org/W2884326683","https://openalex.org/W2885380450","https://openalex.org/W2887712318","https://openalex.org/W2887967003","https://openalex.org/W2896603934","https://openalex.org/W2896902935","https://openalex.org/W2904323922","https://openalex.org/W2916723116","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963383024","https://openalex.org/W2963770662","https://openalex.org/W2963954913","https://openalex.org/W2964072591","https://openalex.org/W2964137974","https://openalex.org/W2964199361","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2979382951","https://openalex.org/W2981578638","https://openalex.org/W3003735286","https://openalex.org/W3004349648","https://openalex.org/W3005971801","https://openalex.org/W3033514332","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6695676441","https://openalex.org/W6717487601","https://openalex.org/W6728881024","https://openalex.org/W6729948091","https://openalex.org/W6738893770","https://openalex.org/W6743842864","https://openalex.org/W6748581942","https://openalex.org/W6752083267","https://openalex.org/W6752404935","https://openalex.org/W6754553780"],"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":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4],"a":[5,100,130],"task":[6],"to":[7,13,27,76,120,203],"answer":[8],"natural":[9],"language":[10],"questions":[11,68],"tied":[12],"the":[14,30,36,58,84,138,156,166,185,193,205],"content":[15],"of":[16,74,87,173,189,208],"visual":[17,32,44,88,118,147,175,181,186],"images.":[18],"Most":[19],"recent":[20],"VQA":[21,103],"approaches":[22],"usually":[23],"apply":[24],"attention":[25,134,149],"mechanism":[26],"focus":[28],"on":[29,213],"relevant":[31],"objects":[33,39,163],"and/or":[34],"consider":[35],"relations":[37,60,119,141,161,176],"between":[38,61,142,162],"via":[40],"off-the-shelf":[41],"methods":[42],"in":[43,65],"relation":[45,92,133,148,201],"reasoning.":[46],"However,":[47],"they":[48,55,81],"still":[49],"suffer":[50],"from":[51],"several":[52],"drawbacks.":[53],"First,":[54],"mostly":[56],"model":[57,113,195,229],"simple":[59],"objects,":[62],"which":[63,136],"results":[64],"many":[66],"complicated":[67],"cannot":[69],"be":[70],"answered":[71],"correctly,":[72],"because":[73],"failing":[75],"provide":[77,177],"sufficient":[78],"knowledge.":[79],"Second,":[80],"seldom":[82],"leverage":[83],"harmony":[85],"cooperation":[86],"appearance":[89,198],"feature":[90,199,202],"and":[91,117,123,158,179,223],"feature.":[93],"To":[94],"solve":[95],"these":[96],"problems,":[97],"we":[98,127],"propose":[99],"novel":[101],"end-to-end":[102],"model,":[104],"termed":[105],"Multi-modal":[106],"Relation":[107],"Attention":[108],"Network":[109],"(MRA-Net).":[110],"The":[111],"proposed":[112,194,228],"explores":[114],"both":[115],"textual":[116],"improve":[121],"performance":[122],"interpretability.":[124],"In":[125],"specific,":[126],"devise":[128],"1)":[129],"self-guided":[131],"word":[132],"scheme,":[135],"explore":[137],"latent":[139],"semantic":[140],"words;":[143],"2)":[144],"two":[145,206],"question-adaptive":[146],"modules":[150],"that":[151,226],"can":[152],"extract":[153],"not":[154],"only":[155],"fine-grained":[157],"precise":[159],"binary":[160],"but":[164],"also":[165,196],"more":[167,178],"sophisticated":[168],"trinary":[169],"relations.":[170],"Both":[171],"kinds":[172],"question-related":[174],"deeper":[180],"semantics,":[182],"thereby":[183],"improving":[184],"reasoning":[187],"ability":[188],"question":[190],"answering.":[191],"Furthermore,":[192],"combines":[197],"with":[200],"reconcile":[204],"types":[207],"features":[209],"effectively.":[210],"Extensive":[211],"experiments":[212],"five":[214],"large":[215],"benchmark":[216],"datasets,":[217],"VQA-1.0,":[218],"VQA-2.0,":[219],"COCO-QA,":[220],"VQA-CP":[221],"v2,":[222],"TDIUC,":[224],"demonstrate":[225],"our":[227],"outperforms":[230],"state-of-the-art":[231],"approaches.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}