{"id":"https://openalex.org/W3006750887","doi":"https://doi.org/10.1109/access.2020.2975093","title":"Multimodal Encoder-Decoder Attention Networks for Visual Question Answering","display_name":"Multimodal Encoder-Decoder Attention Networks for Visual Question Answering","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3006750887","doi":"https://doi.org/10.1109/access.2020.2975093","mag":"3006750887"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2975093","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2975093","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09003229.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09003229.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039492436","display_name":"Chongqing Chen","orcid":"https://orcid.org/0000-0002-0521-0184"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chongqing Chen","raw_affiliation_strings":["School of Information Engineering, Shanghai Maritime University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dezhi Han","orcid":"https://orcid.org/0000-0001-9392-9262"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhi Han","raw_affiliation_strings":["School of Information Engineering, Shanghai Maritime University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100384682","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-0926-4761"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Department of ECE, University of Central Florida, Orlando, USA"],"affiliations":[{"raw_affiliation_string":"Department of ECE, University of Central Florida, Orlando, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039492436"],"corresponding_institution_ids":["https://openalex.org/I96733725"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.9259,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.94850966,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"35662","last_page":"35671"},"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":0.9976999759674072,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9968000054359436,"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":0.7991596460342407},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7063502669334412},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4489330053329468},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3361871838569641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3252168297767639},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06715801358222961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991596460342407},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7063502669334412},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4489330053329468},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3361871838569641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3252168297767639},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06715801358222961}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.2975093","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2975093","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09003229.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:396129956ddb4a8b92cb31d646f83364","is_oa":true,"landing_page_url":"https://doaj.org/article/396129956ddb4a8b92cb31d646f83364","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 35662-35671 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2975093","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2975093","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09003229.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1745623571","display_name":null,"funder_award_id":"61873160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3445439380","display_name":null,"funder_award_id":"61672338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3601181153","display_name":null,"funder_award_id":"Grant 61672338 and Grant 61873160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3006750887.pdf","grobid_xml":"https://content.openalex.org/works/W3006750887.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1924770834","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2156387975","https://openalex.org/W2190656909","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2508429489","https://openalex.org/W2546696630","https://openalex.org/W2554320282","https://openalex.org/W2560730294","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2787119853","https://openalex.org/W2808181286","https://openalex.org/W2890598214","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2949197413","https://openalex.org/W2951619830","https://openalex.org/W2963066927","https://openalex.org/W2963150162","https://openalex.org/W2963176022","https://openalex.org/W2963191264","https://openalex.org/W2963341956","https://openalex.org/W2963383024","https://openalex.org/W2963403868","https://openalex.org/W2963521239","https://openalex.org/W2963717374","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964121744","https://openalex.org/W2964345214","https://openalex.org/W2966683369","https://openalex.org/W2968543045","https://openalex.org/W3002557610","https://openalex.org/W4298392976","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6640212811","https://openalex.org/W6674330103","https://openalex.org/W6682086655","https://openalex.org/W6682889407","https://openalex.org/W6687239747","https://openalex.org/W6728881024","https://openalex.org/W6739901393","https://openalex.org/W6748581942","https://openalex.org/W6752083267","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6766272978","https://openalex.org/W6766645339","https://openalex.org/W6767494712"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,19,45,60],"a":[5,22,27,53,111],"multimodal":[6],"task":[7],"involving":[8],"Computer":[9],"Vision":[10],"(CV)":[11],"and":[12,29,39,74,78,82,117,152],"Natural":[13],"Language":[14],"Processing":[15],"(NLP),":[16],"the":[17,34,40,46,104,115,125,137,149,154,165,176],"goal":[18],"to":[20,174],"establish":[21],"high-efficiency":[23],"VQA":[24,134],"model.":[25],"Learning":[26],"fine-grained":[28],"simultaneous":[30],"understanding":[31],"of":[32,37,43,48,65,106,119,162],"both":[33],"visual":[35],"content":[36,42],"images":[38],"textual":[41],"questions":[44],"heart":[47],"VQA.":[49],"In":[50],"this":[51],"paper,":[52],"novel":[54],"Multimodal":[55,66],"Encoder-Decoder":[56,67],"Attention":[57,68],"Networks":[58],"(MEDAN)":[59],"proposed.":[61],"The":[62],"MEDAN":[63,131],"consists":[64],"(MEDA)":[69],"layers":[70],"cascaded":[71],"in":[72,88,94],"depth,":[73],"can":[75],"capture":[76],"rich":[77],"reasonable":[79],"question":[80,89],"features":[81,84],"image":[83],"by":[85],"associating":[86],"keywords":[87],"with":[90,153],"important":[91],"object":[92],"regions":[93],"image.":[95],"Each":[96],"MEDA":[97],"layer":[98],"contains":[99],"an":[100,159],"Encoder":[101],"module":[102,113],"modeling":[103,114],"self-attention":[105,118],"questions,":[107],"as":[108,110],"well":[109],"Decoder":[112],"question-guided-attention":[116],"images.":[120],"Experimental":[121],"evaluation":[122],"results":[123],"on":[124,148,164],"benchmark":[126],"VQA-v2":[127],"dataset":[128],"demonstrate":[129],"that":[130],"achieves":[132],"state-of-the-art":[133],"performance.":[135],"With":[136],"Adam":[138],"solver,":[139,156],"our":[140],"best":[141],"single":[142],"model":[143],"delivers":[144],"71.01%":[145],"overall":[146,160],"accuracy":[147,161],"test-std":[150],"set,":[151],"AdamW":[155],"we":[157],"achieve":[158],"70.76%":[163],"test-dev":[166],"set.":[167],"Additionally,":[168],"extensive":[169],"ablation":[170],"studies":[171],"are":[172],"conducted":[173],"explore":[175],"reasons":[177],"for":[178],"MEDAN's":[179],"effectiveness.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}