{"id":"https://openalex.org/W3164103590","doi":"https://doi.org/10.2298/csis201120032l","title":"Multimodal encoders and decoders with gate attention for visual question answering","display_name":"Multimodal encoders and decoders with gate attention for visual question answering","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3164103590","doi":"https://doi.org/10.2298/csis201120032l","mag":"3164103590"},"language":"en","primary_location":{"id":"doi:10.2298/csis201120032l","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis201120032l","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142100032L","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142100032L","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100360524","display_name":"Haiyan Li","orcid":"https://orcid.org/0000-0002-8684-1083"},"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":"Haiyan Li","raw_affiliation_strings":["School of Information Engineering, Shanghai Maritime University Shanghai, China","School of Information Engineering, Shanghai Maritime University Shanghai,201306, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Shanghai Maritime University Shanghai, China","institution_ids":["https://openalex.org/I96733725"]},{"raw_affiliation_string":"School of Information Engineering, Shanghai Maritime University Shanghai,201306, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101744803","display_name":"Dezhi Han","orcid":"https://orcid.org/0000-0001-8861-5461"},"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":"Dezhi Han","raw_affiliation_strings":["School of Information Engineering, Shanghai Maritime University Shanghai, China","School of Information Engineering, Shanghai Maritime University Shanghai,201306, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Shanghai Maritime University Shanghai, China","institution_ids":["https://openalex.org/I96733725"]},{"raw_affiliation_string":"School of Information Engineering, Shanghai Maritime University Shanghai,201306, China","institution_ids":["https://openalex.org/I96733725"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101744803"],"corresponding_institution_ids":["https://openalex.org/I96733725"],"apc_list":null,"apc_paid":null,"fwci":0.3843,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59598039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":"3","first_page":"1023","last_page":"1040"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9912999868392944,"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":0.9902999997138977,"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/computer-science","display_name":"Computer science","score":0.8837958574295044},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6790683269500732},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5634738802909851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5392132997512817},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.532403290271759},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42606133222579956},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42020338773727417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41637086868286133},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4109247922897339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8837958574295044},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6790683269500732},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5634738802909851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5392132997512817},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.532403290271759},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42606133222579956},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42020338773727417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41637086868286133},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4109247922897339},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2298/csis201120032l","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis201120032l","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142100032L","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.2298/csis201120032l","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis201120032l","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142100032L","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3164103590.pdf","grobid_xml":"https://content.openalex.org/works/W3164103590.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2181682482","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2463565445","https://openalex.org/W2546696630","https://openalex.org/W2560920409","https://openalex.org/W2744926832","https://openalex.org/W2745461083","https://openalex.org/W2747623286","https://openalex.org/W2767794011","https://openalex.org/W2787119853","https://openalex.org/W2896457183","https://openalex.org/W2926818924","https://openalex.org/W2949197413","https://openalex.org/W2961087419","https://openalex.org/W2963176022","https://openalex.org/W2963383024","https://openalex.org/W2963521239","https://openalex.org/W2963622213","https://openalex.org/W2963717374","https://openalex.org/W2963770662","https://openalex.org/W2963954913","https://openalex.org/W2964067226","https://openalex.org/W2964345214","https://openalex.org/W2973400388","https://openalex.org/W2986670728","https://openalex.org/W2999422171","https://openalex.org/W3006750887","https://openalex.org/W3007146850","https://openalex.org/W3010457411","https://openalex.org/W3011329351","https://openalex.org/W3011651912","https://openalex.org/W3013064459","https://openalex.org/W3016211260","https://openalex.org/W3023906497","https://openalex.org/W3040161129","https://openalex.org/W3046031979","https://openalex.org/W3095543650","https://openalex.org/W3096547803","https://openalex.org/W3161765645","https://openalex.org/W4299522971","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3157284875","https://openalex.org/W2259406085","https://openalex.org/W2099715052","https://openalex.org/W4226247999","https://openalex.org/W4213176082","https://openalex.org/W2187398150","https://openalex.org/W3209772662","https://openalex.org/W4200629926","https://openalex.org/W4220955952","https://openalex.org/W4226470070"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"is":[4,36],"a":[5,46],"multimodal":[6,51],"research":[7],"related":[8,119],"to":[9,19,33,105,120],"Computer":[10],"Vision":[11],"(CV)":[12],"and":[13,26,28,53,61,71,88,94,111,123,141],"Natural":[14],"Language":[15],"Processing":[16],"(NLP).":[17],"How":[18],"better":[20,84],"obtain":[21],"useful":[22],"information":[23,103],"from":[24],"images":[25],"questions":[27],"give":[29],"an":[30],"accurate":[31],"answer":[32,129],"the":[34,37,40,65,80,106,128,137,142,149,155,159],"question":[35],"core":[38],"of":[39,151],"VQA":[41,47,138],"task.":[42],"This":[43],"paper":[44],"presents":[45],"model":[48,82],"based":[49],"on":[50,86,136,158],"encoders":[52],"decoders":[54],"with":[55],"gate":[56,76,109],"attention":[57,73,110,114],"(MEDGA).":[58],"Each":[59],"encoder":[60],"decoder":[62],"block":[63],"in":[64],"MEDGA":[66,98,156],"applies":[67],"not":[68],"only":[69],"self-attention":[70],"crossmodal":[72],"but":[74],"also":[75],"attention,":[77],"so":[78],"that":[79,116],"new":[81],"can":[83],"focus":[85],"inter-modal":[87],"intra-modal":[89],"interactions":[90],"simultaneously":[91],"within":[92],"visual":[93,121],"language":[95,124],"modality.":[96],"Besides,":[97],"further":[99],"filters":[100],"out":[101],"noise":[102],"irrelevant":[104],"results":[107,115],"via":[108],"finally":[112],"outputs":[113],"are":[117],"closely":[118],"features":[122],"features,":[125],"which":[126,165],"makes":[127],"prediction":[130],"result":[131],"more":[132],"accurate.":[133],"Experimental":[134],"evaluations":[135],"2.0":[139],"dataset":[140,161],"ablation":[143],"experiments":[144],"under":[145],"different":[146],"conditions":[147],"prove":[148],"effectiveness":[150],"MEDGA.":[152],"In":[153],"addition,":[154],"accuracy":[157],"test-std":[160],"has":[162],"reached":[163],"70.11%,":[164],"exceeds":[166],"many":[167],"existing":[168],"methods.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}