{"id":"https://openalex.org/W4308544918","doi":"https://doi.org/10.1007/s41019-022-00200-9","title":"A Multi-level Mesh Mutual Attention Model for Visual Question Answering","display_name":"A Multi-level Mesh Mutual Attention Model for Visual Question Answering","publication_year":2022,"publication_date":"2022-10-30","ids":{"openalex":"https://openalex.org/W4308544918","doi":"https://doi.org/10.1007/s41019-022-00200-9"},"language":"en","primary_location":{"id":"doi:10.1007/s41019-022-00200-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-022-00200-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-022-00200-9.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s41019-022-00200-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088098617","display_name":"Zhi Lei","orcid":"https://orcid.org/0000-0003-0169-7666"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhi Lei","raw_affiliation_strings":["Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China"],"raw_orcid":"https://orcid.org/0000-0003-0169-7666","affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073893996","display_name":"Guixian Zhang","orcid":"https://orcid.org/0000-0002-7632-8411"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guixian Zhang","raw_affiliation_strings":["Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023022659","display_name":"Lijuan Wu","orcid":"https://orcid.org/0000-0002-0390-1782"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijuan Wu","raw_affiliation_strings":["Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435165","display_name":"Kui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Zhang","raw_affiliation_strings":["Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005849650","display_name":"Rongjiao Liang","orcid":"https://orcid.org/0000-0002-8514-9263"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongjiao Liang","raw_affiliation_strings":["Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Multi-Source Information Mining & Security, Guangxi Normal University, GuiLin, 541000, GuangXi, China","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088098617"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":1.6258,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84999635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"7","issue":"4","first_page":"339","last_page":"353"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962000250816345,"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":0.9118763208389282},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6507564187049866},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.636854350566864},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5866151452064514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5687662363052368},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5380366444587708},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4930691421031952},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4224271774291992},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3915436267852783},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32903963327407837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9118763208389282},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6507564187049866},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.636854350566864},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5866151452064514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5687662363052368},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5380366444587708},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4930691421031952},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4224271774291992},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3915436267852783},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32903963327407837},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s41019-022-00200-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-022-00200-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-022-00200-9.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4b35f2f286ec4562b1a4ccafc4ab3544","is_oa":true,"landing_page_url":"https://doaj.org/article/4b35f2f286ec4562b1a4ccafc4ab3544","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science and Engineering, Vol 7, Iss 4, Pp 339-353 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s41019-022-00200-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-022-00200-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-022-00200-9.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1838624305","display_name":null,"funder_award_id":"MIMS20-04","funder_id":"https://openalex.org/F4320336248","funder_display_name":"Guangxi Key Laboratory of Multi-Source Information Mining and Security"},{"id":"https://openalex.org/G6497971106","display_name":null,"funder_award_id":"20-A-01-02","funder_id":"https://openalex.org/F4320336248","funder_display_name":"Guangxi Key Laboratory of Multi-Source Information Mining and Security"}],"funders":[{"id":"https://openalex.org/F4320336248","display_name":"Guangxi Key Laboratory of Multi-Source Information Mining and Security","ror":null},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308544918.pdf","grobid_xml":"https://content.openalex.org/works/W4308544918.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W1981276685","https://openalex.org/W2142192571","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2277195237","https://openalex.org/W2529436507","https://openalex.org/W2546696630","https://openalex.org/W2560730294","https://openalex.org/W2595840341","https://openalex.org/W2745461083","https://openalex.org/W2926818924","https://openalex.org/W2962933067","https://openalex.org/W2963176022","https://openalex.org/W2963191264","https://openalex.org/W2963383024","https://openalex.org/W2963466731","https://openalex.org/W2963560969","https://openalex.org/W2963954913","https://openalex.org/W2964138017","https://openalex.org/W2964345214","https://openalex.org/W2966683369","https://openalex.org/W3005012942","https://openalex.org/W3007556011","https://openalex.org/W3080952252","https://openalex.org/W3111066448","https://openalex.org/W3135705837","https://openalex.org/W3157224510","https://openalex.org/W4312820606","https://openalex.org/W6638553918","https://openalex.org/W6702248584"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2466816617","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W4381058564","https://openalex.org/W3003945460","https://openalex.org/W2964413124","https://openalex.org/W4288267738"],"abstract_inverted_index":{"Abstract":[0],"Visual":[1],"question":[2,47,82,93,109,136],"answering":[3],"is":[4,48],"a":[5,57,97,127,147],"complex":[6],"multimodal":[7,32],"task":[8],"involving":[9],"images":[10],"and":[11,20,31,42,84,111,124,138,168,176],"text,":[12],"with":[13,27,134],"broad":[14],"application":[15],"prospects":[16],"in":[17,39,45,70,126,141,151],"human\u2013computer":[18],"interaction":[19,30],"medical":[21],"assistance.":[22],"Therefore,":[23],"how":[24],"to":[25,77,90,101,162],"deal":[26],"the":[28,36,40,43,46,62,66,71,116,122,152,170],"feature":[29,33,157],"fusion":[34,149,153],"between":[35,105],"critical":[37],"regions":[38],"image":[41,112],"keywords":[44],"an":[49,142],"important":[50],"issue.":[51],"To":[52],"this":[53],"end,":[54],"we":[55,73,120],"propose":[56,96,146],"neural":[58],"network":[59],"based":[60],"on":[61,115,173],"encoder\u2013decoder":[63],"structure":[64],"of":[65,88],"transformer":[67],"architecture.":[68],"Specifically,":[69],"encoder,":[72],"use":[74],"multi-head":[75],"self-attention":[76],"mine":[78],"word\u2013word":[79],"connections":[80],"within":[81],"features":[83,110,113],"stack":[85],"multiple":[86],"layers":[87],"attention":[89,99,132],"obtain":[91],"multi-level":[92,135],"features.":[94],"We":[95,145,166],"mutual":[98,131],"module":[100,150],"perform":[102,130],"information":[103,140,158],"exchange":[104],"modalities":[106],"for":[107],"better":[108,183],"representation":[114],"decoder":[117,125],"side.":[118],"Besides,":[119],"connect":[121],"encoder":[123],"meshed":[128],"manner,":[129],"operations":[133],"features,":[137],"aggregate":[139],"adaptive":[143],"way.":[144],"multi-scale":[148],"stage,":[154],"which":[155],"utilizes":[156],"at":[159],"different":[160],"scales":[161],"complete":[163],"modal":[164],"fusion.":[165],"test":[167],"validate":[169],"model":[171,181],"effectiveness":[172],"VQA":[174,177],"v1":[175],"v2":[178],"datasets.":[179],"Our":[180],"achieves":[182],"results":[184],"than":[185],"state-of-the-art":[186],"methods.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}