{"id":"https://openalex.org/W4364377616","doi":"https://doi.org/10.1007/s44196-023-00233-6","title":"Multiscale Feature Extraction and Fusion of Image and Text in VQA","display_name":"Multiscale Feature Extraction and Fusion of Image and Text in VQA","publication_year":2023,"publication_date":"2023-04-11","ids":{"openalex":"https://openalex.org/W4364377616","doi":"https://doi.org/10.1007/s44196-023-00233-6"},"language":"en","primary_location":{"id":"doi:10.1007/s44196-023-00233-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-023-00233-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-023-00233-6.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44196-023-00233-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029777041","display_name":"Siyu Lu","orcid":"https://orcid.org/0009-0003-5903-4117"},"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":"Siyu Lu","raw_affiliation_strings":["School of Automation, University of Electronic Science and Technology of China, Chengdu, 610054, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, University of Electronic Science and Technology of China, Chengdu, 610054, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050577817","display_name":"Yueming Ding","orcid":"https://orcid.org/0000-0003-3133-3839"},"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":"Yueming Ding","raw_affiliation_strings":["School of Automation, University of Electronic Science and Technology of China, Chengdu, 610054, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, University of Electronic Science and Technology of China, Chengdu, 610054, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674094","display_name":"Mingzhe Liu","orcid":"https://orcid.org/0000-0001-7054-997X"},"institutions":[{"id":"https://openalex.org/I4400573270","display_name":"Wenzhou University of Technology","ror":"https://ror.org/03dd7qj98","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573270"]},{"id":"https://openalex.org/I146620803","display_name":"Wenzhou University","ror":"https://ror.org/020hxh324","country_code":"CN","type":"education","lineage":["https://openalex.org/I146620803"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingzhe Liu","raw_affiliation_strings":["School of Data Science and Artificial Intelligence, Wenzhou University of Technology, Wenzhou, 325000, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science and Artificial Intelligence, Wenzhou University of Technology, Wenzhou, 325000, China","institution_ids":["https://openalex.org/I146620803","https://openalex.org/I4400573270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021201289","display_name":"Zhengtong Yin","orcid":"https://orcid.org/0000-0002-9818-9205"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengtong Yin","raw_affiliation_strings":["College of Resource and Environment Engineering, Guizhou University, Guiyang, 550025, China"],"affiliations":[{"raw_affiliation_string":"College of Resource and Environment Engineering, Guizhou University, Guiyang, 550025, China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023971713","display_name":"Lirong Yin","orcid":"https://orcid.org/0000-0002-5022-610X"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lirong Yin","raw_affiliation_strings":["Department of Geography and Anthropology, Louisiana State University, Baton Rouge, LA, 70803, USA"],"affiliations":[{"raw_affiliation_string":"Department of Geography and Anthropology, Louisiana State University, Baton Rouge, LA, 70803, USA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062384828","display_name":"Wenfeng Zheng","orcid":"https://orcid.org/0000-0002-8486-1654"},"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":"Wenfeng Zheng","raw_affiliation_strings":["School of Automation, University of Electronic Science and Technology of China, Chengdu, 610054, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, University of Electronic Science and Technology of China, Chengdu, 610054, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100674094"],"corresponding_institution_ids":["https://openalex.org/I146620803","https://openalex.org/I4400573270"],"apc_list":{"value":1390,"currency":"GBP","value_usd":1704},"apc_paid":{"value":1390,"currency":"GBP","value_usd":1704},"fwci":27.2229,"has_fulltext":true,"cited_by_count":411,"citation_normalized_percentile":{"value":0.99785542,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"16","issue":"1","first_page":null,"last_page":null},"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":0.991599977016449,"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":0.9750000238418579,"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":0.7828863859176636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7671717405319214},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6735161542892456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6476950645446777},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6187410354614258},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4822607636451721},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4554124176502228},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4443603754043579},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3363415002822876},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.326954185962677}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828863859176636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7671717405319214},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6735161542892456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6476950645446777},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6187410354614258},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4822607636451721},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4554124176502228},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4443603754043579},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3363415002822876},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.326954185962677},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"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/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/s44196-023-00233-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-023-00233-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-023-00233-6.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:56cc4f1ae32544d98979747c17001998","is_oa":true,"landing_page_url":"https://doaj.org/article/56cc4f1ae32544d98979747c17001998","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Computational Intelligence Systems, Vol 16, Iss 1, Pp 1-11 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44196-023-00233-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44196-023-00233-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44196-023-00233-6.pdf","source":{"id":"https://openalex.org/S190680769","display_name":"International Journal of Computational Intelligence Systems","issn_l":"1875-6883","issn":["1875-6883","1875-6891"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"International Journal of Computational Intelligence Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4364377616.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1947481528","https://openalex.org/W2094728533","https://openalex.org/W2102605133","https://openalex.org/W2104657103","https://openalex.org/W2122865749","https://openalex.org/W2131494463","https://openalex.org/W2142192571","https://openalex.org/W2189070436","https://openalex.org/W2463565445","https://openalex.org/W2471366537","https://openalex.org/W2552161745","https://openalex.org/W2884875744","https://openalex.org/W2921873695","https://openalex.org/W2927774766","https://openalex.org/W2963150162","https://openalex.org/W2963383024","https://openalex.org/W2963717374","https://openalex.org/W2964018924","https://openalex.org/W2964118342","https://openalex.org/W2964138343","https://openalex.org/W2991391304","https://openalex.org/W3006962461","https://openalex.org/W3033514332","https://openalex.org/W4206336297","https://openalex.org/W4224062983","https://openalex.org/W4280528456","https://openalex.org/W4281608801","https://openalex.org/W4283009457","https://openalex.org/W4284994893","https://openalex.org/W4285231916","https://openalex.org/W4291900964","https://openalex.org/W4295934629","https://openalex.org/W4302362504","https://openalex.org/W4305082803","https://openalex.org/W4307818888","https://openalex.org/W4312447176","https://openalex.org/W6600324250","https://openalex.org/W6638824847","https://openalex.org/W6715144786","https://openalex.org/W6728881024"],"related_works":["https://openalex.org/W2354322770","https://openalex.org/W3000097931","https://openalex.org/W4237547500","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1537496349","https://openalex.org/W2379407973","https://openalex.org/W4243305035","https://openalex.org/W2079488604"],"abstract_inverted_index":{"Abstract":[0],"The":[1,194],"Visual":[2],"Question":[3],"Answering":[4],"(VQA)":[5],"system":[6],"is":[7,62],"the":[8,18,22,31,47,56,64,70,76,93,103,114,128,145,158,172,181,187,198,207,210],"process":[9],"of":[10,33,49,102,132,148,160,178,200,209],"finding":[11],"useful":[12],"information":[13,78,99],"from":[14],"images":[15],"related":[16],"to":[17,20,107,168],"question":[19,23],"answer":[21],"correctly.":[24],"It":[25],"can":[26],"be":[27,80],"widely":[28],"used":[29,85],"in":[30,59,92],"fields":[32],"visual":[34],"assistance,":[35],"automated":[36],"security":[37],"surveillance,":[38],"and":[39,44,55,72,75,89,97,122,127,144,170,175,191,204],"intelligent":[40],"interaction":[41],"between":[42],"robots":[43],"humans.":[45],"However,":[46],"accuracy":[48,208],"VQA":[50,104,182,211],"has":[51],"not":[52],"been":[53],"ideal,":[54],"main":[57],"difficulty":[58],"its":[60,109],"research":[61],"that":[63,197],"image":[65,94,115,129],"features":[66,130,177],"cannot":[67,79],"well":[68],"represent":[69],"scene":[71],"object":[73],"information,":[74],"text":[77,98],"fully":[81],"represented.":[82],"This":[83],"paper":[84],"multi-scale":[86,119,163,188,201],"feature":[87,95,116,120,149,164,189,202],"extraction":[88,121,190,203],"fusion":[90,123,150,192,205],"methods":[91],"characterization":[96],"representation":[100,117,159],"sections":[101],"system,":[105],"respectively":[106],"improve":[108],"accuracy.":[110],"Firstly,":[111],"aiming":[112],"at":[113],"problem,":[118],"method":[124,151,165],"were":[125,136],"adopted,":[126],"output":[131],"different":[133],"network":[134],"layers":[135],"extracted":[137],"by":[138],"a":[139,162],"pre-trained":[140],"deep":[141],"neural":[142],"network,":[143],"optimal":[146],"scheme":[147],"was":[152,166,184],"found":[153],"through":[154],"experiments.":[155],"Secondly,":[156],"for":[157],"sentences,":[161],"introduced":[167],"characterize":[169],"fuse":[171],"word-level,":[173],"phrase-level,":[174],"sentence-level":[176],"sentences.":[179],"Finally,":[180],"model":[183],"improved":[185],"using":[186],"method.":[193],"results":[195],"show":[196],"addition":[199],"improves":[206],"model.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":44},{"year":2024,"cited_by_count":66},{"year":2023,"cited_by_count":114},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":31},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}