{"id":"https://openalex.org/W4386453567","doi":"https://doi.org/10.1109/lsp.2023.3310870","title":"The Style Transformer With Common Knowledge Optimization for Image-Text Retrieval","display_name":"The Style Transformer With Common Knowledge Optimization for Image-Text Retrieval","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386453567","doi":"https://doi.org/10.1109/lsp.2023.3310870"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3310870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3310870","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5046442204","display_name":"Wenrui Li","orcid":"https://orcid.org/0000-0002-2393-9016"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenrui Li","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079107646","display_name":"Zhengyu Ma","orcid":"https://orcid.org/0000-0003-0799-440X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyu Ma","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062607701","display_name":"Jinqiao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiao Shi","raw_affiliation_strings":["School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079412089","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Fan","raw_affiliation_strings":["Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046442204"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.324,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82945392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"1197","last_page":"1201"},"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":0.9995999932289124,"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":0.9975000023841858,"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":0.7893380522727966},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7565237283706665},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6764015555381775},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.510585606098175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4862765073776245},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42312371730804443},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4007669985294342},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36832162737846375},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3410673141479492}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893380522727966},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7565237283706665},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6764015555381775},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.510585606098175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4862765073776245},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42312371730804443},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4007669985294342},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36832162737846375},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3410673141479492},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3310870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3310870","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G124397460","display_name":null,"funder_award_id":"62236009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1774558579","display_name":null,"funder_award_id":"62206141","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5430980299","display_name":null,"funder_award_id":"U22B2035","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6569862357","display_name":null,"funder_award_id":"62272128","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2025432722","https://openalex.org/W2067766814","https://openalex.org/W2185175083","https://openalex.org/W2289354478","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2944026969","https://openalex.org/W2962856082","https://openalex.org/W2962964995","https://openalex.org/W2966715458","https://openalex.org/W3005971801","https://openalex.org/W3035454331","https://openalex.org/W3122154272","https://openalex.org/W3137191861","https://openalex.org/W3155230099","https://openalex.org/W3201645700","https://openalex.org/W3213100861","https://openalex.org/W4206546481","https://openalex.org/W4213348104","https://openalex.org/W4214819138","https://openalex.org/W4225329158","https://openalex.org/W4281758439","https://openalex.org/W4285118104","https://openalex.org/W4285138127","https://openalex.org/W4312238224","https://openalex.org/W4313477296","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6739901393","https://openalex.org/W6766904570","https://openalex.org/W6788684253"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602","https://openalex.org/W2419146053","https://openalex.org/W2088247287","https://openalex.org/W3006008237","https://openalex.org/W2312145515"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,156],"which":[2,172],"associates":[3],"different":[4,97,116,137],"modalities":[5],"has":[6],"drawn":[7],"broad":[8,17],"attention":[9],"due":[10,184],"to":[11,91,106,119,131,185],"its":[12],"excellent":[13],"research":[14],"value":[15],"and":[16,34,76,159,176,189],"real-world":[18],"application.":[19],"However,":[20],"most":[21],"of":[22,96,112,136,150,181],"the":[23,28,64,71,77,84,87,94,109,134,148,151,169,179,186],"existing":[24],"methods":[25,153],"haven't":[26],"taken":[27],"high-level":[29],"semantic":[30],"relationships":[31],"(\u201cstyle":[32],"embedding\u201d)":[33],"common":[35,53,65,78,113,123,143],"knowledge":[36,54,66,79,114],"from":[37,115],"multi-modalities":[38],"into":[39],"full":[40],"consideration.":[41],"To":[42],"this":[43],"end,":[44],"we":[45,125],"introduce":[46],"a":[47,127],"novel":[48],"style":[49,72],"transformer":[50,171],"network":[51],"with":[52,69,141],"optimization":[55,80],"(CKSTN)":[56],"for":[57,178],"image-text":[58,155],"retrieval.":[59],"The":[60,101],"main":[61],"module":[62,103],"is":[63,104,165,173],"adaptor":[67],"(CKA)":[68],"both":[70],"embedding":[73],"extractor":[74],"(SEE)":[75],"(CKO)":[81],"modules.":[82],"Specifically,":[83],"SEE":[85,140],"uses":[86],"sequential":[88,128],"update":[89,129],"strategy":[90,130],"effectively":[92,132],"connect":[93],"features":[95,135],"stages":[98],"in":[99,139,154],"SEE.":[100],"CKO":[102],"introduced":[105],"dynamically":[107],"capture":[108],"latent":[110],"concepts":[111],"modalities.":[117],"Besides,":[118],"get":[120],"generalized":[121],"temporal":[122],"knowledge,":[124],"propose":[126],"integrate":[133],"layers":[138],"previous":[142],"feature":[144],"units.":[145],"CKSTN":[146,164],"demonstrates":[147],"superiorities":[149],"state-of-the-art":[152],"on":[157,168],"MSCOCO":[158],"Flickr30":[160],"K":[161],"datasets.":[162],"Moreover,":[163],"constructed":[166],"based":[167],"lightweight":[170],"more":[174],"convenient":[175],"practical":[177],"application":[180],"real":[182],"scenes,":[183],"better":[187],"performance":[188],"lower":[190],"parameters.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}