{"id":"https://openalex.org/W4405304350","doi":"https://doi.org/10.1109/besc64747.2024.10780701","title":"Text-to-image Retrieval Based on Zero-shot Transfer Learning with CLIP Model and Vector Database","display_name":"Text-to-image Retrieval Based on Zero-shot Transfer Learning with CLIP Model and Vector Database","publication_year":2024,"publication_date":"2024-08-16","ids":{"openalex":"https://openalex.org/W4405304350","doi":"https://doi.org/10.1109/besc64747.2024.10780701"},"language":"en","primary_location":{"id":"doi:10.1109/besc64747.2024.10780701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/besc64747.2024.10780701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 11th International Conference on Behavioural and Social Computing (BESC)","raw_type":"proceedings-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/A5046111232","display_name":"Junfeng Xie","orcid":"https://orcid.org/0000-0002-3961-4283"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junfeng Xie","raw_affiliation_strings":["School of Software Engineering, South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101953158","display_name":"Junying Chen","orcid":"https://orcid.org/0009-0003-5322-5211"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junying Chen","raw_affiliation_strings":["School of Software Engineering, South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046111232"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.6531,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76526012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.7682999968528748,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.7682999968528748,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7235000133514404,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.6723999977111816,"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":0.7538704872131348},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6056345701217651},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5619950294494629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5174437165260315},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4946896731853485},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.47902196645736694},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.43822047114372253},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.436079740524292},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43145108222961426},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3489319086074829},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3298112750053406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538704872131348},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6056345701217651},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5619950294494629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5174437165260315},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4946896731853485},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.47902196645736694},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.43822047114372253},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.436079740524292},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43145108222961426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3489319086074829},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3298112750053406},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/besc64747.2024.10780701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/besc64747.2024.10780701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 11th International Conference on Behavioural and Social Computing (BESC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1980867644","https://openalex.org/W2151103935","https://openalex.org/W2606965845","https://openalex.org/W2962964995","https://openalex.org/W2965848243","https://openalex.org/W2988823324","https://openalex.org/W3035552787","https://openalex.org/W3174809957","https://openalex.org/W6789753369","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W3044321615","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2773965352","https://openalex.org/W4294892107","https://openalex.org/W2357748469","https://openalex.org/W2392917037"],"abstract_inverted_index":{"With":[0],"the":[1,5,10,16,58,74,79,90,98,101,120,128,140,145,160],"continuous":[2],"increase":[3],"in":[4,68,94],"number":[6],"of":[7,12,78,109,130],"internet":[8],"users,":[9],"explosion":[11],"multimodal":[13],"data":[14],"on":[15,33,53,119],"web":[17],"has":[18],"led":[19],"to":[20,39,65,150],"a":[21,48],"growing":[22],"demand":[23],"for":[24,82,104],"image":[25,110,152],"retrieval.":[26,96],"Current":[27],"text-to-image":[28,49,69,95,131],"retrieval":[29,43,50,70,108,153],"systems":[30],"often":[31],"rely":[32],"keyword":[34],"matching,":[35],"which":[36],"frequently":[37],"fails":[38],"accurately":[40],"capture":[41],"users'":[42],"needs.":[44],"This":[45],"work":[46,138],"proposes":[47],"method":[51,99,126,142],"based":[52],"zero-shot":[54],"transfer":[55],"learning":[56],"with":[57],"CLIP":[59,80],"model":[60,81],"and":[61,84,107,163],"vector":[62],"database,":[63],"designed":[64],"be":[66],"applied":[67],"systems.":[71],"By":[72],"leveraging":[73],"semantic":[75,91],"alignment":[76],"capability":[77],"text":[83,156],"images,":[85],"this":[86,125,137],"study":[87],"effectively":[88],"addresses":[89],"gap":[92],"problem":[93],"Additionally,":[97],"utilizes":[100],"Milvus":[102],"database":[103],"efficient":[105],"storage":[106],"feature":[111],"vectors,":[112],"thereby":[113],"enhancing":[114],"system":[115],"stability.":[116],"Experimental":[117],"results":[118],"Flickr30k":[121],"dataset":[122],"demonstrate":[123],"that":[124],"improves":[127],"accuracy":[129],"retrieval,":[132],"verifying":[133],"its":[134],"effectiveness.":[135],"Furthermore,":[136],"extends":[139],"proposed":[141],"by":[143],"incorporating":[144],"iFLYTEK":[146],"Spark":[147],"Cognitive":[148],"Model":[149],"support":[151],"using":[154],"Chinese":[155],"descriptions,":[157],"further":[158],"broadening":[159],"system's":[161],"applicability":[162],"reliability.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}