{"id":"https://openalex.org/W4416078259","doi":"https://doi.org/10.1109/access.2025.3630632","title":"Fashion Image Retrieval With Vision\u2013Language Model Guided Fine-Grained Textual Attributes and Cross-Domain Contrastive Optimization","display_name":"Fashion Image Retrieval With Vision\u2013Language Model Guided Fine-Grained Textual Attributes and Cross-Domain Contrastive Optimization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416078259","doi":"https://doi.org/10.1109/access.2025.3630632"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3630632","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3630632","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3630632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Eojin Kim","orcid":"https://orcid.org/0009-0000-8322-5819"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Eojin Kim","raw_affiliation_strings":["Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063424739","display_name":"Sangyeop Kim","orcid":"https://orcid.org/0000-0002-7584-1061"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangyeop Kim","raw_affiliation_strings":["Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cholhwan Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Cholhwan Jung","raw_affiliation_strings":["Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117833951","display_name":"Youngseok Hahm","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngseok Hahm","raw_affiliation_strings":["Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102814007","display_name":"Sungzoon Cho","orcid":"https://orcid.org/0000-0002-1695-1973"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungzoon Cho","raw_affiliation_strings":["Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Industrial Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.328302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"192403","last_page":"192415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.784600019454956,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.784600019454956,"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/T11448","display_name":"Face recognition and analysis","score":0.06419999897480011,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.05000000074505806,"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/image-retrieval","display_name":"Image retrieval","score":0.63919997215271},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5372999906539917},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4837000072002411},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39079999923706055},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.3849000036716461},{"id":"https://openalex.org/keywords/automatic-image-annotation","display_name":"Automatic image annotation","score":0.36079999804496765},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34689998626708984},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3427000045776367},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.34209999442100525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805000185966492},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.63919997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5861999988555908},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5372999906539917},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5277000069618225},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.36079999804496765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34940001368522644},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33730000257492065},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.2712000012397766},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.26809999346733093},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3630632","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3630632","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:87f740647dd54ef09241bcf8f6645cd3","is_oa":true,"landing_page_url":"https://doaj.org/article/87f740647dd54ef09241bcf8f6645cd3","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":"IEEE Access, Vol 13, Pp 192403-192415 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3630632","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3630632","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1933349210","https://openalex.org/W1975517671","https://openalex.org/W2074621908","https://openalex.org/W2096733369","https://openalex.org/W2200092826","https://openalex.org/W2471768434","https://openalex.org/W2798951647","https://openalex.org/W2885563408","https://openalex.org/W2951882943","https://openalex.org/W2963367015","https://openalex.org/W2963664762","https://openalex.org/W2964211610","https://openalex.org/W2988281744","https://openalex.org/W2996695408","https://openalex.org/W2998804039","https://openalex.org/W3035724178","https://openalex.org/W3107840323","https://openalex.org/W3110551393","https://openalex.org/W3120946780","https://openalex.org/W3130073172","https://openalex.org/W3159683145","https://openalex.org/W4280530070","https://openalex.org/W4297105730","https://openalex.org/W4308586874","https://openalex.org/W4381804476","https://openalex.org/W4387845356","https://openalex.org/W4387889759","https://openalex.org/W4390618645","https://openalex.org/W4390873312","https://openalex.org/W4392016246","https://openalex.org/W4399034461","https://openalex.org/W4404212764","https://openalex.org/W4404579909","https://openalex.org/W4410641357"],"related_works":[],"abstract_inverted_index":{"Fashion":[0],"image":[1],"retrieval":[2,154,188],"(FIR)":[3],"enables":[4],"consumers":[5],"to":[6,47,71],"discover":[7],"products":[8],"using":[9,68],"visual":[10],"queries,":[11],"however":[12],"current":[13],"methods":[14,150],"struggle":[15],"with":[16,43,63,194],"fine-grained":[17,40],"fashion":[18,66,93,173,187],"differences":[19],"and":[20,26,133,141,156,175,198],"cross-domain":[21,127,178],"gaps":[22],"between":[23,129],"user":[24,131],"photos":[25],"professional":[27,134],"catalogs.":[28],"We":[29],"propose":[30],"a":[31,183],"novel":[32,190],"two-stage":[33],"framework":[34,147,185],"that":[35,114,145],"combines":[36],"vision-language":[37],"model":[38],"guided":[39],"textual":[41],"attributes":[42],"weighted":[44],"contrastive":[45,196],"optimization":[46],"address":[48],"these":[49],"fundamental":[50],"limitations.":[51],"The":[52,103],"first":[53],"stage":[54,105],"employs":[55],"Sigmoid":[56],"Loss":[57],"for":[58,201],"Language":[59],"Image":[60],"Pre-training":[61],"(SigLIP)":[62],"systematic":[64],"twelve-attribute":[65],"annotations":[67],"binary":[69],"classification":[70,158],"accommodate":[72],"multi-positive":[73],"scenarios":[74],"where":[75,95],"single":[76],"garments":[77],"can":[78],"be":[79],"validly":[80],"described":[81],"by":[82],"multiple":[83,96],"attributes.":[84],"This":[85,180],"approach":[86],"naturally":[87],"handles":[88],"the":[89,164],"semantic":[90],"richness":[91],"of":[92,153,166,192],"items,":[94],"descriptions":[97],"may":[98],"accurately":[99],"characterize":[100],"individual":[101],"garments.":[102],"second":[104],"introduces":[106],"Weighted":[107],"Multi":[108],"Normalized":[109],"Temperature-Scaled":[110],"Cross-Entropy":[111],"(NT-Xent)":[112],"loss":[113],"strategically":[115],"prioritizes":[116],"street-to-shop":[117],"matching":[118],"while":[119],"eliminating":[120],"complex":[121],"negative":[122],"sampling":[123],"requirements,":[124],"enabling":[125,176],"effective":[126],"learning":[128],"casual":[130],"photography":[132],"catalog":[135],"imagery.":[136],"Extensive":[137],"experiments":[138],"on":[139],"Street2Shop":[140],"DeepFashion":[142],"datasets":[143],"demonstrate":[144],"our":[146],"outperforms":[148],"existing":[149],"in":[151,170],"terms":[152],"accuracy":[155],"zero-shot":[157],"performance.":[159],"Comprehensive":[160],"ablation":[161],"studies":[162],"confirm":[163],"effectiveness":[165],"each":[167],"proposed":[168],"component":[169],"capturing":[171],"detailed":[172],"characteristics":[174],"practical":[177,199],"matching.":[179],"paper":[181],"contributes":[182],"comprehensive":[184],"addressing":[186],"challenges,":[189],"application":[191],"SigLIP":[193],"specialized":[195],"learning,":[197],"improvements":[200],"real-world":[202],"applications.":[203]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-11-10T00:00:00"}