{"id":"https://openalex.org/W7168380164","doi":"https://doi.org/10.1145/3805712.3808442","title":"Preliminary Study of an Evaluation Benchmark for Vision\u2013Language Models in Fashion E-Commerce","display_name":"Preliminary Study of an Evaluation Benchmark for Vision\u2013Language Models in Fashion E-Commerce","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168380164","doi":"https://doi.org/10.1145/3805712.3808442"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808442","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808442","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808442","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140811668","display_name":"Ryotaro Shimizu","orcid":"https://orcid.org/0000-0002-4841-1824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryotaro Shimizu","raw_affiliation_strings":["ZOZO Research, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4841-1824","affiliations":[{"raw_affiliation_string":"ZOZO Research, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140844312","display_name":"Sai Htaungkham","orcid":"https://orcid.org/0009-0005-8803-5842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sai Htaungkham","raw_affiliation_strings":["ZOZO Research, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0005-8803-5842","affiliations":[{"raw_affiliation_string":"ZOZO Research, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140800362","display_name":"Shion Sakurai","orcid":"https://orcid.org/0009-0001-4828-8555"},"institutions":[{"id":"https://openalex.org/I4210088800","display_name":"Tokyo Zoological Park Society","ror":"https://ror.org/002fj3m33","country_code":"JP","type":"nonprofit","lineage":["https://openalex.org/I4210088800"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shion Sakurai","raw_affiliation_strings":["ZOZO, Inc., Chiba, Japan"],"raw_orcid":"https://orcid.org/0009-0001-4828-8555","affiliations":[{"raw_affiliation_string":"ZOZO, Inc., Chiba, Japan","institution_ids":["https://openalex.org/I4210088800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140927978","display_name":"Yuki Shimizu","orcid":"https://orcid.org/0009-0002-6738-0274"},"institutions":[{"id":"https://openalex.org/I4210088800","display_name":"Tokyo Zoological Park Society","ror":"https://ror.org/002fj3m33","country_code":"JP","type":"nonprofit","lineage":["https://openalex.org/I4210088800"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Shimizu","raw_affiliation_strings":["ZOZO, Inc., Chiba, Japan"],"raw_orcid":"https://orcid.org/0009-0002-6738-0274","affiliations":[{"raw_affiliation_string":"ZOZO, Inc., Chiba, Japan","institution_ids":["https://openalex.org/I4210088800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4880","last_page":"4885"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.446399986743927},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3061000108718872},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.25999999046325684},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.24740000069141388},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24729999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6190999746322632},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24740000069141388},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24729999899864197},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2313999980688095},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.23109999299049377}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808442","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808442","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808442","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808442","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2170505850","https://openalex.org/W2471768434","https://openalex.org/W2967819436","https://openalex.org/W3110551393","https://openalex.org/W3156470785","https://openalex.org/W3172514680","https://openalex.org/W4308432165","https://openalex.org/W4312729433","https://openalex.org/W4384563227","https://openalex.org/W4389523832","https://openalex.org/W4401208776","https://openalex.org/W4402671206","https://openalex.org/W4402716381","https://openalex.org/W4402716477","https://openalex.org/W4402727764","https://openalex.org/W7133193597","https://openalex.org/W7133211372","https://openalex.org/W7133224126","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"We":[0,34],"report":[1],"an":[2],"evaluation":[3],"benchmark":[4],"for":[5,105],"assessing":[6],"the":[7,26,67],"operational":[8],"suitability":[9],"of":[10],"Vision-Language":[11],"Models":[12],"(VLMs)":[13],"in":[14,31,108],"fashion":[15,110],"e-commerce.":[16],"General-purpose":[17],"benchmarks":[18],"do":[19],"not":[20],"adequately":[21],"cover":[22],"fashion-specific":[23],"attributes":[24],"or":[25],"structured":[27],"extraction":[28],"tasks":[29,37,86],"common":[30],"e-commerce":[32],"workflows.":[33],"define":[35],"five":[36],"across":[38],"two":[39,50],"image":[40],"streams---outfit":[41],"and":[42,49,61,80,99],"single-item":[43],"product":[44],"images---and":[45],"compare":[46],"six":[47],"commercial":[48],"open-source":[51],"models":[52],"with":[53],"multiple":[54],"prompt":[55,60,96],"variants,":[56],"including":[57],"a":[58],"canonical":[59],"model-proposed":[62],"prompts.":[63],"Experiments":[64],"show":[65],"that":[66,93],"best-performing":[68],"model":[69,81],"varies":[70],"by":[71],"task,":[72],"error":[73],"patterns":[74],"are":[75,102],"more":[76],"model-dependent":[77],"than":[78],"prompt-dependent,":[79],"updates":[82],"can":[83],"improve":[84],"some":[85],"while":[87],"degrading":[88],"others.":[89],"These":[90],"results":[91],"indicate":[92],"task-specific":[94],"evaluation,":[95],"robustness":[97],"checks,":[98],"continuous":[100],"monitoring":[101],"practical":[103],"requirements":[104],"deploying":[106],"VLMs":[107],"production":[109],"systems.":[111]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}