{"id":"https://openalex.org/W4403577779","doi":"https://doi.org/10.1145/3627673.3679926","title":"FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings","display_name":"FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577779","doi":"https://doi.org/10.1145/3627673.3679926"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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":null,"display_name":"Zhen Wang","orcid":"https://orcid.org/0009-0005-8957-7432"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701873","display_name":"Da Li","orcid":"https://orcid.org/0009-0009-0345-7771"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Da Li","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012506270","display_name":"Yulin Su","orcid":"https://orcid.org/0009-0002-5270-5291"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulin Su","raw_affiliation_strings":["ByteDance Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100582234","display_name":"Yang Min","orcid":"https://orcid.org/0009-0004-5885-8138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Yang","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101851065","display_name":"Minghui Qiu","orcid":"https://orcid.org/0000-0002-5184-9886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghui Qiu","raw_affiliation_strings":["ByteDance Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Walton Wang","orcid":"https://orcid.org/0009-0007-9651-9569"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Walton Wang","raw_affiliation_strings":["ByteDance Inc., Shanghai, China"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc., Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6426,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70354385,"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":"4113","last_page":"4117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9865999817848206,"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":0.9542999863624573,"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/computer-science","display_name":"Computer science","score":0.7764350771903992},{"id":"https://openalex.org/keywords/logo","display_name":"Logo (programming language)","score":0.6995767951011658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4473978281021118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4469633102416992},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4303479492664337},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30395007133483887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764350771903992},{"id":"https://openalex.org/C2778720087","wikidata":"https://www.wikidata.org/wiki/Q201436","display_name":"Logo (programming language)","level":2,"score":0.6995767951011658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4473978281021118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4469633102416992},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4303479492664337},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30395007133483887}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679926","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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":15,"referenced_works":["https://openalex.org/W1965842729","https://openalex.org/W1980972548","https://openalex.org/W2036363317","https://openalex.org/W2080829704","https://openalex.org/W2089760990","https://openalex.org/W2097748059","https://openalex.org/W2132064754","https://openalex.org/W2574981201","https://openalex.org/W2953759675","https://openalex.org/W2992733631","https://openalex.org/W2997947223","https://openalex.org/W3015331896","https://openalex.org/W4226278401","https://openalex.org/W4294733375","https://openalex.org/W4319300041"],"related_works":["https://openalex.org/W4382895929","https://openalex.org/W2164977745","https://openalex.org/W4247466689","https://openalex.org/W2156726901","https://openalex.org/W2940416500","https://openalex.org/W2734681527","https://openalex.org/W654884026","https://openalex.org/W1577150342","https://openalex.org/W3127211284","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Logo":[0],"embedding":[1,40,136],"models":[2,52,122],"convert":[3],"the":[4,24,73,78],"product":[5,32,116],"logos":[6],"in":[7,91,166],"images":[8],"into":[9],"vectors,":[10],"enabling":[11],"their":[12],"utilization":[13],"for":[14,115],"logo":[15,39,125,161],"recognition":[16],"and":[17,30,94,159],"detection":[18],"within":[19],"e-commerce":[20],"platforms.":[21],"This":[22],"facilitates":[23],"enforcement":[25],"of":[26,77,156],"intellectual":[27],"property":[28],"rights":[29],"enhances":[31],"search":[33],"capabilities.":[34],"However,":[35],"current":[36],"methods":[37],"treat":[38],"as":[41,62,68],"a":[42,63,129],"purely":[43],"visual":[44,51,74,93,121,135],"problem.":[45],"A":[46],"noteworthy":[47],"issue":[48],"is":[49,154],"that":[50,133,152],"capture":[53],"features":[54],"more":[55],"than":[56],"logos.":[57],"Instead,":[58],"we":[59,100],"view":[60],"this":[61],"multimodal":[64],"task,":[65],"using":[66],"text":[67,114],"auxiliary":[69],"information":[70],"to":[71,105,108,111,137],"facilitate":[72],"model's":[75],"understanding":[76],"logo.":[79],"The":[80],"emerging":[81],"Multimodal":[82],"Large":[83],"Language":[84],"Models":[85],"(MLLMs)":[86],"have":[87],"demonstrated":[88],"remarkable":[89],"capabilities":[90],"both":[92],"textual":[95,143],"understanding.":[96],"Inspired":[97],"by":[98],"this,":[99],"propose":[101],"an":[102],"approach,":[103],"FashionLOGO,":[104],"explore":[106],"how":[107],"prompt":[109],"MLLMs":[110],"generate":[112],"appropriate":[113],"images,":[117],"which":[118],"can":[119],"help":[120],"achieve":[123],"better":[124],"embeddings.":[126],"We":[127],"adopt":[128],"cross-attention":[130],"transformer":[131],"block":[132],"enables":[134],"automatically":[138],"learn":[139],"supplementary":[140],"knowledge":[141],"from":[142],"embedding.":[144],"Our":[145],"extensive":[146],"experiments":[147],"on":[148],"real-world":[149],"datasets":[150],"prove":[151],"FashionLOGO":[153],"capable":[155],"generating":[157],"generic":[158],"robust":[160],"embeddings,":[162],"achieving":[163],"state-of-the-art":[164],"performance":[165],"all":[167],"benchmarks.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}