{"id":"https://openalex.org/W4415995480","doi":"https://doi.org/10.1145/3774884","title":"Dual Alignment-Enhanced Fashion Vision-Language Pre-Training","display_name":"Dual Alignment-Enhanced Fashion Vision-Language Pre-Training","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4415995480","doi":"https://doi.org/10.1145/3774884"},"language":"en","primary_location":{"id":"doi:10.1145/3774884","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774884","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5075938343","display_name":"Weili Guan","orcid":"https://orcid.org/0000-0002-5658-5509"},"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":"Weili Guan","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology (Shenzhen), China"],"raw_orcid":"https://orcid.org/0000-0002-5658-5509","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053685797","display_name":"Kejie Wang","orcid":"https://orcid.org/0000-0003-0595-6856"},"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":"Kejie Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology (Shenzhen), China"],"raw_orcid":"https://orcid.org/0000-0003-0595-6856","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072768866","display_name":"Xuemeng Song","orcid":"https://orcid.org/0000-0002-5274-4197"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemeng Song","raw_affiliation_strings":["Southern University of Science and Technology, Shenzhen, China","Southern University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-5274-4197","affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology, Shenzhen, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144603","display_name":"Kaihao Zhang","orcid":"https://orcid.org/0000-0002-4317-660X"},"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":"Kaihao Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, China","Harbin Institute of Technology (Shenzhen), China"],"raw_orcid":"https://orcid.org/0000-0002-4317-660X","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China","University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-7778-8807","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084025984","display_name":"Shengping Zhang","orcid":"https://orcid.org/0000-0001-5200-3420"},"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":"Shengping Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Weihai, China","Harbin Institute of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-5200-3420","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Weihai, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29577814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"23"},"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":0.9333999752998352,"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":0.9333999752998352,"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":0.02710000053048134,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.02710000053048134,"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/joint","display_name":"Joint (building)","score":0.5957000255584717},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5723999738693237},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5703999996185303},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5619000196456909},{"id":"https://openalex.org/keywords/subcategory","display_name":"Subcategory","score":0.4837000072002411},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42320001125335693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8661999702453613},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5723999738693237},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5703999996185303},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5619000196456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C2780617661","wikidata":"https://www.wikidata.org/wiki/Q541563","display_name":"Subcategory","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774884","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774884","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5740385822","display_name":null,"funder_award_id":"No. U24A20328, 62476071, and 62376137","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7721725717","display_name":null,"funder_award_id":"No. ZR2022YQ59","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2081580037","https://openalex.org/W4212804468","https://openalex.org/W4383337770","https://openalex.org/W4390879096","https://openalex.org/W4392172801","https://openalex.org/W4401993157","https://openalex.org/W4405706077"],"related_works":[],"abstract_inverted_index":{"Fashion":[0],"vision-language":[1],"pre-training":[2,104],"(VLP)":[3],"models":[4,21],"have":[5],"demonstrated":[6],"remarkable":[7],"capabilities":[8],"in":[9,45],"excelling":[10],"at":[11],"a":[12,43,55,73],"wide":[13],"range":[14],"of":[15,34,57,88,156,185],"fashion":[16,77,97,191],"cross-modal":[17,170],"tasks.":[18],"However,":[19],"current":[20],"still":[22],"face":[23],"three":[24],"notable":[25],"limitations":[26],"(1)":[27],"an":[28],"inability":[29],"to":[30,141,149],"discern":[31],"varying":[32],"levels":[33],"consistency":[35],"between":[36,49,127],"textual":[37],"descriptions":[38],"and":[39,51,53,91,111,130,137,177],"multi-view":[40,89,128],"images,":[41],"(2)":[42],"deficiency":[44],"explicit":[46],"fine-grained":[47,138,152],"alignment":[48,126,139],"images":[50,90,129],"text,":[52],"(3)":[54],"lack":[56],"specific":[58],"supervision":[59],"mechanisms":[60],"for":[61],"facilitating":[62],"global":[63,158],"joint":[64,160],"embedding":[65],"learning.":[66],"To":[67],"address":[68],"these":[69],"limitations,":[70],"we":[71,100],"propose":[72],"novel":[74,103],"dual":[75],"alignment-enhanced":[76],"VLP":[78,192],"model.":[79],"This":[80,133],"model":[81,187],"delves":[82],"deeply":[83],"into":[84],"the":[85,120,151,157,181],"rich":[86],"resources":[87],"semantic":[92,143,153],"attributes":[93],"associated":[94],"with":[95],"each":[96],"item.":[98],"Notably,":[99],"introduce":[101],"two":[102],"tasks:":[105],"Multi-grained":[106],"Adaptive":[107],"Image-Text":[108],"Alignment":[109,114],"(MAITA)":[110],"Joint":[112],"Embedding-oriented":[113],"(JEA).":[115],"MAITA":[116],"focuses":[117],"on":[118],"optimizing":[119],"text/image":[121],"encoder":[122],"by":[123],"orchestrating":[124],"adaptive":[125],"input":[131],"text.":[132],"encompasses":[134],"both":[135],"coarse-grained":[136],"strategies":[140],"enrich":[142],"understanding,":[144],"while":[145],"JEA":[146],"is":[147],"devised":[148],"supervise":[150],"learning":[154],"process":[155],"multimodal":[159],"embedding.":[161],"Experimental":[162],"results":[163],"spanning":[164],"four":[165],"diverse":[166],"downstream":[167],"tasks,":[168],"including":[169],"retrieval,":[171,174],"text-guided":[172],"image":[173],"category":[175],"recognition,":[176,179],"subcategory":[178],"substantiate":[180],"significant":[182],"performance":[183],"superiority":[184],"our":[186],"over":[188],"prior":[189],"state-of-the-art":[190],"models.":[193]},"counts_by_year":[],"updated_date":"2026-06-25T06:16:34.145877","created_date":"2025-11-07T00:00:00"}
