{"id":"https://openalex.org/W4387925344","doi":"https://doi.org/10.1145/3606040.3617438","title":"Dynamic Network for Language-based Fashion Retrieval","display_name":"Dynamic Network for Language-based Fashion Retrieval","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4387925344","doi":"https://doi.org/10.1145/3606040.3617438"},"language":"en","primary_location":{"id":"doi:10.1145/3606040.3617438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606040.3617438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deep Multimodal Learning for Information Retrieval","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":"Hangfei Li","orcid":"https://orcid.org/0009-0002-4036-4098"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangfei Li","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-4036-4098","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490743","display_name":"Yiming Wu","orcid":"https://orcid.org/0000-0002-9866-669X"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Wu","raw_affiliation_strings":["Zhejiang University of Technology, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9866-669X","affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391381","display_name":"Fangfang Wang","orcid":"https://orcid.org/0000-0002-7685-5705"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangfang Wang","raw_affiliation_strings":["Zhejiang Laboratory, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7685-5705","affiliations":[{"raw_affiliation_string":"Zhejiang Laboratory, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4491,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64549375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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":0.9962000250816345,"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":0.9944999814033508,"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":0.8428279161453247},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6201202869415283},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.618183434009552},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6128413081169128},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5998457074165344},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5575999617576599},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5374027490615845},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.4486801028251648},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.44695693254470825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4463019371032715},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4437468349933624},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4368610978126526},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42121583223342896},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3756713569164276},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3246425986289978},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.10251447558403015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0917651355266571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428279161453247},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6201202869415283},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.618183434009552},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6128413081169128},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5998457074165344},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5575999617576599},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5374027490615845},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.4486801028251648},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.44695693254470825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4463019371032715},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4437468349933624},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4368610978126526},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42121583223342896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3756713569164276},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3246425986289978},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.10251447558403015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0917651355266571},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3606040.3617438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606040.3617438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Deep Multimodal Learning for Information Retrieval","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":36,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2618530766","https://openalex.org/W2735001949","https://openalex.org/W2760103357","https://openalex.org/W2905544595","https://openalex.org/W2951104886","https://openalex.org/W2962964995","https://openalex.org/W2964157791","https://openalex.org/W2972137450","https://openalex.org/W3005971801","https://openalex.org/W3006500080","https://openalex.org/W3026458074","https://openalex.org/W3034467781","https://openalex.org/W3035552787","https://openalex.org/W3092767330","https://openalex.org/W3119510203","https://openalex.org/W3120735991","https://openalex.org/W3150955418","https://openalex.org/W3154902219","https://openalex.org/W3155230099","https://openalex.org/W3172514680","https://openalex.org/W3175684172","https://openalex.org/W3176909828","https://openalex.org/W3195866476","https://openalex.org/W3205173298","https://openalex.org/W3206569427","https://openalex.org/W4286696412","https://openalex.org/W4295308727","https://openalex.org/W4312940158","https://openalex.org/W4312974690","https://openalex.org/W4313855701","https://openalex.org/W4386075974","https://openalex.org/W4387967965","https://openalex.org/W4387968166"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W936373746","https://openalex.org/W4382701072","https://openalex.org/W627697492"],"abstract_inverted_index":{"Language-based":[0],"fashion":[1,28],"image":[2,9,36,60,158,183],"retrieval,":[3,10],"as":[4],"a":[5,12,34,38,47,74,85,101,143],"kind":[6],"of":[7,18,57,84,119,133,146,180,199],"composed":[8],"presents":[11],"substantial":[13],"challenge":[14],"in":[15,30,76],"the":[16,26,31,54,58,82,111,117,147,175,197,205],"domain":[17],"multi-modal":[19,49],"retrieval.":[20],"This":[21],"task":[22],"aims":[23],"to":[24,52,81,95,109],"retrieve":[25],"target":[27],"item":[29],"gallery":[32],"given":[33],"reference":[35,59,157,182],"and":[37,61,122,159,178,184,194],"modification":[39,62],"text.":[40,63,161,186],"Existing":[41],"approaches":[42,69],"primarily":[43],"concentrate":[44],"on":[45,174,189],"developing":[46],"static":[48,96],"fusion":[50,87,97],"module":[51,88],"learn":[53],"combined":[55],"semantics":[56,177],"Despite":[64],"their":[65],"commendable":[66],"advancements,":[67],"these":[68],"are":[70],"still":[71],"limited":[72],"by":[73,115],"deficiency":[75],"flexibility,":[77],"which":[78],"is":[79,131],"attributed":[80],"application":[83],"singluar":[86],"across":[89],"diverse":[90],"input":[91],"queries.":[92],"In":[93,126],"contrast":[94],"methods,":[98],"we":[99],"propose":[100],"novel":[102],"method":[103,130],"termed":[104],"Dynamic":[105,137],"Fusion":[106],"Network":[107],"(DFN)":[108],"compose":[110],"multi-granularity":[112,152],"features":[113],"dynamically":[114],"considering":[116],"consistency":[118],"routing":[120,171],"path":[121],"modality-specific":[123],"information":[124],"simultaneously.":[125],"specific,":[127],"our":[128,200],"proposed":[129,201],"consisted":[132],"two":[134],"modules:":[135],"(1)":[136],"Network.":[138],"The":[139,167],"dynamic":[140],"network":[141],"enables":[142],"flexible":[144],"combination":[145],"different":[148],"operation":[149],"modules,":[150],"providing":[151],"modality":[153],"interaction":[154],"for":[155],"each":[156,181],"modifier":[160,185],"(2)":[162],"Modality":[163],"Specific":[164],"Routers":[165],"(MSR).":[166],"MSR":[168],"generates":[169],"precise":[170],"decisions":[172],"based":[173],"distinct":[176],"distributions":[179],"Extensive":[187],"experiments":[188],"three":[190],"benchmarks,\\textiti.e.,":[191],"FashionIQ,":[192],"Shoes":[193],"Fashion200K,":[195],"demonstrate":[196],"effectiveness":[198],"model":[202],"compared":[203],"with":[204],"existing":[206],"methods.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}