{"id":"https://openalex.org/W4322207844","doi":"https://doi.org/10.1007/s11633-022-1394-4","title":"Masked Vision-language Transformer in Fashion","display_name":"Masked Vision-language Transformer in Fashion","publication_year":2023,"publication_date":"2023-02-27","ids":{"openalex":"https://openalex.org/W4322207844","doi":"https://doi.org/10.1007/s11633-022-1394-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-022-1394-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1394-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1394-4.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1394-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001285878","display_name":"Ge-Peng Ji","orcid":"https://orcid.org/0000-0001-7092-2877"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge-Peng Ji","raw_affiliation_strings":["International Core Business Unit, Alibaba Group, Hangzhou, 310051, China"],"raw_orcid":"https://orcid.org/0000-0001-7092-2877","affiliations":[{"raw_affiliation_string":"International Core Business Unit, Alibaba Group, Hangzhou, 310051, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030077358","display_name":"Mingchen Zhuge","orcid":"https://orcid.org/0000-0003-2561-7712"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingchen Zhuge","raw_affiliation_strings":["International Core Business Unit, Alibaba Group, Hangzhou, 310051, China"],"raw_orcid":"https://orcid.org/0000-0003-2561-7712","affiliations":[{"raw_affiliation_string":"International Core Business Unit, Alibaba Group, Hangzhou, 310051, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062149619","display_name":"Dehong Gao","orcid":"https://orcid.org/0000-0002-6636-5702"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehong Gao","raw_affiliation_strings":["International Core Business Unit, Alibaba Group, Hangzhou, 310051, China"],"raw_orcid":"https://orcid.org/0000-0002-6636-5702","affiliations":[{"raw_affiliation_string":"International Core Business Unit, Alibaba Group, Hangzhou, 310051, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056294284","display_name":"Deng-Ping Fan","orcid":"https://orcid.org/0000-0002-5245-7518"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Deng-Ping Fan","raw_affiliation_strings":["Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5245-7518","affiliations":[{"raw_affiliation_string":"Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058481699","display_name":"Christos Sakaridis","orcid":"https://orcid.org/0000-0003-1127-8887"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christos Sakaridis","raw_affiliation_strings":["Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-1127-8887","affiliations":[{"raw_affiliation_string":"Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001254143","display_name":"Luc Van Gool","orcid":"https://orcid.org/0000-0002-3445-5711"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luc Van Gool","raw_affiliation_strings":["Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-3445-5711","affiliations":[{"raw_affiliation_string":"Computer Vision Lab, ETH Z\u00fcrich, Z\u00fcrich, 8092, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056294284"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":2.1272,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89287589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"20","issue":"3","first_page":"421","last_page":"434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9986000061035156,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9954000115394592,"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/transformer","display_name":"Transformer","score":0.8377759456634521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7872588634490967},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6340944766998291},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.523104190826416},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5098256468772888},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4946255385875702},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4286070466041565},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.42316934466362},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3845755457878113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34043657779693604},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09288862347602844},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07532152533531189}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.8377759456634521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872588634490967},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6340944766998291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.523104190826416},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5098256468772888},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4946255385875702},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4286070466041565},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42316934466362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3845755457878113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34043657779693604},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09288862347602844},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07532152533531189},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11633-022-1394-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1394-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1394-4.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/613701","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/613701","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Intelligence Research, 20 (3)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/616543","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/616543","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Intelligence Research, 20 (3)","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.3929/ethz-b-000613701","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000613701","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1007/s11633-022-1394-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1394-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1394-4.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.4000000059604645,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"},{"id":"https://openalex.org/F4320335507","display_name":"Toyota Motor Europe","ror":"https://ror.org/023g86t37"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4322207844.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2613718673","https://openalex.org/W2774267535","https://openalex.org/W2778940641","https://openalex.org/W2795117763","https://openalex.org/W2962964995","https://openalex.org/W2963341956","https://openalex.org/W2965848243","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2970869018","https://openalex.org/W2972801466","https://openalex.org/W2996545740","https://openalex.org/W2998356391","https://openalex.org/W3035485997","https://openalex.org/W3035726724","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3107492437","https://openalex.org/W3122006940","https://openalex.org/W3126792443","https://openalex.org/W3131500599","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3154596443","https://openalex.org/W3165938948","https://openalex.org/W3168640669","https://openalex.org/W3170767867","https://openalex.org/W3171915994","https://openalex.org/W3172514680","https://openalex.org/W3176362845","https://openalex.org/W3184784418","https://openalex.org/W3202031169","https://openalex.org/W3202461379","https://openalex.org/W4210593721","https://openalex.org/W4220834633","https://openalex.org/W4285606598","https://openalex.org/W4304080188","https://openalex.org/W4312940158","https://openalex.org/W4313156423","https://openalex.org/W6739901393","https://openalex.org/W6779879114","https://openalex.org/W6790978476","https://openalex.org/W6796761347"],"related_works":["https://openalex.org/W2275988210","https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W4313303565","https://openalex.org/W2892009249","https://openalex.org/W4386160099"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"present":[2],"a":[3,51],"masked":[4,46],"vision-language":[5,77],"transformer":[6,18],"(MVLT)":[7],"for":[8,20,39,50],"fashion-specific":[9],"multi-modal":[10,66],"representation.":[11],"Technically,":[12],"we":[13,44],"simply":[14],"utilize":[15],"the":[16,22,30,35,40,76,106],"vision":[17],"architecture":[19,62],"replacing":[21],"bidirectional":[23],"encoder":[24],"representations":[25],"from":[26],"Transformers":[27],"(BERT)":[28],"in":[29,96],"pre-training":[31],"model,":[32],"making":[33],"MVLT":[34,56,81],"first":[36],"end-to-end":[37],"framework":[38],"fashion":[41],"domain.":[42],"Besides,":[43],"designed":[45],"image":[47],"reconstruction":[48],"(MIR)":[49],"fine-grained":[52],"understanding":[53],"of":[54],"fashion.":[55],"is":[57,113],"an":[58],"extensible":[59],"and":[60,88,100],"convenient":[61],"that":[63],"admits":[64],"raw":[65],"inputs":[67],"without":[68],"extra":[69],"pre-processing":[70],"models":[71],"(e.g.,":[72],"ResNet),":[73],"implicitly":[74],"modeling":[75],"alignments.":[78],"More":[79],"importantly,":[80],"can":[82],"easily":[83],"generalize":[84],"to":[85],"various":[86],"matching":[87],"generative":[89],"tasks.":[90],"Experimental":[91],"results":[92],"show":[93],"obvious":[94],"improvements":[95],"retrieval":[97],"(rank@5:":[98],"17%)":[99],"recognition":[101],"(accuracy:":[102],"3%)":[103],"tasks":[104],"over":[105],"Fashion-Gen":[107],"2018":[108],"winner,":[109],"Kaleido-BERT.":[110],"The":[111],"code":[112],"available":[114],"at":[115],"https://github.com/GewelsJI/MVLT":[116],".":[117]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}