{"id":"https://openalex.org/W4291219744","doi":"https://doi.org/10.1145/3503161.3548230","title":"ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design","display_name":"ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Design","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4291219744","doi":"https://doi.org/10.1145/3503161.3548230"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548230","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548230","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.05621","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004500525","display_name":"Xu\u2010Jie Zhang","orcid":"https://orcid.org/0000-0003-2585-534X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xujie Zhang","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University, shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University, shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045758146","display_name":"Sha Yu","orcid":"https://orcid.org/0000-0002-2551-7458"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Sha","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University, shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University, shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023225712","display_name":"Michael Kampffmeyer","orcid":"https://orcid.org/0000-0002-7699-0405"},"institutions":[{"id":"https://openalex.org/I78037679","display_name":"UiT The Arctic University of Norway","ror":"https://ror.org/00wge5k78","country_code":"NO","type":"education","lineage":["https://openalex.org/I78037679"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Michael C. Kampffmeyer","raw_affiliation_strings":["UiT The Arctic University of Norway, Troms\u00f8, Norway"],"affiliations":[{"raw_affiliation_string":"UiT The Arctic University of Norway, Troms\u00f8, Norway","institution_ids":["https://openalex.org/I78037679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060590214","display_name":"Zhenyu Xie","orcid":"https://orcid.org/0000-0001-9207-1014"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Xie","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University,ByteDance, shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University,ByteDance, shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075329194","display_name":"Zequn Jie","orcid":"https://orcid.org/0000-0002-3038-5891"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zequn Jie","raw_affiliation_strings":["Meituan Inc., shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Meituan Inc., shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102533932","display_name":"Chengwen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086402","display_name":"Shenzhen General Institute of Architectural Design and Research (China)","ror":"https://ror.org/00wa5fs40","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210086402"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwen Huang","raw_affiliation_strings":["Shidi Inc., shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shidi Inc., shenzhen, China","institution_ids":["https://openalex.org/I4210086402"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017987831","display_name":"Jianqing Peng","orcid":"https://orcid.org/0000-0002-9777-842X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqing Peng","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University, shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University, shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University, shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University, shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5004500525"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.1965,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.85890703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4525","last_page":"4535"},"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":0.9994999766349792,"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":0.9994999766349792,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.9609000086784363,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8253588676452637},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6840933561325073},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6490676403045654},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.607826828956604},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5767847895622253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5069394707679749},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41076990962028503},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11587291955947876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253588676452637},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6840933561325073},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6490676403045654},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.607826828956604},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5767847895622253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5069394707679749},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41076990962028503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11587291955947876},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548230","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548230","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2208.05621","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.05621","pdf_url":"https://arxiv.org/pdf/2208.05621","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2208.05621","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.05621","pdf_url":"https://arxiv.org/pdf/2208.05621","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2145023731","https://openalex.org/W2405756170","https://openalex.org/W2471768434","https://openalex.org/W2790214987","https://openalex.org/W2904322775","https://openalex.org/W2952866402","https://openalex.org/W2962770929","https://openalex.org/W2963163163","https://openalex.org/W2963270749","https://openalex.org/W2963373786","https://openalex.org/W2963402808","https://openalex.org/W2963413689","https://openalex.org/W2963799213","https://openalex.org/W2963966654","https://openalex.org/W2964216930","https://openalex.org/W2965289598","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2971074500","https://openalex.org/W2982450728","https://openalex.org/W2995665739","https://openalex.org/W3034667500","https://openalex.org/W3035316078","https://openalex.org/W3089767655","https://openalex.org/W3090449556","https://openalex.org/W3126337491","https://openalex.org/W3126792443","https://openalex.org/W3129576130","https://openalex.org/W3132890542","https://openalex.org/W3133431537","https://openalex.org/W3153469116","https://openalex.org/W3165647589","https://openalex.org/W3166396011","https://openalex.org/W3170082999","https://openalex.org/W3173220247","https://openalex.org/W3174525637","https://openalex.org/W3180355996","https://openalex.org/W3199850185","https://openalex.org/W3201409833","https://openalex.org/W3207865986","https://openalex.org/W3212456749","https://openalex.org/W3212801546","https://openalex.org/W4206706211","https://openalex.org/W4214926101","https://openalex.org/W4226348722","https://openalex.org/W4250533120","https://openalex.org/W4287547182","https://openalex.org/W4287556760","https://openalex.org/W4297606427","https://openalex.org/W4310486995"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2137816434","https://openalex.org/W2163679795","https://openalex.org/W2736714427","https://openalex.org/W2017956276","https://openalex.org/W2048606991"],"abstract_inverted_index":{"Cross-modal":[0],"fashion":[1,32,110,227],"image":[2,33,119,142,147,204,244],"synthesis":[3,40,205,237,245],"has":[4],"emerged":[5],"as":[6,211],"one":[7],"of":[8,23,31,74,141,151],"the":[9,14,19,28,72,75,84,96,139,149,152,174,180],"most":[10],"promising":[11],"directions":[12],"in":[13,129,155,235],"generation":[15],"domain":[16],"due":[17],"to":[18,49,70,137,160,182,187],"vast":[20],"untapped":[21],"potential":[22],"incorporating":[24],"multiple":[25],"modalities":[26],"and":[27,52,64,78,91,98,133,201,216,239],"wide":[29],"range":[30],"applications.":[34],"To":[35],"facilitate":[36],"accurate":[37,93],"generation,":[38],"cross-modal":[39,109,127,196,226,243],"methods":[41],"typically":[42],"rely":[43,165],"on":[44,102,124,166,222],"Contrastive":[45],"Language-Image":[46],"Pre-training":[47],"(CLIP)":[48],"align":[50],"textual":[51,171],"garment":[53,65],"information.":[54,100],"In":[55],"this":[56],"work,":[57],"we":[58,104],"argue":[59],"that":[60,163,230],"simply":[61],"aligning":[62],"texture":[63],"information":[66,77,186],"is":[67,199,249],"not":[68],"sufficient":[69],"capture":[71],"semantics":[73],"visual":[76,97],"therefore":[79],"propose":[80,105],"MaskCLIP.":[81],"MaskCLIP":[82],"decomposes":[83],"garments":[85],"into":[86,120,173],"semantic":[87,185],"parts,":[88],"ensuring":[89],"fine-grained":[90],"semantically":[92],"alignment":[94],"between":[95],"text":[99],"Building":[101],"MaskCLIP,":[103],"ARMANI,":[106],"a":[107,125,135,145,195],"unified":[108],"designer":[111],"with":[112],"part-level":[113],"garment-text":[114],"alignment.":[115],"ARMANI":[116,169,198,231],"discretizes":[117],"an":[118],"uniform":[121],"tokens":[122,143,150,172],"based":[123],"learned":[126],"codebook":[128],"its":[130,156],"first":[131],"stage":[132],"uses":[134],"Transformer":[136],"model":[138,181],"distribution":[140],"for":[144,179],"real":[146],"given":[148],"control":[153,208],"signals":[154],"second":[157],"stage.":[158],"Contrary":[159],"prior":[161],"approaches":[162],"also":[164],"two-stage":[167],"paradigms,":[168],"introduces":[170],"codebook,":[175],"making":[176],"it":[177],"possible":[178],"utilize":[183],"fine-grain":[184],"generate":[188],"more":[189],"realistic":[190],"images.":[191,218],"Further,":[192],"by":[193],"introducing":[194],"Transformer,":[197],"versatile":[200],"can":[202],"accomplish":[203],"from":[206],"various":[207],"signals,":[209],"such":[210],"pure":[212],"text,":[213],"sketch":[214],"images,":[215],"partial":[217],"Extensive":[219],"experiments":[220],"conducted":[221],"our":[223],"newly":[224],"collected":[225],"dataset":[228],"demonstrate":[229],"generates":[232],"photo-realistic":[233],"images":[234],"diverse":[236],"tasks":[238],"outperforms":[240],"existing":[241],"state-of-the-art":[242],"approaches.":[246],"Our":[247],"code":[248],"available":[250],"at":[251],"https://github.com/Harvey594/ARMANI.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-08-13T00:00:00"}