{"id":"https://openalex.org/W7164645298","doi":"https://doi.org/10.1145/3805622.3810590","title":"VietFashion: Benchmarking Sketch\u2013Text Composed Image Retrieval for Cultural Outfits","display_name":"VietFashion: Benchmarking Sketch\u2013Text Composed Image Retrieval for Cultural Outfits","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164645298","doi":"https://doi.org/10.1145/3805622.3810590"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810590","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138556530","display_name":"Hoang-Nguyen Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hoang-Nguyen Cao","raw_affiliation_strings":["University Of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":"https://orcid.org/0009-0003-0459-730X","affiliations":[{"raw_affiliation_string":"University Of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138582098","display_name":"Le-Hoang Bui","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Le-Hoang Bui","raw_affiliation_strings":["University Of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":"https://orcid.org/0009-0003-1162-234X","affiliations":[{"raw_affiliation_string":"University Of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138560251","display_name":"Dinh-Khoi Vo","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dinh-Khoi Vo","raw_affiliation_strings":["University of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":"https://orcid.org/0000-0001-8831-8846","affiliations":[{"raw_affiliation_string":"University of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138564392","display_name":"Minh-Triet Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Triet Tran","raw_affiliation_strings":["University of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":"https://orcid.org/0000-0003-3046-3041","affiliations":[{"raw_affiliation_string":"University of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062359795","display_name":"Trung-Nghia Le","orcid":"https://orcid.org/0000-0002-7363-2610"},"institutions":[{"id":"https://openalex.org/I123565023","display_name":"Vietnam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Trung-Nghia Le","raw_affiliation_strings":["University of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-7363-2610","affiliations":[{"raw_affiliation_string":"University of Science, Ho Chi Minh City, Vietnam and Vietnam National University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I123565023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123565023"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2588","last_page":"2596"},"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":0.9599999785423279,"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":0.9599999785423279,"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":0.006099999882280827,"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":0.004999999888241291,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.746999979019165},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7458000183105469},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.6869999766349792},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.520799994468689},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5091999769210815},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.40869998931884766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052999973297119},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.746999979019165},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7458000183105469},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7142000198364258},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6869999766349792},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C530175646","wikidata":"https://www.wikidata.org/wiki/Q11460","display_name":"Clothing","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.3197000026702881},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.29269999265670776},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2694000005722046}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805622.3810590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810590","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.13427","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.13427","pdf_url":"https://arxiv.org/pdf/2606.13427","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810590","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810590","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326592","display_name":"Viet Nam National University Ho Chi Minh City","ror":"https://ror.org/00waaqh38"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cultural":[0],"garments":[1],"pose":[2],"a":[3,32,45,60,126,131,169],"unique":[4],"challenge":[5],"for":[6,35,172],"visual":[7],"retrieval":[8,39,128,150],"systems,":[9],"as":[10,168],"their":[11],"identity":[12],"often":[13],"depends":[14],"on":[15,41],"subtle":[16],"structural":[17],"and":[18,52,69,83,113,145,163],"symbolic":[19],"details":[20],"that":[21,99],"are":[22,105],"poorly":[23],"captured":[24],"by":[25],"standard":[26],"AI":[27],"models.":[28],"We":[29,140],"introduce":[30],"VietFashion,":[31],"new":[33],"benchmark":[34,146,171],"sketch\u2013text":[36],"composed":[37,148],"image":[38,149],"centered":[40],"the":[42,118],"Ao":[43],"Dai,":[44],"traditional":[46],"Vietnamese":[47],"garment.":[48],"VietFashion":[49,124,167],"enables":[50],"designers":[51],"researchers":[53],"to":[54,88,110,136],"retrieve":[55],"culturally":[56],"meaningful":[57],"outfits":[58],"using":[59,85],"combination":[61],"of":[62,121],"hand-drawn":[63],"sketches,":[64],"which":[65,72,104],"convey":[66],"garment":[67],"structure,":[68],"textual":[70],"descriptions,":[71],"encode":[73],"cultural":[74,161],"semantics.":[75],"The":[76,176],"dataset":[77,177],"is":[78,178],"initialized":[79],"with":[80,94],"650":[81],"sketches":[82],"expanded":[84],"generative":[86],"models":[87],"produce":[89],"over":[90],"21,000":[91],"photorealistic":[92],"images":[93],"aligned":[95],"captions.":[96],"Textual":[97],"prompts":[98],"describe":[100],"detailed":[101],"outfit":[102],"attributes,":[103],"extracted":[106],"from":[107],"fashion":[108,174],"magazines":[109],"ensure":[111],"authenticity":[112],"diversity.":[114],"To":[115],"better":[116],"reflect":[117],"inherent":[119],"ambiguity":[120],"design":[122],"intent,":[123],"adopts":[125],"multi-target":[127],"setting,":[129],"where":[130],"single":[132],"query":[133],"may":[134],"correspond":[135],"multiple":[137],"valid":[138],"results.":[139],"establish":[141],"standardized":[142],"evaluation":[143],"protocols":[144],"state-of-the-art":[147],"methods.":[151],"Experimental":[152],"results":[153],"reveal":[154],"significant":[155],"performance":[156],"gaps":[157],"in":[158],"modeling":[159],"fine-grained":[160,173],"semantics":[162],"multi-modal":[164],"composition,":[165],"positioning":[166],"challenging":[170],"retrieval.":[175],"publicly":[179],"available":[180],"at:":[181],"https://hng0303.github.io/VietFashion.":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-14T00:00:00"}
