{"id":"https://openalex.org/W7118170951","doi":"https://doi.org/10.1109/tcsvt.2026.3650934","title":"Vision-Guided Fashion Fine-Grained Attribute Editing via Semantic Segmentation and Disentangled Representation","display_name":"Vision-Guided Fashion Fine-Grained Attribute Editing via Semantic Segmentation and Disentangled Representation","publication_year":2026,"publication_date":"2026-01-05","ids":{"openalex":"https://openalex.org/W7118170951","doi":"https://doi.org/10.1109/tcsvt.2026.3650934"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3650934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3650934","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","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/A5103006369","display_name":"Kexin Sun","orcid":"https://orcid.org/0000-0001-5277-0304"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kexin Sun","raw_affiliation_strings":["Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-5277-0304","affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103467349","display_name":"Yujie Han","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yujie Han","raw_affiliation_strings":["Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081499025","display_name":"Zhiheng Zhao","orcid":"https://orcid.org/0000-0002-0024-8116"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiheng Zhao","raw_affiliation_strings":["Department of Industrial and Systems Engineering, Research Institute for Advanced Manufacturing, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0024-8116","affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, Research Institute for Advanced Manufacturing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":null,"display_name":"George Q. Huang","orcid":"https://orcid.org/0000-0003-3592-7917"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"George Q. Huang","raw_affiliation_strings":["Department of Industrial and Systems Engineering, Research Institute for Advanced Manufacturing, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-3592-7917","affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, Research Institute for Advanced Manufacturing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03368885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"6152","last_page":"6167"},"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":0.817799985408783,"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":0.817799985408783,"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":0.13369999825954437,"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/T11448","display_name":"Face recognition and analysis","score":0.012600000016391277,"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/pipeline","display_name":"Pipeline (software)","score":0.626800000667572},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5741999745368958},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5733000040054321},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5644999742507935},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.48240000009536743},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42750000953674316},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.39809998869895935},{"id":"https://openalex.org/keywords/composability","display_name":"Composability","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8499000072479248},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.626800000667572},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5733000040054321},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5644999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5523999929428101},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5034999847412109},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C2778814252","wikidata":"https://www.wikidata.org/wiki/Q5156715","display_name":"Composability","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C530175646","wikidata":"https://www.wikidata.org/wiki/Q11460","display_name":"Clothing","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3650934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3650934","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4714890029","display_name":null,"funder_award_id":"2024A1515011930","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7877397331","display_name":null,"funder_award_id":"52305557","funder_id":"https://openalex.org/F4320314062","funder_display_name":"National Research Council"},{"id":"https://openalex.org/G8819798200","display_name":null,"funder_award_id":"52305557","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320314062","display_name":"National Research Council","ror":"https://ror.org/02eq2w707"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Advances":[0],"in":[1,14,47,78],"image":[2],"editing":[3,12,72],"models":[4],"have":[5],"enabled":[6],"intelligent,":[7],"rapid":[8],"fashion":[9,48,92,200],"customization.":[10,49,201],"Vision-guided":[11],"models,":[13],"particular,":[15],"offer":[16],"more":[17],"precise":[18],"and":[19,34,44,76,103,138,141,179,188],"flexible":[20],"control":[21],"over":[22],"fine-grained":[23,79,93],"garment":[24,80,98],"attributes.":[25],"However,":[26],"existing":[27],"methods":[28],"are":[29],"limited":[30],"to":[31,36,69,107,154],"coarse-grained":[32],"edits":[33],"fail":[35],"achieve":[37,70],"attribute-level":[38,199],"manipulation,":[39],"thereby":[40],"restricting":[41],"the":[42,183],"flexibility":[43],"composability":[45],"required":[46],"To":[50],"address":[51],"these":[52],"issues,":[53],"this":[54],"paper":[55],"proposes":[56],"a":[57,90,119,143,156,194],"Vision-Guided":[58],"Fashion":[59],"Fine-Grained":[60],"Attribute":[61],"Editing":[62],"(VFFAE)":[63],"framework,":[64],"which":[65],"leverages":[66,148],"visual":[67],"references":[68],"customized":[71],"of":[73,129,136,151,185],"both":[74],"style":[75,137],"structure":[77,139],"regions.":[81],"The":[82],"VFFAE":[83,175],"framework":[84],"involves":[85],"three":[86],"key":[87],"components:":[88],"(1)":[89],"text-driven":[91],"attribute":[94,121,166],"segmenter":[95],"that":[96,147,174],"incorporates":[97],"keypoints":[99],"as":[100,193],"spatial":[101,109],"priors":[102],"applies":[104],"deformable":[105],"attention":[106],"enhance":[108],"perception,":[110],"with":[111],"CLIP-based":[112],"multimodal":[113],"alignment":[114],"for":[115,197],"accurate":[116],"segmentation;":[117],"(2)":[118],"clothing":[120],"disentanglement":[122,189],"module":[123],"based":[124],"on":[125,169],"orthogonal":[126],"subspace":[127],"projection":[128],"CLIP":[130],"embeddings,":[131],"enabling":[132,164],"zero-shot":[133],"explicit":[134],"separation":[135],"attributes;":[140],"(3)":[142],"conditional":[144],"diffusion":[145],"pipeline":[146],"disentangled":[149],"representations":[150],"segmented":[152],"regions":[153],"fine-tune":[155],"pretrained":[157],"Stable":[158],"Diffusion":[159],"model":[160],"under":[161],"classifier-free":[162],"guidance,":[163],"controllable":[165],"editing.":[167],"Experiments":[168],"multiple":[170],"public":[171],"datasets":[172],"show":[173],"surpasses":[176],"state-of-the-art":[177],"methods,":[178],"ablation":[180],"analyses":[181],"confirm":[182],"effectiveness":[184],"its":[186],"segmentation":[187],"modules,":[190],"establishing":[191],"it":[192],"practical":[195],"solution":[196],"high-fidelity":[198]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2026-01-05T00:00:00"}