{"id":"https://openalex.org/W7138180012","doi":"https://doi.org/10.1609/aaai.v40i19.38672","title":"Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic Aggregation","display_name":"Fashion Microscope: Pixel-Level Attribute Perception via Optimal Transport and Neural Semantic Aggregation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138180012","doi":"https://doi.org/10.1609/aaai.v40i19.38672"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i19.38672","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i19.38672","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i19.38672","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129690677","display_name":"Shuili Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shuili Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042345951","display_name":"Hongzhang Mu","orcid":"https://orcid.org/0000-0003-0378-4587"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongzhang Mu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080665569","display_name":"Jiawei Sheng","orcid":"https://orcid.org/0000-0002-4865-982X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Sheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129674964","display_name":"Qianqian Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianqian Tong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129711046","display_name":"Wenyuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenyuan Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129750795","display_name":"Quangang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quangang Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103214505","display_name":"Tingwen Liu","orcid":"https://orcid.org/0000-0003-0487-0751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingwen Liu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129690677"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50260999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"19","first_page":"16343","last_page":"16351"},"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":0.8991000056266785,"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":0.8991000056266785,"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":0.03889999911189079,"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":0.008899999782443047,"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/feature","display_name":"Feature (linguistics)","score":0.6330999732017517},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.5601999759674072},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5220999717712402},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.47600001096725464},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4652000069618225},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.420199990272522},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41339999437332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601000070571899},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6183000206947327},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.5601999759674072},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41339999437332153},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i19.38672","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i19.38672","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i19.38672","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i19.38672","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Attribute-specific":[0],"fashion":[1,67],"retrieval":[2,8],"aims":[3],"to":[4,23,89,154,163],"enhance":[5],"fine-grained":[6,40],"image":[7],"by":[9,85,115],"emphasizing":[10],"the":[11,33,66,117,134,160,173,180,194,207],"similarity":[12],"of":[13,35,121,187,201],"specific":[14],"attributes.":[15],"Current":[16],"methods":[17],"primarily":[18],"rely":[19],"on":[20,53,147,172,206],"attention":[21],"mechanisms":[22],"extract":[24],"attribute-related":[25,131],"visual":[26,94],"features":[27,55,132,166],"but":[28],"face":[29],"two":[30],"key":[31,140],"challenges:":[32],"limitations":[34],"coarse-grained":[36],"localization":[37],"in":[38],"achieving":[39,183],"accuracy,":[41],"and":[42,47,78,128,138,167,176,190,204,210],"an":[43,101,149],"imbalance":[44],"between":[45],"global":[46,98],"local":[48,54],"perception,":[49],"where":[50],"excessive":[51],"focus":[52],"can":[56],"undermine":[57],"overall":[58,184],"performance.":[59],"To":[60],"address":[61],"these":[62],"issues,":[63],"we":[64],"propose":[65],"microscope":[68],"ProFashion,":[69],"which":[70],"achieves":[71],"pixel-level":[72],"attribute":[73,122,150],"awareness":[74],"through":[75,125],"optimal":[76,87],"transport":[77,88],"neural":[79],"semantic":[80,91,136,141],"aggregation.":[81],"The":[82],"framework":[83,195],"begins":[84],"employing":[86],"align":[90],"attributes":[92],"with":[93],"patterns":[95,124],"from":[96],"a":[97],"perspective,":[99],"generating":[100],"attribute-visual":[102],"value":[103],"map":[104],"that":[105,143],"highlights":[106],"distinctive":[107],"regions":[108],"while":[109],"reducing":[110],"interference.":[111],"This":[112],"is":[113,152],"followed":[114],"simulating":[116],"human":[118],"brain's":[119],"perception":[120],"feature":[123,156],"superpixel":[126],"generation":[127],"aggregation,":[129],"capturing":[130],"at":[133],"pixel":[135],"level":[137],"forming":[139],"clusters":[142],"preserve":[144],"microstructures.":[145],"Building":[146],"this,":[148],"graph":[151],"constructed":[153],"facilitate":[155],"clustering,":[157],"significantly":[158],"enhancing":[159],"framework's":[161,181],"capability":[162],"handle":[164],"overlapping":[165],"cross-scale":[168],"relationships.":[169],"Comprehensive":[170],"experiments":[171],"FashionAI,":[174,208],"DeepFashion,":[175,209],"DARN":[177,211],"datasets":[178],"demonstrate":[179],"effectiveness,":[182],"MAP":[185],"improvements":[186],"3.11%,":[188],"3.70%,":[189],"3.49%,":[191],"respectively.":[192,213],"Additionally,":[193],"delivers":[196],"relative":[197],"average":[198],"throughput":[199],"gains":[200],"26.94%,":[202],"22.22%,":[203],"24.78%":[205],"datasets,":[212]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}