{"id":"https://openalex.org/W3093022753","doi":"https://doi.org/10.1145/3422852.3423480","title":"Towards Purely Unsupervised Disentanglement of Appearance and Shape for Person Images Generation","display_name":"Towards Purely Unsupervised Disentanglement of Appearance and Shape for Person Images Generation","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093022753","doi":"https://doi.org/10.1145/3422852.3423480","mag":"3093022753"},"language":"en","primary_location":{"id":"doi:10.1145/3422852.3423480","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422852.3423480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Human-centric Multimedia Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110658995","display_name":"Hongtao Yang","orcid":"https://orcid.org/0009-0009-0059-5693"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongtao Yang","raw_affiliation_strings":["The Australian National University, Canberra, ACT, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378792","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-5511-2558"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032642601","display_name":"Wenbing Huang","orcid":"https://orcid.org/0000-0002-2566-4159"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbing Huang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015970030","display_name":"Xuming He","orcid":"https://orcid.org/0000-0003-2150-1237"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuming He","raw_affiliation_strings":["ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038550641","display_name":"Fatih Porikli","orcid":"https://orcid.org/0000-0002-1520-4466"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fatih Porikli","raw_affiliation_strings":["The Australian National University, Canberra, ACT, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"41"},"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":0.9998000264167786,"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":0.9998000264167786,"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/T11019","display_name":"Image Enhancement Techniques","score":0.998199999332428,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9980000257492065,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7555689811706543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7545668482780457},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6964662075042725},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6107860803604126},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5793688297271729},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5482259392738342},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5337606072425842},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48134931921958923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4750223755836487},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4650576710700989},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.45736512541770935}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7555689811706543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545668482780457},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6964662075042725},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6107860803604126},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5793688297271729},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5482259392738342},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5337606072425842},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48134931921958923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4750223755836487},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4650576710700989},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.45736512541770935},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3422852.3423480","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422852.3423480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Human-centric Multimedia Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2125389028","https://openalex.org/W2331128040","https://openalex.org/W2471768434","https://openalex.org/W2552465644","https://openalex.org/W2559085405","https://openalex.org/W2559823555","https://openalex.org/W2584009249","https://openalex.org/W2592480533","https://openalex.org/W2593414223","https://openalex.org/W2598915960","https://openalex.org/W2605287558","https://openalex.org/W2608015370","https://openalex.org/W2739748921","https://openalex.org/W2752328934","https://openalex.org/W2753738274","https://openalex.org/W2766091292","https://openalex.org/W2768192412","https://openalex.org/W2771558241","https://openalex.org/W2771740950","https://openalex.org/W2798714868","https://openalex.org/W2798813225","https://openalex.org/W2883309205","https://openalex.org/W2883861033","https://openalex.org/W2886799640","https://openalex.org/W2888164449","https://openalex.org/W2951939904","https://openalex.org/W2953318193","https://openalex.org/W2962819541","https://openalex.org/W2962879692","https://openalex.org/W2962963674","https://openalex.org/W2963032478","https://openalex.org/W2963045453","https://openalex.org/W2963216700","https://openalex.org/W2963522749","https://openalex.org/W2963896050","https://openalex.org/W2964002510","https://openalex.org/W2964050021","https://openalex.org/W2964270502","https://openalex.org/W4242177601","https://openalex.org/W4254373586"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W2361861616","https://openalex.org/W4310988119","https://openalex.org/W4285226279"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"a":[3,60],"fairly":[4],"of":[5,12,141,212],"research":[6],"interests":[7],"in":[8,59,166],"exploring":[9],"the":[10,34,85,94,99,125,132,139,163,183,199],"disentanglement":[11,204],"appearance":[13,88,129,143,171],"and":[14,87,97,110,128,195,205],"shape":[15,86,127,155],"from":[16,90],"human":[17,42,177,185],"images.":[18],"Most":[19],"existing":[20],"endeavours":[21],"pursuit":[22],"this":[23,51,57,75],"goal":[24],"by":[25,101],"either":[26],"using":[27,174],"training":[28,35],"images":[29,92,211],"with":[30,37,215],"annotations":[31],"or":[32,46,218],"regulating":[33],"process":[36],"external":[38,71],"clues":[39],"such":[40],"as":[41,157],"skeleton,":[43,178],"body":[44],"segmentation":[45],"cloth":[47],"patches":[48],"etc.":[49],"In":[50],"paper,":[52],"we":[53,77],"aim":[54],"to":[55,82,120,137,162,168,208],"address":[56],"challenge":[58],"more":[61],"unsupervised":[62,151],"manner---we":[63],"do":[64],"not":[65],"require":[66],"any":[67,70],"annotation":[68],"nor":[69],"task-specific":[72],"clues.":[73],"To":[74],"end,":[76],"formulate":[78],"an":[79],"encoder-decoder-like":[80],"network":[81,180],"extract":[83],"both":[84],"features":[89,156],"input":[91,164,176],"at":[93],"same":[95],"time,":[96],"train":[98],"parameters":[100],"three":[102],"losses:":[103],"feature":[104,114],"adversarial":[105,115],"loss,":[106],"color":[107,133],"consistency":[108,134],"loss":[109,116,135],"reconstruction":[111],"loss.":[112],"The":[113],"mainly":[117],"impose":[118],"little":[119],"none":[121],"mutual":[122],"information":[123],"between":[124],"extracted":[126],"features,":[130],"while":[131,187],"is":[136,206],"encourage":[138],"invariance":[140],"person":[142],"conditioned":[144],"on":[145,193],"different":[146],"shapes.":[147],"More":[148],"importantly,":[149],"our":[150,179],"framework":[152],"utilizes":[153],"learned":[154],"masks":[158],"which":[159],"are":[160],"applied":[161],"itself":[165],"order":[167],"obtain":[169],"clean":[170,203],"features.":[172],"Without":[173],"fixed":[175],"better":[181],"preserves":[182],"conditional":[184],"posture":[186],"requiring":[188],"less":[189],"supervision.":[190],"Experimental":[191],"results":[192],"DeepFashion":[194],"Market1501":[196],"demonstrate":[197],"that":[198],"proposed":[200],"method":[201],"achieves":[202],"able":[207],"synthesis":[209],"novel":[210],"comparable":[213],"quality":[214],"state-of-the-art":[216],"weakly-supervised":[217],"even":[219],"supervised":[220],"methods.":[221]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}