{"id":"https://openalex.org/W4390577888","doi":"https://doi.org/10.1109/tmm.2023.3345180","title":"Disentangled Representation Learning for Controllable Person Image Generation","display_name":"Disentangled Representation Learning for Controllable Person Image Generation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390577888","doi":"https://doi.org/10.1109/tmm.2023.3345180"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3345180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3345180","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5031765917","display_name":"Wenju Xu","orcid":"https://orcid.org/0000-0003-2740-0357"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenju Xu","raw_affiliation_strings":["AMAZON, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2740-0357","affiliations":[{"raw_affiliation_string":"AMAZON, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027540915","display_name":"Chengjiang Long","orcid":"https://orcid.org/0000-0003-1584-7290"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengjiang Long","raw_affiliation_strings":["META Reality Labs, Burlingame, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1584-7290","affiliations":[{"raw_affiliation_string":"META Reality Labs, Burlingame, CA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083221103","display_name":"Yongwei Nie","orcid":"https://orcid.org/0000-0002-8922-3205"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Nie","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8922-3205","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100399485","display_name":"Guanghui Wang","orcid":"https://orcid.org/0000-0003-3182-104X"},"institutions":[{"id":"https://openalex.org/I530967","display_name":"Toronto Metropolitan University","ror":"https://ror.org/05g13zd79","country_code":"CA","type":"education","lineage":["https://openalex.org/I530967"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Guanghui Wang","raw_affiliation_strings":["Department of Computer Science, Toronto Metropolitan University, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-3182-104X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Toronto Metropolitan University, Toronto, ON, Canada","institution_ids":["https://openalex.org/I530967"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4306,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81276719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"6065","last_page":"6077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983999729156494,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9983999729156494,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.995199978351593,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.826274037361145},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6718138456344604},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6683018803596497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6398997902870178},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6008870601654053},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.555796205997467},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5291077494621277},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46628519892692566},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4591358006000519},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3548152446746826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33635956048965454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.826274037361145},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6718138456344604},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6683018803596497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6398997902870178},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6008870601654053},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.555796205997467},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5291077494621277},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46628519892692566},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4591358006000519},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3548152446746826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33635956048965454},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3345180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3345180","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2204750386","https://openalex.org/W2296073425","https://openalex.org/W2471768434","https://openalex.org/W2517617019","https://openalex.org/W2598915960","https://openalex.org/W2603777577","https://openalex.org/W2607151106","https://openalex.org/W2771558241","https://openalex.org/W2798714868","https://openalex.org/W2950689937","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2962963674","https://openalex.org/W2962974533","https://openalex.org/W2963091558","https://openalex.org/W2963266880","https://openalex.org/W2963890275","https://openalex.org/W2964002510","https://openalex.org/W2964097473","https://openalex.org/W2964219393","https://openalex.org/W2964309429","https://openalex.org/W3034214199","https://openalex.org/W3035515747","https://openalex.org/W3088241548","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3119557339","https://openalex.org/W3127751679","https://openalex.org/W3131500599","https://openalex.org/W3134275945","https://openalex.org/W3166096919","https://openalex.org/W3176412779","https://openalex.org/W3177421482","https://openalex.org/W3189898414","https://openalex.org/W3200121240","https://openalex.org/W3204595673","https://openalex.org/W3205071568","https://openalex.org/W3212203927","https://openalex.org/W4200326209","https://openalex.org/W4200631136","https://openalex.org/W4213019189","https://openalex.org/W4214736485","https://openalex.org/W4221153186","https://openalex.org/W4312896571","https://openalex.org/W4313030876","https://openalex.org/W4385245566","https://openalex.org/W4386047789","https://openalex.org/W4386071778","https://openalex.org/W6718140377","https://openalex.org/W6729110096","https://openalex.org/W6738824914","https://openalex.org/W6765779288","https://openalex.org/W6784094891","https://openalex.org/W6790275670"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2357256365","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2348502264","https://openalex.org/W2365486383","https://openalex.org/W2362059367","https://openalex.org/W4205302943","https://openalex.org/W2901443725","https://openalex.org/W2350084742"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,59,143,198],"propose":[4,60,144],"a":[5,67,75,81,86,145],"novel":[6,68,146],"framework":[7],"named":[8],"DRL-CPG":[9],"to":[10,52,61,85,97,120,132,150,180,202],"learn":[11,203],"disentangled":[12,63,204],"latent":[13,64,205],"representation":[14,55],"for":[15,209],"controllable":[16],"person":[17,24,104,210],"image":[18,211],"generation,":[19],"which":[20,107],"can":[21],"produce":[22],"realistic":[23,193],"images":[25],"with":[26,71,162,207],"desired":[27],"poses":[28],"and":[29,37,115,137,158,185,191],"human":[30,189],"attributes":[31,153],"(e.g.":[32,154],"pose,":[33],"head,":[34],"upper":[35],"clothes,":[36],"pants)":[38],"provided":[39],"by":[40],"various":[41],"source":[42],"persons.":[43],"Unlike":[44],"the":[45,49,54,103,111,117,122,130,135,140,155,159,175,183,200],"existing":[46],"works":[47],"leveraging":[48],"semantic":[50],"masks":[51,101],"obtain":[53],"of":[56,77,113,139,187],"each":[57,126],"component,":[58],"generate":[62],"code":[65],"via":[66],"attribute":[69,147,160],"encoder":[70,119],"transformers":[72,208],"trained":[73],"in":[74],"manner":[76],"curriculum":[78],"learning":[79],"from":[80,102],"relatively":[82],"easy":[83],"step":[84],"gradually":[87],"hard":[88],"one.":[89],"A":[90],"random":[91],"component":[92,100],"mask-agnostic":[93],"strategy":[94],"is":[95,178],"introduced":[96],"randomly":[98],"remove":[99],"segmentation":[105],"masks,":[106],"aims":[108],"at":[109],"increasing":[110],"difficulty":[112],"training":[114],"promoting":[116],"transformer":[118],"recognize":[121],"underlying":[123],"boundaries":[124],"between":[125],"component.":[127],"This":[128],"enables":[129],"model":[131],"transfer":[133,181],"both":[134,182],"shape":[136,186],"texture":[138,184],"components.":[141],"Furthermore,":[142],"decoder":[148],"network":[149],"integrate":[151],"multi-level":[152],"structure":[156],"feature":[157],"representation)":[161],"well-designed":[163],"Dual":[164],"Adaptive":[165],"Denormalization":[166],"(DAD)":[167],"residual":[168],"blocks.":[169],"Extensive":[170],"experiments":[171],"strongly":[172],"demonstrate":[173],"that":[174],"proposed":[176],"approach":[177],"able":[179],"different":[188],"parts":[190],"yield":[192],"results.":[194],"To":[195],"our":[196],"knowledge,":[197],"are":[199],"first":[201],"representations":[206],"generation.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}