{"id":"https://openalex.org/W3163844068","doi":"https://doi.org/10.1109/icpr48806.2021.9411925","title":"Disentangled Representation Learning for Controllable Image Synthesis: An Information-Theoretic Perspective","display_name":"Disentangled Representation Learning for Controllable Image Synthesis: An Information-Theoretic Perspective","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3163844068","doi":"https://doi.org/10.1109/icpr48806.2021.9411925","mag":"3163844068"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9411925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9411925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5085323907","display_name":"Shichang Tang","orcid":"https://orcid.org/0000-0003-0089-7367"},"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":"Shichang Tang","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":"middle","author":{"id":"https://openalex.org/A5101654991","display_name":"Xu Zhou","orcid":"https://orcid.org/0000-0003-3418-1447"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhou","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"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/A5062841020","display_name":"Yi Ma","orcid":"https://orcid.org/0000-0001-5485-419X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Ma","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1606 3498","issue":null,"first_page":"10042","last_page":"10049"},"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":0.9997000098228455,"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":0.9997000098228455,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9965000152587891,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9927999973297119,"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/mnist-database","display_name":"MNIST database","score":0.7678288221359253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6124081611633301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5390640497207642},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5243887305259705},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5125102996826172},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4657467305660248},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4632604718208313},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4469069838523865},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43501016497612},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.37793880701065063},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34806519746780396},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34062570333480835}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7678288221359253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6124081611633301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5390640497207642},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5243887305259705},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5125102996826172},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4657467305660248},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4632604718208313},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4469069838523865},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43501016497612},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37793880701065063},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34806519746780396},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34062570333480835},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9411925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9411925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1691728462","https://openalex.org/W1813765053","https://openalex.org/W1834627138","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2135346645","https://openalex.org/W2145094598","https://openalex.org/W2163922914","https://openalex.org/W2188365844","https://openalex.org/W2411541852","https://openalex.org/W2412320034","https://openalex.org/W2548275288","https://openalex.org/W2554314924","https://openalex.org/W2559823555","https://openalex.org/W2607170299","https://openalex.org/W2617602381","https://openalex.org/W2621350877","https://openalex.org/W2753738274","https://openalex.org/W2807692250","https://openalex.org/W2883861033","https://openalex.org/W2903782687","https://openalex.org/W2950776302","https://openalex.org/W2960178077","https://openalex.org/W2962738009","https://openalex.org/W2962770929","https://openalex.org/W2962772087","https://openalex.org/W2962793481","https://openalex.org/W2962808998","https://openalex.org/W2962947361","https://openalex.org/W2963010714","https://openalex.org/W2963226019","https://openalex.org/W2963373786","https://openalex.org/W2963626105","https://openalex.org/W2963683323","https://openalex.org/W2963684088","https://openalex.org/W2963746531","https://openalex.org/W2963767194","https://openalex.org/W2963890275","https://openalex.org/W2963981733","https://openalex.org/W2970554285","https://openalex.org/W2982232682","https://openalex.org/W2997574889","https://openalex.org/W3034720584","https://openalex.org/W3035574324","https://openalex.org/W3084315282","https://openalex.org/W3104876213","https://openalex.org/W4288356932","https://openalex.org/W4293320219","https://openalex.org/W4294568686","https://openalex.org/W4301206121","https://openalex.org/W4320013936","https://openalex.org/W6637412569","https://openalex.org/W6638464934","https://openalex.org/W6640963894","https://openalex.org/W6678815747","https://openalex.org/W6680150708","https://openalex.org/W6681096077","https://openalex.org/W6685352114","https://openalex.org/W6687045409","https://openalex.org/W6714590955","https://openalex.org/W6715501732","https://openalex.org/W6718140377","https://openalex.org/W6718379498","https://openalex.org/W6729482032","https://openalex.org/W6729767818","https://openalex.org/W6734074887","https://openalex.org/W6738438352","https://openalex.org/W6738543193","https://openalex.org/W6739139180","https://openalex.org/W6744627333","https://openalex.org/W6745535286","https://openalex.org/W6748038043","https://openalex.org/W6750298367","https://openalex.org/W6752944736","https://openalex.org/W6762655333","https://openalex.org/W6765779288","https://openalex.org/W6765907231","https://openalex.org/W6771275388","https://openalex.org/W6779093361"],"related_works":["https://openalex.org/W2950475743","https://openalex.org/W4386603768","https://openalex.org/W2886711096","https://openalex.org/W4380078352","https://openalex.org/W3046591097","https://openalex.org/W2590796488","https://openalex.org/W2734358244","https://openalex.org/W2750384547","https://openalex.org/W2809732489","https://openalex.org/W3088091256"],"abstract_inverted_index":{"In":[0],"this":[1,73],"paper,":[2],"we":[3,75],"look":[4],"into":[5,104],"the":[6,30,67,77,81,92,97,105,114,119,154],"problem":[7,79],"of":[8,29,59,70,83,91,149],"disentangled":[9],"representation":[10],"learning":[11,78],"and":[12,42,101,118,134],"controllable":[13,124],"image":[14,98,125],"synthesis":[15,99],"in":[16,96],"a":[17,27],"deep":[18],"generative":[19],"model.":[20],"We":[21,108],"develop":[22],"an":[23,146],"encoder-decoder":[24],"architecture":[25],"for":[26],"variant":[28],"Variational":[31],"Auto-Encoder":[32],"(VAE)":[33],"with":[34],"two":[35],"latent":[36],"codes":[37],"z":[38,43,51,62],"<sub":[39,44,52,63],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[40,45,53,64],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[41,65],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sub>":[46,54],".":[47],"Our":[48,127],"framework":[49],"uses":[50],"to":[55,137],"capture":[56],"specified":[57],"factors":[58,69],"variation":[60],"while":[61],"captures":[66],"complementary":[68],"variation.":[71],"To":[72],"end,":[74],"analyze":[76],"from":[80],"perspective":[82],"multivariate":[84],"mutual":[85,94],"information,":[86],"derive":[87],"optimizable":[88],"lower":[89],"bounds":[90],"conditional":[93],"information":[95],"processes":[100],"incorporate":[102],"them":[103],"training":[106],"objective.":[107],"validate":[109],"our":[110],"method":[111],"empirically":[112],"on":[113],"Color":[115],"MNIST":[116],"dataset":[117,121],"CelebA":[120],"by":[122],"showing":[123],"syntheses.":[126],"proposed":[128],"paradigm":[129],"is":[130,135,144],"simple":[131],"yet":[132],"effective":[133],"applicable":[136],"many":[138],"situations,":[139],"including":[140],"those":[141],"where":[142,153],"there":[143],"not":[145],"explicit":[147],"factorization":[148],"features":[150,155],"available,":[151],"or":[152],"are":[156],"non-categorical.":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}