{"id":"https://openalex.org/W3193428169","doi":"https://doi.org/10.1109/icip42928.2021.9506505","title":"Disentangling Latent Groups Of Factors","display_name":"Disentangling Latent Groups Of Factors","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3193428169","doi":"https://doi.org/10.1109/icip42928.2021.9506505","mag":"3193428169"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-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/A5101261291","display_name":"Nakamasa Inoue","orcid":"https://orcid.org/0009-0006-1145-0914"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nakamasa Inoue","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105179702","display_name":"Ryota Yamada","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryota Yamada","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073109086","display_name":"Rei Kawakami","orcid":"https://orcid.org/0000-0003-2342-3324"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I67530263","display_name":"Denso (United States)","ror":"https://ror.org/02w314k38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132650","https://openalex.org/I67530263"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Rei Kawakami","raw_affiliation_strings":["Tokyo Institute of Technology","Denso IT Laboratory, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Denso IT Laboratory, Inc","institution_ids":["https://openalex.org/I67530263"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100862952","display_name":"Ikuro Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I67530263","display_name":"Denso (United States)","ror":"https://ror.org/02w314k38","country_code":"US","type":"company","lineage":["https://openalex.org/I4210132650","https://openalex.org/I67530263"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Ikuro Sato","raw_affiliation_strings":["Tokyo Institute of Technology","Denso IT Laboratory, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Denso IT Laboratory, Inc","institution_ids":["https://openalex.org/I67530263"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09620813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2548","last_page":"2552"},"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/T11448","display_name":"Face recognition and analysis","score":0.9993000030517578,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9775999784469604,"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":0.7951560020446777},{"id":"https://openalex.org/keywords/header","display_name":"Header","score":0.7814456224441528},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.6645485758781433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6624555587768555},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6078914403915405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5479110479354858},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5255345702171326},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.510452389717102},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4881039559841156},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48706915974617004},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.4724807143211365},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3905564248561859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7951560020446777},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.7814456224441528},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.6645485758781433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6624555587768555},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6078914403915405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5479110479354858},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5255345702171326},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.510452389717102},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4881039559841156},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48706915974617004},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.4724807143211365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3905564248561859},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip42928.2021.9506505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2138621090","https://openalex.org/W2142838865","https://openalex.org/W2753738274","https://openalex.org/W2785519580","https://openalex.org/W2885949783","https://openalex.org/W2903782687","https://openalex.org/W2940579548","https://openalex.org/W2950662112","https://openalex.org/W2962898354","https://openalex.org/W2963466847","https://openalex.org/W2964127395","https://openalex.org/W2969985801","https://openalex.org/W2970336984","https://openalex.org/W2990376402","https://openalex.org/W2991234496","https://openalex.org/W3005680577","https://openalex.org/W3035524453","https://openalex.org/W3082368324","https://openalex.org/W3090806161","https://openalex.org/W3109684201","https://openalex.org/W4287995546","https://openalex.org/W4295112158","https://openalex.org/W6640963894","https://openalex.org/W6744627333","https://openalex.org/W6745687250","https://openalex.org/W6748223763","https://openalex.org/W6748391871","https://openalex.org/W6753859023","https://openalex.org/W6756663807","https://openalex.org/W6761687776","https://openalex.org/W6763012920","https://openalex.org/W6771994616","https://openalex.org/W6774314701","https://openalex.org/W6774759361"],"related_works":["https://openalex.org/W2171597999","https://openalex.org/W2189136227","https://openalex.org/W1866537546","https://openalex.org/W630850086","https://openalex.org/W3200508093","https://openalex.org/W4372053344","https://openalex.org/W3193978431","https://openalex.org/W2379752180","https://openalex.org/W2519240373","https://openalex.org/W1496096987"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,25,54,57,68,92,128],"framework":[4],"for":[5,10],"training":[6],"variational":[7],"autoencoders":[8],"(VAEs)":[9],"image":[11,33],"distributions":[12],"that":[13],"have":[14],"latent":[15],"groups":[16],"of":[17,49,84,100,112,131],"factors.":[18],"Our":[19],"key":[20],"idea":[21],"is":[22,75],"to":[23,27,35,125],"introduce":[24],"mechanism":[26],"predict":[28],"the":[29,72,78,82,110,113],"factor":[30],"group":[31,99],"an":[32,46,52],"belongs":[34],"while":[36],"simultaneously":[37],"disentangling":[38],"factors":[39,101],"in":[40,94],"it.":[41],"More":[42],"specifically,":[43],"we":[44,90],"propose":[45],"architecture":[47],"consisting":[48],"three":[50],"components:":[51],"encoder,":[53],"decoder,":[55],"and":[56,71,108,134],"factor-group":[58],"prediction":[59],"header.":[60],"The":[61,116],"first":[62],"two":[63],"components":[64],"are":[65],"trained":[66,76],"with":[67,77],"VAE":[69],"objective,":[70],"last":[73],"one":[74,98],"proposed":[79,114],"algorithm":[80],"using":[81],"loss":[83],"unsupervised":[85],"contrastive":[86],"learning.":[87],"In":[88],"experiments,":[89],"designed":[91],"task":[93],"which":[95],"more":[96],"than":[97],"were":[102],"entangled":[103],"by":[104],"combining":[105],"multiple":[106],"datasets":[107],"demonstrated":[109],"effectiveness":[111],"framework.":[115],"Mutual":[117],"Information":[118],"Gap":[119],"score":[120],"was":[121],"improved":[122],"from":[123],"0.089":[124],"0.125":[126],"on":[127],"merged":[129],"dataset":[130],"Color-dSprites,":[132],"3DShapes,":[133],"MPI3D.":[135]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}