{"id":"https://openalex.org/W4388187887","doi":"https://doi.org/10.1145/3581783.3613859","title":"Disentangled Representation Learning for Multimedia","display_name":"Disentangled Representation Learning for Multimedia","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388187887","doi":"https://doi.org/10.1145/3581783.3613859"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613859","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613859","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613859","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613859","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022927606","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"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":"Xin Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0351-2939","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420416","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-0943-2286"},"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":"Hong Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0943-2286","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"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":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2236-9290","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.4805,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.94385374,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9702","last_page":"9704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9983999729156494,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7700227499008179},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5836421251296997},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5516043901443481},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5054235458374023},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.503023087978363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47182947397232056},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4586370885372162},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4410395622253418},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42066630721092224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3528215289115906},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14390918612480164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700227499008179},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5836421251296997},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5516043901443481},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5054235458374023},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.503023087978363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47182947397232056},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4586370885372162},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4410395622253418},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42066630721092224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3528215289115906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14390918612480164},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613859","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613859","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613859","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3613859","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3613859","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3613859","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1570076315","display_name":null,"funder_award_id":"BNR2023RC01003,BNR2023TD03006","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"},{"id":"https://openalex.org/G2628686278","display_name":null,"funder_award_id":"62222209, 62250008, 62102222","funder_id":"https://openalex.org/F4320334062","funder_display_name":"National Natural Science Foundation of China-Liaoning Joint Fund"},{"id":"https://openalex.org/G3720940119","display_name":null,"funder_award_id":"2020AAA0106300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null},{"id":"https://openalex.org/F4320334062","display_name":"National Natural Science Foundation of China-Liaoning Joint Fund","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388187887.pdf","grobid_xml":"https://content.openalex.org/works/W4388187887.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2973131617","https://openalex.org/W2981519363","https://openalex.org/W2999905431","https://openalex.org/W3080374445","https://openalex.org/W3093273257","https://openalex.org/W3142849873","https://openalex.org/W3169346140","https://openalex.org/W3187249216","https://openalex.org/W3195406508","https://openalex.org/W3206827956","https://openalex.org/W3213068453","https://openalex.org/W4205324649","https://openalex.org/W4226054951","https://openalex.org/W4240926358","https://openalex.org/W4295934584","https://openalex.org/W4304080420","https://openalex.org/W4385565184","https://openalex.org/W6600146492","https://openalex.org/W6600577311","https://openalex.org/W6600788769","https://openalex.org/W6803947598"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"Disentangled":[0],"Representation":[1],"Learning":[2],"(DRL)":[3],"aims":[4],"to":[5,167],"learn":[6],"a":[7,60,82],"model":[8,72,114],"capable":[9],"of":[10,27,31,43,51,85],"identifying":[11],"and":[12,113,131,160],"disentangling":[13],"the":[14,19,47,71,138,206,210],"underlying":[15,29],"factors":[16,30],"hidden":[17],"in":[18,22,39,69,81,177,186,209],"observable":[20],"data":[21,94],"representation":[23],"form.":[24],"The":[25],"process":[26,50],"separating":[28],"variation":[32],"into":[33,142],"variables":[34],"with":[35],"semantic":[36],"meaning":[37],"benefits":[38],"learning":[40,62],"explainable":[41],"representations":[42],"data,":[44],"which":[45],"imitates":[46],"meaningful":[48],"understanding":[49],"humans":[52],"when":[53],"observing":[54],"an":[55],"object":[56],"or":[57],"relation.":[58],"As":[59],"general":[61],"strategy,":[63],"DRL":[64,103,122,141,170,187,207],"has":[65],"demonstrated":[66],"its":[67],"power":[68],"improving":[70],"explainability,":[73],"controllability,":[74],"robustness,":[75],"as":[76,78,88,188,190],"well":[77,189],"generalization":[79],"capacity":[80],"wide":[83],"range":[84],"scenarios":[86],"such":[87],"computer":[89],"vision,":[90],"natural":[91],"language":[92],"processing,":[93],"mining":[95],"etc.":[96],"In":[97],"this":[98,199],"tutorial,":[99],"we":[100,182],"comprehensively":[101],"present":[102],"from":[104],"various":[105],"aspects":[106],"including":[107],"motivations,":[108],"definitions,":[109,127],"methodologies,":[110],"evaluations,":[111],"applications":[112],"designs":[115],"for":[116,140,204],"multimedia.":[117],"We":[118,135,163,197],"discuss":[119],"works":[120],"on":[121,124],"based":[123],"two":[125],"well-recognized":[126],"i.e.,":[128,145],"Intuitive":[129],"Definition":[130],"Group":[132],"Theory":[133],"Definition.":[134],"further":[136],"categorize":[137],"methodologies":[139],"four":[143],"groups,":[144],"Traditional":[146],"Statistical":[147],"Approaches,":[148,152,157],"Variational":[149],"Auto-encoder":[150],"Based":[151,156],"Generative":[153],"Adversarial":[154],"Networks":[155],"Hierarchical":[158],"Approaches":[159],"Other":[161],"Approaches.":[162],"also":[164],"analyze":[165],"principles":[166],"design":[168],"different":[169,175],"models":[171],"that":[172],"may":[173,201],"benefit":[174],"tasks":[176],"practical":[178],"multimedia":[179,211],"applications.":[180],"Finally,":[181],"point":[183],"out":[184],"challenges":[185],"potential":[191],"research":[192,208],"directions":[193],"deserving":[194],"future":[195],"investigations.":[196],"believe":[198],"tutorial":[200],"provide":[202],"insights":[203],"promoting":[205],"community.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}