{"id":"https://openalex.org/W4293795298","doi":"https://doi.org/10.1109/icme52920.2022.9859831","title":"Disentangled Visual Representations for Extreme Human Body Video Compression","display_name":"Disentangled Visual Representations for Extreme Human Body Video Compression","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293795298","doi":"https://doi.org/10.1109/icme52920.2022.9859831"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859831","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100600016","display_name":"Ruofan Wang","orcid":"https://orcid.org/0009-0000-8236-1122"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruofan Wang","raw_affiliation_strings":["Shenzhen Graduate School, Peking University,China","Shenzhen Graduate School, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101968594","display_name":"Qi Mao","orcid":"https://orcid.org/0000-0001-9362-6237"},"institutions":[{"id":"https://openalex.org/I4391768176","display_name":"State Key Laboratory of Media Convergence and Communication","ror":"https://ror.org/0595ys057","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Mao","raw_affiliation_strings":["Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communication University of China,State Key Laboratory of Media Convergence and Communication,Beijing,China","institution_ids":["https://openalex.org/I4391768176","https://openalex.org/I75689368"]},{"raw_affiliation_string":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385178","display_name":"Shiqi Wang","orcid":"https://orcid.org/0000-0002-3583-959X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["City University of Hong Kong,Department of Computer Science,China","Department of Computer Science, City University of Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Department of Computer Science,China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040292663","display_name":"Chuanmin Jia","orcid":"https://orcid.org/0000-0002-7418-6245"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanmin Jia","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University,Beijing,China","National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050071143","display_name":"Ronggang Wang","orcid":"https://orcid.org/0000-0003-0873-0465"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronggang Wang","raw_affiliation_strings":["Shenzhen Graduate School, Peking University,China","Shenzhen Graduate School, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Shenzhen Graduate School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039832462","display_name":"Siwei Ma","orcid":"https://orcid.org/0000-0002-2731-5403"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siwei Ma","raw_affiliation_strings":["National Engineering Research Center of Visual Technology, School of Computer Science, Peking University,Beijing,China","National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9995999932289124,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9994000196456909,"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":0.829826831817627},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6940070390701294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6686588525772095},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6470460891723633},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5653601288795471},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.5173772573471069},{"id":"https://openalex.org/keywords/multiview-video-coding","display_name":"Multiview Video Coding","score":0.4775146543979645},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.47615572810173035},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4456586539745331},{"id":"https://openalex.org/keywords/texture-compression","display_name":"Texture compression","score":0.4265863299369812},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.33331459760665894},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.33063602447509766},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.27428436279296875},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.14206066727638245},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0891190767288208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829826831817627},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6940070390701294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6686588525772095},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6470460891723633},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5653601288795471},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.5173772573471069},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.4775146543979645},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.47615572810173035},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4456586539745331},{"id":"https://openalex.org/C54243161","wikidata":"https://www.wikidata.org/wiki/Q39333","display_name":"Texture compression","level":5,"score":0.4265863299369812},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.33331459760665894},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.33063602447509766},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.27428436279296875},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.14206066727638245},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0891190767288208},{"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/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859831","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.49000000953674316,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1999237308","display_name":null,"funder_award_id":"61902008,U21B2012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1603895355","https://openalex.org/W1959608418","https://openalex.org/W2129652681","https://openalex.org/W2146395539","https://openalex.org/W2785562966","https://openalex.org/W2842511635","https://openalex.org/W2962730651","https://openalex.org/W2962785568","https://openalex.org/W2963266880","https://openalex.org/W2964098744","https://openalex.org/W2964309429","https://openalex.org/W2969260367","https://openalex.org/W2971011627","https://openalex.org/W2988036615","https://openalex.org/W3005680577","https://openalex.org/W3008823916","https://openalex.org/W3017136408","https://openalex.org/W3035515747","https://openalex.org/W3035524453","https://openalex.org/W3108139283","https://openalex.org/W3178284600","https://openalex.org/W3180770160","https://openalex.org/W3195748956","https://openalex.org/W3202918664","https://openalex.org/W4288090857","https://openalex.org/W4297808394","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6767264202","https://openalex.org/W6768910476","https://openalex.org/W6771018969","https://openalex.org/W6774314701"],"related_works":["https://openalex.org/W1536392060","https://openalex.org/W2075165083","https://openalex.org/W1507361256","https://openalex.org/W19023560","https://openalex.org/W2735592227","https://openalex.org/W2069786138","https://openalex.org/W2561097443","https://openalex.org/W2926477181","https://openalex.org/W4293795298","https://openalex.org/W2040867942"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"the":[4,21,43,48,62,67,73,81,96,102,108,130,133,137,144,155],"great":[5],"promise":[6],"of":[7,36,76,87,139],"deep":[8],"neural":[9],"video":[10,56,135,175],"compression":[11],"codecs.":[12,176],"However,":[13],"there":[14],"are":[15,23,122],"still":[16],"unprecedented":[17],"challenges":[18],"ahead":[19],"when":[20],"videos":[22],"expected":[24],"to":[25,46,60,113],"be":[26,171],"encoded":[27],"with":[28,136],"extremely":[29],"low":[30],"bitrate.":[31],"Motivated":[32],"by":[33,106,173],"recent":[34],"attempts":[35],"layered":[37],"conceptual":[38],"image":[39],"compression,":[40],"we":[41,65],"make":[42],"first":[44],"attempt":[45],"leverage":[47],"disentangled":[49],"visual":[50],"representations":[51,142],"for":[52,90],"extreme":[53],"human":[54,69],"body":[55],"compression.":[57,92],"More":[58],"specifically,":[59],"capture":[61],"main":[63],"structure,":[64],"adopt":[66],"inferred":[68],"pose":[70],"keypoints":[71],"as":[72],"structure":[74,85],"code":[75],"each":[77],"frame,":[78],"thereby":[79],"deriving":[80],"motion":[82],"information":[83],"from":[84],"codes":[86,105],"adjacent":[88],"frames":[89,100],"further":[91],"To":[93],"better":[94],"exploit":[95],"texture":[97,104,110,115],"redundancy,":[98],"all":[99,140],"share":[101],"same":[103],"incorporating":[107],"proposed":[109,156],"contrastive":[111],"learning":[112],"ensure":[114],"consistency":[116],"within":[117],"a":[118,126],"video.":[119],"Two":[120],"branches":[121],"consequently":[123],"transmitted":[124],"in":[125,164],"separable":[127],"manner,":[128],"and":[129,149],"generator":[131],"synthesizes":[132],"reconstructed":[134],"combination":[138],"decoded":[141],"at":[143],"decoder":[145],"side.":[146],"Both":[147],"qualitative":[148],"quantitative":[150],"experimental":[151],"results":[152,163],"demonstrate":[153],"that":[154,169],"scheme":[157],"can":[158,170],"produce":[159],"perceptually":[160],"pleasing":[161],"reconstruction":[162],"ultra-low":[165],"bitrates":[166],"far":[167],"below":[168],"reached":[172],"other":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}