{"id":"https://openalex.org/W4402325759","doi":"https://doi.org/10.1109/mmsp61759.2024.10743797","title":"Multi-Reference Generative Face Video Compression with Contrastive Learning","display_name":"Multi-Reference Generative Face Video Compression with Contrastive Learning","publication_year":2024,"publication_date":"2024-10-02","ids":{"openalex":"https://openalex.org/W4402325759","doi":"https://doi.org/10.1109/mmsp61759.2024.10743797"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp61759.2024.10743797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp61759.2024.10743797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.01029","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005502345","display_name":"Goluck Konuko","orcid":null},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Goluck Konuko","raw_affiliation_strings":["CenraleSupelec - Université Paris-Saclay,Laboratoire de Signaux et Systè mes (L2S),Paris,France"],"affiliations":[{"raw_affiliation_string":"CenraleSupelec - Université Paris-Saclay,Laboratoire de Signaux et Systè mes (L2S),Paris,France","institution_ids":["https://openalex.org/I102475099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034069364","display_name":"Giuseppe Valenzise","orcid":"https://orcid.org/0000-0002-5840-5743"},"institutions":[{"id":"https://openalex.org/I4210097418","display_name":"Laboratoire des signaux et syst\u00e8mes","ror":"https://ror.org/00skw9v43","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210097418","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Giuseppe Valenzise","raw_affiliation_strings":["CNRS,Laboratoire de Signaux et Systè mes (L2S),Paris,France"],"affiliations":[{"raw_affiliation_string":"CNRS,Laboratoire de Signaux et Systè mes (L2S),Paris,France","institution_ids":["https://openalex.org/I4210097418","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005502345"],"corresponding_institution_ids":["https://openalex.org/I102475099"],"apc_list":null,"apc_paid":null,"fwci":0.3439,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54427428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10860","display_name":"Speech and Audio Processing","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9693999886512756,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9634000062942505,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8791295886039734},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6846477389335632},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.5439772605895996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5295596718788147},{"id":"https://openalex.org/keywords/bitstream","display_name":"Bitstream","score":0.514034628868103},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.4960697591304779},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4714190661907196},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4531481862068176},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.423606812953949},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3604905903339386},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.16101351380348206},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.12978795170783997},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.10326984524726868},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09424084424972534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8791295886039734},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6846477389335632},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.5439772605895996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5295596718788147},{"id":"https://openalex.org/C136695289","wikidata":"https://www.wikidata.org/wiki/Q415568","display_name":"Bitstream","level":3,"score":0.514034628868103},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.4960697591304779},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4714190661907196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4531481862068176},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.423606812953949},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3604905903339386},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16101351380348206},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.12978795170783997},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.10326984524726868},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09424084424972534},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/mmsp61759.2024.10743797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp61759.2024.10743797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 26th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.01029","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.01029","pdf_url":"https://arxiv.org/pdf/2409.01029","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-04683529v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04683529","pdf_url":"https://hal.science/hal-04683529v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE 26th International Workshop on Multimedia Signal Processing (MMSP), IEEE Signal Processing Society, Oct 2024, WEST LAFAYETTE - INDIANA, United States. ⟨10.1109/mmsp61759.2024.10743797⟩","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2409.01029","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.01029","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.01029","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.01029","pdf_url":"https://arxiv.org/pdf/2409.01029","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324252","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"},{"id":"https://openalex.org/F4320334537","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402325759.pdf","grobid_xml":"https://content.openalex.org/works/W4402325759.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2962785568","https://openalex.org/W3005680577","https://openalex.org/W3008823916","https://openalex.org/W3017136408","https://openalex.org/W3096655658","https://openalex.org/W3160069937","https://openalex.org/W3180770160","https://openalex.org/W4283819141","https://openalex.org/W4292828480","https://openalex.org/W4297039696","https://openalex.org/W4308236559","https://openalex.org/W4312581434","https://openalex.org/W4386597022","https://openalex.org/W6637373629","https://openalex.org/W6767264202","https://openalex.org/W6774314701"],"related_works":["https://openalex.org/W4205607586","https://openalex.org/W2980252933","https://openalex.org/W1994767227","https://openalex.org/W2054991208","https://openalex.org/W4206534210","https://openalex.org/W2610181890","https://openalex.org/W2359242134","https://openalex.org/W2071850723","https://openalex.org/W2039662546","https://openalex.org/W2144823424"],"abstract_inverted_index":{"Generative":[0],"face":[1],"video":[2,16,52],"coding":[3,25,223],"(GFVC)":[4],"has":[5,83],"been":[6,84],"demonstrated":[7],"as":[8,59,94,141],"a":[9,80,142,153,160,171,205],"potential":[10],"approach":[11,144],"to":[12,34,50,78,109,145,195,214,229],"low-latency,":[13],"low":[14],"bitrate":[15,30],"conferencing.":[17],"GFVC":[18,55,89,129,231],"frameworks":[19,56],"achieve":[20,204],"an":[21],"extreme":[22],"gain":[23,207],"in":[24,67,87,152,208,238],"efficiency":[26],"with":[27,199],"over":[28],"70%":[29],"savings":[31],"when":[32,150],"compared":[33,228],"conventional":[35],"codecs":[36],"at":[37,211,253],"bitrates":[38,213],"below":[39],"10kbps.":[40],"In":[41,71],"recent":[42],"MPEG/JVET":[43],"standardization":[44],"efforts,":[45],"all":[46],"the":[47,62,95,98,107,111,123,128,176,180],"information":[48,65],"required":[49],"reconstruct":[51],"sequences":[53,198],"using":[54,170],"are":[57,122],"adopted":[58],"part":[60],"of":[61,73,127,179,240],"supplemental":[63],"enhancement":[64],"(SEI)":[66],"existing":[68],"compression":[69],"pipelines.":[70],"light":[72],"this":[74,133],"development,":[75],"we":[76,135,158],"aim":[77],"address":[79],"challenge":[81,105],"that":[82,169],"weakly":[85],"addressed":[86],"prior":[88],"frameworks,":[90],"i.e.,":[91],"reconstruction":[92,147,209,225],"drift":[93],"distance":[96],"between":[97],"reference":[99,112,139,201],"and":[100,218,224,233,243],"target":[101],"frames":[102,202],"increases.":[103],"This":[104],"creates":[106],"need":[108],"update":[110],"buffer":[113],"more":[114,118,234],"frequently":[115],"by":[116],"transmitting":[117],"Intra-refresh":[119],"frames,":[120],"which":[121],"most":[124],"expensive":[125],"element":[126],"bitstream.":[130],"To":[131],"overcome":[132],"problem,":[134],"propose":[136,159],"instead":[137],"multiple":[138],"animation":[140,181,236],"robust":[143],"minimizing":[146],"drift,":[148],"especially":[149],"used":[151,194],"bi-directional":[154],"prediction":[155],"mode.":[156],"Further,":[157],"contrastive":[161,172],"learning":[162,173],"formulation":[163],"for":[164],"multi-reference":[165],"animation.":[166],"We":[167],"observe":[168],"framework":[174],"enhances":[175],"representation":[177],"capabilities":[178],"generator.":[182],"The":[183,247],"resulting":[184],"framework,":[185],"MRDAC":[186],"(Multi-Reference":[187],"Deep":[188],"Animation":[189],"Codec)":[190],"can":[191],"therefore":[192],"be":[193,251],"compress":[196],"longer":[197],"fewer":[200],"or":[203],"significant":[206,222],"accuracy":[210],"comparable":[212],"previous":[215,230],"frameworks.":[216],"Quantitative":[217],"qualitative":[219],"results":[220],"show":[221],"quality":[226,237],"gains":[227],"methods,":[232],"accurate":[235],"presence":[239],"large":[241],"pose":[242],"facial":[244],"expression":[245],"changes.":[246],"source":[248],"code":[249],"will":[250],"available":[252],"https://github.com/Goluck-Konuko/animation-based-codecs":[254]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2024-09-07T00:00:00"}