{"id":"https://openalex.org/W7123360334","doi":"https://doi.org/10.1109/tip.2025.3648562","title":"CoFaCo: Controllable Generative Talking Face Video Coding","display_name":"CoFaCo: Controllable Generative Talking Face Video Coding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123360334","doi":"https://doi.org/10.1109/tip.2025.3648562","pmid":"https://pubmed.ncbi.nlm.nih.gov/41525637"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3648562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3648562","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaona Li","orcid":"https://orcid.org/0000-0001-5027-5836"},"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":"Xiaona Li","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-5027-5836","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017703152","display_name":"Xihua Sheng","orcid":"https://orcid.org/0000-0001-7350-4929"},"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":"Xihua Sheng","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122875813","display_name":"Meng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["School of Data Sciences, Lingnan University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Sciences, Lingnan University, Hong Kong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023617834","display_name":"Fu-Zhao Ou","orcid":"https://orcid.org/0000-0003-1245-8345"},"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":"Fu-Zhao Ou","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-1245-8345","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748649","display_name":"Bolin Chen","orcid":"https://orcid.org/0009-0009-7076-4739"},"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":"Bolin Chen","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0009-7076-4739","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122858020","display_name":"Shiqi Wang","orcid":null},"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":["Department of Computer Science, City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3583-959X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105624356","display_name":"Sam Kwong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Kwong","raw_affiliation_strings":["School of Data Sciences, Lingnan University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7484-7261","affiliations":[{"raw_affiliation_string":"School of Data Sciences, Lingnan University, Hong Kong, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.05372849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"465","last_page":"479"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8256999850273132,"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/T11448","display_name":"Face recognition and analysis","score":0.8256999850273132,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07360000163316727,"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/T10860","display_name":"Speech and Audio Processing","score":0.020899999886751175,"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/coding","display_name":"Coding (social sciences)","score":0.6078000068664551},{"id":"https://openalex.org/keywords/multiview-video-coding","display_name":"Multiview Video Coding","score":0.5327000021934509},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4966000020503998},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.4952000081539154},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4903999865055084},{"id":"https://openalex.org/keywords/coding-tree-unit","display_name":"Coding tree unit","score":0.4260999858379364},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4101000130176544},{"id":"https://openalex.org/keywords/compression-artifact","display_name":"Compression artifact","score":0.3865000009536743},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.3504999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804999947547913},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6078000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5590999722480774},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5447999835014343},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.5327000021934509},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.4952000081539154},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C190750250","wikidata":"https://www.wikidata.org/wiki/Q13533439","display_name":"Coding tree unit","level":3,"score":0.4260999858379364},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4101000130176544},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.3865000009536743},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.35019999742507935},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C175732694","wikidata":"https://www.wikidata.org/wiki/Q1128713","display_name":"Context-adaptive binary arithmetic coding","level":3,"score":0.33980000019073486},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C133529210","wikidata":"https://www.wikidata.org/wiki/Q1076113","display_name":"Scalable Video Coding","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C97501218","wikidata":"https://www.wikidata.org/wiki/Q219763","display_name":"MPEG-4","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C76862118","wikidata":"https://www.wikidata.org/wiki/Q1105671","display_name":"Coding gain","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C116709606","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Algorithmic efficiency","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2025.3648562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3648562","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41525637","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41525637","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1142168939","display_name":null,"funder_award_id":"GHP/044/21SZ","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3763968737","display_name":null,"funder_award_id":"13200425","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4919694410","display_name":null,"funder_award_id":"PRP/036/24FX","funder_id":"https://openalex.org/F4320324196","funder_display_name":"Innovation and Technology Commission - Hong Kong"},{"id":"https://openalex.org/G5849505163","display_name":null,"funder_award_id":"PRP/036/24FX","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G793240811","display_name":null,"funder_award_id":"GHP/044/21SZ","funder_id":"https://openalex.org/F4320324196","funder_display_name":"Innovation and Technology Commission - Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324196","display_name":"Innovation and Technology Commission - Hong Kong","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1974042972","https://openalex.org/W2081280191","https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2161628678","https://openalex.org/W2169169193","https://openalex.org/W2555231364","https://openalex.org/W2726515241","https://openalex.org/W2807126412","https://openalex.org/W2898275197","https://openalex.org/W2949662773","https://openalex.org/W2950689937","https://openalex.org/W2962785568","https://openalex.org/W2963092440","https://openalex.org/W2969260367","https://openalex.org/W3017136408","https://openalex.org/W3026802938","https://openalex.org/W3035169015","https://openalex.org/W3081192838","https://openalex.org/W3081492798","https://openalex.org/W3099284785","https://openalex.org/W3119221111","https://openalex.org/W3123221586","https://openalex.org/W3152624359","https://openalex.org/W3160069937","https://openalex.org/W3173272744","https://openalex.org/W3176032345","https://openalex.org/W3176913662","https://openalex.org/W3180770160","https://openalex.org/W3180794345","https://openalex.org/W3202918664","https://openalex.org/W3205358019","https://openalex.org/W3216942228","https://openalex.org/W4200414709","https://openalex.org/W4200517036","https://openalex.org/W4206355076","https://openalex.org/W4225701435","https://openalex.org/W4225769600","https://openalex.org/W4281913152","https://openalex.org/W4283818044","https://openalex.org/W4283819141","https://openalex.org/W4304014863","https://openalex.org/W4311415873","https://openalex.org/W4312095800","https://openalex.org/W4312238466","https://openalex.org/W4312590328","https://openalex.org/W4313423374","https://openalex.org/W4320502137","https://openalex.org/W4321021409","https://openalex.org/W4321608032","https://openalex.org/W4367276751","https://openalex.org/W4381716448","https://openalex.org/W4385490328","https://openalex.org/W4386075576","https://openalex.org/W4386363058","https://openalex.org/W4388519998","https://openalex.org/W4388624308","https://openalex.org/W4389880093","https://openalex.org/W4391974577","https://openalex.org/W4394597809","https://openalex.org/W4394951229","https://openalex.org/W4399031050","https://openalex.org/W4402716273","https://openalex.org/W4402789411","https://openalex.org/W4407690730","https://openalex.org/W4415799309"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"talking":[1,86],"face":[2,87,135,200],"video":[3,11,55,172,190,201],"coding":[4,56,81],"and":[5,18,35,91,109,123,132,141,154,192],"control":[6,27,52,78,143,193,205],"are":[7,137,162],"crucial":[8],"in":[9,38,169,186],"modern":[10],"communication,":[12],"reshaping":[13],"how":[14],"individuals":[15],"connect,":[16],"collaborate,":[17],"interact.":[19],"Coding":[20,72],"seeks":[21],"to":[22,118,149,165],"reduce":[23],"transmission":[24],"costs,":[25],"while":[26],"enables":[28],"the":[29,39,43,47,80,121,128,133,139,170,175],"realization":[30],"of":[31,46,50,107,115],"user-customizable":[32],"facial":[33],"expressions":[34],"head":[36],"poses":[37],"transmitted":[40],"videos.":[41],"However,":[42],"compression":[44,184],"efficiency":[45,185],"common":[48],"par-adigm":[49],"applying":[51],"algorithms":[53],"before":[54,101],"is":[57],"not":[58],"satisfactory.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,111],"propose":[64],"an":[65],"efficient,":[66],"Controllable":[67],"Generative":[68],"Talking":[69],"Face":[70],"Video":[71],"(CoFaCo)":[73],"framework,":[74],"wh-ich":[75],"seamlessly":[76],"integrates":[77],"into":[79,89],"process.":[82],"Specific-ally,":[83],"CoFaCo":[84,181],"projects":[85],"videos":[88],"ultra-compact":[90],"semantic":[92,134],"feature":[93],"representations":[94,136],"that":[95,180],"can":[96,145],"be":[97,146],"customized":[98],"by":[99,174],"users":[100],"compression.":[102],"To":[103],"enable":[104],"independent":[105],"controls":[106],"pose":[108,122,140,153],"expression,":[110],"design":[112],"a":[113],"set":[114],"sophisticated":[116],"losses":[117],"accurately":[119],"de-couple":[120],"expression":[124,142,155],"direction":[125,130,156,160],"codes.":[126,157],"Once":[127],"decoupled":[129],"codes":[131,161],"obtained,":[138],"modules":[144],"effectively":[147],"learned":[148],"generate":[150],"decoupled,":[151],"controlled":[152,159,171],"The":[158],"subsequently":[163],"smoothed":[164],"enhance":[166],"temporal":[167],"consistency":[168],"output":[173],"generators.":[176],"Experimental":[177],"results":[178],"demonstrate":[179],"achieves":[182],"competitive":[183],"ultra-low":[187],"bit":[188],"rate":[189],"reconstruction":[191],"tasks,":[194],"providing":[195],"valuab-le":[196],"insights":[197],"for":[198],"advancing":[199],"communication":[202],"with":[203],"diverse":[204],"capabilities.":[206]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-14T00:00:00"}
