{"id":"https://openalex.org/W4411635465","doi":"https://doi.org/10.1145/3731715.3733279","title":"Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning","display_name":"Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635465","doi":"https://doi.org/10.1145/3731715.3733279"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5056844117","display_name":"Yifan Xie","orcid":"https://orcid.org/0009-0002-3225-9220"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Xie","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-3225-9220","affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031311274","display_name":"Fei Ma","orcid":"https://orcid.org/0009-0002-5388-9125"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Ma","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-5388-9125","affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Bin","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9714-8738","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693517","display_name":"Ying He","orcid":"https://orcid.org/0000-0003-1733-9791"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying He","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1733-9791","affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420016","display_name":"F. Richard Yu","orcid":"https://orcid.org/0000-0003-1006-7594"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yu","raw_affiliation_strings":["Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1006-7594","affiliations":[{"raw_affiliation_string":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1588","last_page":"1597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9954000115394592,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9952999949455261,"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":0.7536845207214355},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6944291591644287},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.592024564743042},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4713458716869354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42957496643066406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3686436414718628},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3603951930999756},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09060493111610413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536845207214355},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6944291591644287},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.592024564743042},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4713458716869354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42957496643066406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3686436414718628},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3603951930999756},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09060493111610413},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733279","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/W2593414223","https://openalex.org/W2604379605","https://openalex.org/W2612690371","https://openalex.org/W2887922452","https://openalex.org/W2962785568","https://openalex.org/W3034475171","https://openalex.org/W3036167779","https://openalex.org/W3081492798","https://openalex.org/W3099284785","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3174763799","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4281730245","https://openalex.org/W4295916009","https://openalex.org/W4310379947","https://openalex.org/W4313423374","https://openalex.org/W4382240211","https://openalex.org/W4385490328","https://openalex.org/W4386065999","https://openalex.org/W4386066256","https://openalex.org/W4386075487","https://openalex.org/W4386075810","https://openalex.org/W4387074661","https://openalex.org/W4390872116","https://openalex.org/W4402726971","https://openalex.org/W4402727084","https://openalex.org/W4403780774","https://openalex.org/W4403792529","https://openalex.org/W4409366558","https://openalex.org/W6779823529","https://openalex.org/W6811037538","https://openalex.org/W6816251297"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W4396737233","https://openalex.org/W2367747139","https://openalex.org/W4391102217","https://openalex.org/W2566187525","https://openalex.org/W2566334511","https://openalex.org/W4410655552","https://openalex.org/W2367150592"],"abstract_inverted_index":{"Talking":[0],"face":[1,77,196],"video":[2,78,197],"generation":[3,198],"with":[4,148],"arbitrary":[5],"speech":[6],"audio":[7],"is":[8,87,133],"a":[9,68,82,153,159],"significant":[10],"challenge":[11],"within":[12],"the":[13,24,39,64,103,111,118,121,125,130,137,145,149,164,172],"realm":[14],"of":[15,26,41,84,139,176],"digital":[16],"human":[17],"technology.":[18],"The":[19,114],"previous":[20,201],"studies":[21],"have":[22],"emphasized":[23],"significance":[25],"audio-lip":[27,192],"synchronization":[28,193],"and":[29,55,106,124,170,174,191],"visual":[30,42,53,91],"quality.":[31],"Currently,":[32],"limited":[33],"attention":[34],"has":[35],"been":[36],"given":[37],"to":[38,90,100,135,143,162,200],"learning":[40],"uncertainty,":[43,171],"which":[44,80],"creates":[45],"several":[46],"issues":[47],"in":[48,194],"existing":[49],"systems,":[50],"including":[51],"inconsistent":[52],"quality":[54],"unreliable":[56],"performance":[57,173],"across":[58],"different":[59],"input":[60],"conditions.":[61],"To":[62],"address":[63],"problem,":[65],"we":[66,94,157],"propose":[67],"Joint":[69],"Uncertainty":[70],"Learning":[71],"Network":[72],"(JULNet)":[73],"for":[74],"high-quality":[75],"talking":[76,195],"generation,":[79],"incorporates":[81],"representation":[83],"uncertainty":[85,98,107,131,146],"that":[86,185],"directly":[88],"related":[89],"error.":[92],"Specifically,":[93],"first":[95],"design":[96],"an":[97],"module":[99],"individually":[101],"predict":[102,136],"error":[104,115,150,169],"map":[105,108,116,132],"after":[109],"obtaining":[110],"generated":[112,122],"image.":[113],"represents":[117],"difference":[119],"between":[120],"image":[123],"ground":[126],"truth":[127],"image,":[128],"while":[129],"used":[134],"probability":[138],"incorrect":[140],"estimates.":[141],"Furthermore,":[142],"match":[144],"distribution":[147,151],"through":[152],"KL":[154],"divergence":[155],"term,":[156],"introduce":[158],"histogram":[160],"technique":[161],"approximate":[163],"distributions.":[165],"By":[166],"jointly":[167],"optimizing":[168],"robustness":[175],"our":[177,186],"model":[178],"can":[179],"be":[180],"enhanced.":[181],"Extensive":[182],"experiments":[183],"demonstrate":[184],"method":[187],"achieves":[188],"superior":[189],"high-fidelity":[190],"compared":[199],"methods.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}