{"id":"https://openalex.org/W3209629900","doi":"https://doi.org/10.1145/3459637.3482198","title":"Talking Face Generation Based on Information Bottleneck and Complementary Representations","display_name":"Talking Face Generation Based on Information Bottleneck and Complementary Representations","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3209629900","doi":"https://doi.org/10.1145/3459637.3482198","mag":"3209629900"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information &amp; Knowledge Management","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/A5011829218","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0001-8157-3270"},"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":"Jie Tang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101973798","display_name":"Yiling Wu","orcid":"https://orcid.org/0000-0002-7598-7183"},"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":"Yiling Wu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780135","display_name":"Minglei Li","orcid":"https://orcid.org/0000-0002-1427-3507"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglei Li","raw_affiliation_strings":["Huawei Cloud BU, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud BU, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100439573","display_name":"Zhu Wang","orcid":"https://orcid.org/0000-0003-3691-1407"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu Wang","raw_affiliation_strings":["Huawei Technologies Co.,Ltd., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co.,Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2864,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61612903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3443","last_page":"3447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9979000091552734,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9970999956130981,"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":0.8226704597473145},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6757704019546509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5665405988693237},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.552716076374054},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5173803567886353},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5141056180000305},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4865938425064087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47671765089035034},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.47225871682167053},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.4713912606239319},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.44602644443511963},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.41001439094543457},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.34470340609550476},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.281442254781723},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.1776600480079651},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15599501132965088}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226704597473145},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6757704019546509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5665405988693237},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.552716076374054},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5173803567886353},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5141056180000305},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4865938425064087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47671765089035034},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.47225871682167053},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.4713912606239319},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.44602644443511963},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41001439094543457},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34470340609550476},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.281442254781723},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.1776600480079651},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15599501132965088},{"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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3459637.3482198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information &amp; Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2017107803","https://openalex.org/W2105649179","https://openalex.org/W2107037917","https://openalex.org/W2560662850","https://openalex.org/W2560674852","https://openalex.org/W2613087992","https://openalex.org/W2738406145","https://openalex.org/W2796931171","https://openalex.org/W2803705807","https://openalex.org/W2944294033","https://openalex.org/W2949281321","https://openalex.org/W2951270715","https://openalex.org/W2963073614","https://openalex.org/W2963290645","https://openalex.org/W2964449965","https://openalex.org/W2999966482","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3087121792","https://openalex.org/W3101631197","https://openalex.org/W3109114891"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1996547972","https://openalex.org/W2139941521","https://openalex.org/W2363866404","https://openalex.org/W9205999","https://openalex.org/W2392717295","https://openalex.org/W2123022792","https://openalex.org/W2494591065","https://openalex.org/W4388334345","https://openalex.org/W3110605476"],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,166],"face":[2,63,130,167],"generation":[3,148,168],"is":[4,18,27,70,172],"an":[5],"active":[6],"research":[7],"direction":[8],"in":[9,92,123],"the":[10,20,25,32,56,67,73,78,89,93,98,106,116,124,141,147,155,173],"field":[11],"of":[12,24,29,149],"virtual":[13],"reality.":[14],"The":[15,128],"main":[16],"challenge":[17],"that":[19,162],"generated":[21],"lip":[22,120,176],"shape":[23],"speaker":[26],"out":[28],"sync":[30],"with":[31,97,164,178],"input":[33,51],"audio.":[34,52],"To":[35],"address":[36],"this":[37],"challenge,":[38],"we":[39,87,109],"propose":[40],"a":[41],"novel":[42],"solution":[43],"to":[44,76],"synthesize":[45],"lip-synchronized,":[46],"high-quality,":[47],"realistic":[48],"video":[49,59,95,152,180],"given":[50],"We":[53],"first":[54],"decompose":[55],"target":[57,94],"person's":[58],"frames":[60],"into":[61,72],"3D":[62,129],"model":[64],"parameters,":[65],"and":[66,83,104,119,134],"information":[68,139],"bottleneck":[69],"inserted":[71],"audio-to-expression":[74],"network":[75,144],"learn":[77],"mapping":[79],"between":[80],"audio":[81,103,112,118,135],"features":[82],"expression":[84,90,100],"parameters.":[85],"Then,":[86],"replace":[88],"parameters":[91,101],"frame":[96],"extracted":[99,114],"from":[102,115,154],"re-render":[105],"face.":[107],"Finally,":[108],"add":[110],"high-level":[111],"embedding":[113,122,136],"raw":[117],"landmarks":[121],"neural":[125,142],"rendering":[126,143],"network.":[127],"shapes,":[131],"2D":[132],"landmarks,":[133],"provide":[137],"complementary":[138],"for":[140],"which":[145],"guarantees":[146],"lip-synchronized":[150],"high-quality":[151],"portraits":[153],"synthesized":[156],"rendered":[157],"faces.":[158],"Experimental":[159],"results":[160],"show":[161],"compared":[163],"other":[165],"methods,":[169],"our":[170],"method":[171],"best":[174],"concerning":[175],"synchronization":[177],"high":[179],"definition.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
