{"id":"https://openalex.org/W4312357426","doi":"https://doi.org/10.1109/mmsp55362.2022.9949293","title":"A Keypoint Based Enhancement Method for Audio Driven Free View Talking Head Synthesis","display_name":"A Keypoint Based Enhancement Method for Audio Driven Free View Talking Head Synthesis","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4312357426","doi":"https://doi.org/10.1109/mmsp55362.2022.9949293"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp55362.2022.9949293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949293","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},"type":"article","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/A5031705836","display_name":"Yichen Han","orcid":"https://orcid.org/0009-0008-7018-8949"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Han","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,Beijing,China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,Beijing,China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079377968","display_name":"Yingming Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingming Gao","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,Beijing,China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033565985","display_name":"Jinlong Xue","orcid":"https://orcid.org/0009-0000-0442-0932"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Xue","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications,Beijing,China","School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037901154","display_name":"Songpo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143697","display_name":"Center for High Pressure Science & Technology Advanced Research","ror":"https://ror.org/0443s9p82","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210143697"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songpo Wang","raw_affiliation_strings":["DeepScience Tech Ltd.,Beijing,China","DeepScience Tech Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepScience Tech Ltd.,Beijing,China","institution_ids":["https://openalex.org/I4210143697"]},{"raw_affiliation_string":"DeepScience Tech Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039043845","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-2523-671X"},"institutions":[{"id":"https://openalex.org/I4210143697","display_name":"Center for High Pressure Science & Technology Advanced Research","ror":"https://ror.org/0443s9p82","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210143697"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["DeepScience Tech Ltd.,Beijing,China","DeepScience Tech Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepScience Tech Ltd.,Beijing,China","institution_ids":["https://openalex.org/I4210143697"]},{"raw_affiliation_string":"DeepScience Tech Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.403,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81676394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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/T12290","display_name":"Human Motion and Animation","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9965999722480774,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9955999851226807,"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":0.8052234053611755},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7725891470909119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7075068950653076},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6436572074890137},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6281249523162842},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5747777819633484},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.538937509059906},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.49058809876441956},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4158129096031189},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32336363196372986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1011556088924408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052234053611755},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7725891470909119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7075068950653076},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6436572074890137},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6281249523162842},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5747777819633484},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.538937509059906},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.49058809876441956},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4158129096031189},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32336363196372986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1011556088924408},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp55362.2022.9949293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949293","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6685334198","display_name":null,"funder_award_id":"202200042","funder_id":"https://openalex.org/F4320326873","funder_display_name":"National Laboratory of Pattern Recognition"},{"id":"https://openalex.org/G7257301138","display_name":null,"funder_award_id":"2021RC37","funder_id":"https://openalex.org/F4320321470","funder_display_name":"Beijing University of Posts and Telecommunications"}],"funders":[{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320326873","display_name":"National Laboratory of Pattern Recognition","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2077521262","https://openalex.org/W2133665775","https://openalex.org/W2468212864","https://openalex.org/W2726515241","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2745771616","https://openalex.org/W2804619907","https://openalex.org/W2914217321","https://openalex.org/W2944294033","https://openalex.org/W2971278627","https://openalex.org/W3008823916","https://openalex.org/W3019952993","https://openalex.org/W3034211329","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3095664976","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3109585842","https://openalex.org/W3120163087","https://openalex.org/W3174763799","https://openalex.org/W3180770160","https://openalex.org/W3186090335","https://openalex.org/W3211147706","https://openalex.org/W4200174933","https://openalex.org/W4210657261","https://openalex.org/W6763480078","https://openalex.org/W6767264202","https://openalex.org/W6777209069"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W4387098302","https://openalex.org/W2626699140","https://openalex.org/W3165080709","https://openalex.org/W2948317131","https://openalex.org/W4288365855","https://openalex.org/W2111961547"],"abstract_inverted_index":{"Audio":[0],"driven":[1,78],"talking":[2,81],"head":[3,34,82],"synthesis":[4,83,112],"is":[5,61,74],"a":[6],"challenging":[7],"task":[8],"that":[9,174],"attracts":[10],"increasing":[11],"attention":[12],"in":[13,48,162,185],"recent":[14],"years.":[15],"Although":[16],"existing":[17,93],"methods":[18,94],"based":[19,141],"on":[20],"2D":[21],"landmarks":[22],"or":[23],"3D":[24],"face":[25],"models":[26],"can":[27],"synthesize":[28,101],"accurate":[29],"lip":[30],"synchronization":[31],"and":[32,52,119,134,166],"rhythmic":[33],"pose":[35],"for":[36,76],"arbitrary":[37],"identity,":[38],"they":[39],"still":[40],"have":[41],"limitations,":[42],"such":[43],"as":[44,97],"the":[45,49,53,65,86,89,98,116,120,125,131,135,147,151,159,163,167,180],"cut":[46,160],"feeling":[47,161],"mouth":[50,164],"mapping":[51,165],"lack":[54,168],"of":[55,88,169,182,187],"skin":[56,170],"highlights.":[57,171],"The":[58],"morphed":[59],"region":[60],"blurry":[62],"compared":[63],"to":[64,84,100,109,130,145],"surrounding":[66],"face.":[67],"A":[68,138],"Keypoint":[69],"Based":[70],"Enhancement":[71],"(KPBE)":[72],"method":[73,142,178],"proposed":[75,176],"audio":[77],"free":[79],"view":[80],"improve":[85],"naturalness":[87],"generated":[90],"video.":[91],"Firstly,":[92],"were":[95,128],"used":[96,106,144],"backend":[99,117],"intermediate":[102],"results.":[103],"Then":[104],"we":[105,157],"keypoint":[107,152,155],"decomposition":[108],"extract":[110],"video":[111],"controlling":[113,126],"parameters":[114,127],"from":[115,150],"output":[118],"source":[121,132],"image.":[122],"After":[123],"that,":[124],"composited":[129],"keypoints":[133],"driving":[136],"keypoints.":[137],"motion":[139],"field":[140],"was":[143],"generate":[146],"final":[148],"image":[149],"representation.":[153],"With":[154],"representation,":[156],"overcame":[158],"Experiments":[172],"show":[173],"our":[175],"enhancement":[177],"improved":[179],"quality":[181],"talking-head":[183],"videos":[184],"terms":[186],"mean":[188],"opinion":[189],"score.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}