{"id":"https://openalex.org/W3205994442","doi":"https://doi.org/10.1145/3474085.3475196","title":"TACR-Net: Editing on Deep Video and Voice Portraits","display_name":"TACR-Net: Editing on Deep Video and Voice Portraits","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3205994442","doi":"https://doi.org/10.1145/3474085.3475196","mag":"3205994442"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/A5024413169","display_name":"Luchuan Song","orcid":"https://orcid.org/0000-0002-0126-1259"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luchuan Song","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395493","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0002-3977-8800"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033440540","display_name":"Guojun Yin","orcid":"https://orcid.org/0000-0001-8260-5449"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojun Yin","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055238399","display_name":"Xiaoyi Dong","orcid":"https://orcid.org/0000-0002-4654-835X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Dong","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324346","display_name":"Yufei Zhang","orcid":"https://orcid.org/0000-0003-1555-5888"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Zhang","raw_affiliation_strings":["Meituan, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan, Beijing, China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002781909","display_name":"Jia-Xuan Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia-Xuan Bai","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5524,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85256689,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"478","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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":0.998199999332428,"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":0.8449311852455139},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7852175235748291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6003499031066895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4898543059825897},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.4872209131717682},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4809974133968353},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33971232175827026}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449311852455139},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7852175235748291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6003499031066895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4898543059825897},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.4872209131717682},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4809974133968353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33971232175827026},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1523494361","https://openalex.org/W1676314349","https://openalex.org/W1901129140","https://openalex.org/W1922655562","https://openalex.org/W1975848997","https://openalex.org/W2015143272","https://openalex.org/W2087147962","https://openalex.org/W2127141656","https://openalex.org/W2146991130","https://openalex.org/W2237250383","https://openalex.org/W2402146185","https://openalex.org/W2467255717","https://openalex.org/W2486034530","https://openalex.org/W2526425061","https://openalex.org/W2560474170","https://openalex.org/W2562637781","https://openalex.org/W2565639579","https://openalex.org/W2726515241","https://openalex.org/W2738406145","https://openalex.org/W2782422271","https://openalex.org/W2803705807","https://openalex.org/W2806833697","https://openalex.org/W2808631503","https://openalex.org/W2942074357","https://openalex.org/W2944294033","https://openalex.org/W2949281321","https://openalex.org/W2960274051","https://openalex.org/W2963073614","https://openalex.org/W2963211739","https://openalex.org/W2964449965","https://openalex.org/W2971634123","https://openalex.org/W2979894294","https://openalex.org/W3013529009","https://openalex.org/W3015338123","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W4234389704","https://openalex.org/W4236965008","https://openalex.org/W6735927292","https://openalex.org/W6748181857"],"related_works":["https://openalex.org/W2153719181","https://openalex.org/W1971748923","https://openalex.org/W2060986072","https://openalex.org/W1566155057","https://openalex.org/W2052574922","https://openalex.org/W2065045110","https://openalex.org/W64588465","https://openalex.org/W3120641340","https://openalex.org/W2117825986","https://openalex.org/W2079855347"],"abstract_inverted_index":{"Utilizing":[0],"an":[1],"arbitrary":[2],"speech":[3,53,182],"clip":[4],"to":[5,54,84,183],"edit":[6],"the":[7,10,13,34,39,64,87,94,101,106,109,112,115,119,154,180,184],"mouth":[8],"of":[9,76,89,96,108,114],"portrait":[11,186],"in":[12,33,86,91],"target":[14,185],"video":[15,102,175],"is":[16,50,98],"a":[17,128,168,189],"novel":[18,129,169],"yet":[19],"challenging":[20],"task.":[21],"Despite":[22],"impressive":[23],"results":[24],"have":[25],"been":[26],"achieved,":[27],"there":[28,49],"are":[29,42],"still":[30],"three":[31],"limitations":[32],"existing":[35],"methods:":[36],"1)":[37],"since":[38],"acoustic":[40,156],"features":[41,56,157],"not":[43],"completely":[44],"decoupled":[45],"from":[46],"person":[47],"identity,":[48],"no":[51],"global":[52],"facial":[55,149],"(i.e.,":[57],"landmarks,":[58],"expression":[59,150],"blendshape)":[60],"mapping":[61],"method.":[62],"2)":[63],"audio-driven":[65,140],"talking":[66,142],"face":[67,143],"sequences":[68],"generated":[69],"by":[70],"simple":[71],"cascade":[72,171],"structure":[73,172],"usually":[74],"lack":[75],"temporal":[77],"consistency":[78,88],"and":[79,118,187,191],"spatial":[80],"correlation,":[81],"which":[82],"leads":[83],"defects":[85],"changes":[90],"details.":[92],"3)":[93],"operation":[95],"forgery":[97,107],"always":[99],"at":[100],"level,":[103],"without":[104,158],"considering":[105],"voice,":[110],"especially":[111],"synchronization":[113],"converted":[116],"voice":[117],"mouth.":[120],"To":[121],"address":[122],"these":[123],"distortion":[124],"problems,":[125],"we":[126,178],"propose":[127],"deep":[130],"learning":[131],"framework,":[132],"named":[133],"Temporal-Refinement":[134],"Autoregressive-Cascade":[135],"Rendering":[136],"Network":[137],"(TACR-Net)":[138],"for":[139,161,174],"dynamic":[141],"editing.":[144],"The":[145],"proposed":[146],"TACR-Net":[147,165],"encodes":[148],"blendshape":[151],"based":[152],"on":[153],"given":[155],"separately":[159],"training":[160],"special":[162],"video.":[163,193],"Then":[164],"also":[166],"involves":[167],"autoregressive":[170],"generator":[173],"re-rendering.":[176],"Finally,":[177],"transform":[179],"in-the-wild":[181],"obtain":[188],"photo-realistic":[190],"audio-realistic":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}