{"id":"https://openalex.org/W4403791312","doi":"https://doi.org/10.1145/3664647.3681108","title":"SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing","display_name":"SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editing","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791312","doi":"https://doi.org/10.1145/3664647.3681108"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5001102230","display_name":"Lingyu Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Xiong","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-9453-5423","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9708-3225","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jintao Tan","orcid":"https://orcid.org/0009-0000-7777-2162"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jintao Tan","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-7777-2162","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114236922","display_name":"Xianjia Wu","orcid":null},"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":"Xianjia Wu","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-8742-5339","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111346914","display_name":"Xiandong Li","orcid":null},"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":"Xiandong Li","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-7724-3966","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Zhu","orcid":"https://orcid.org/0009-0004-4795-9670"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["Peking University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-4795-9670","affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"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/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 Computing Technologies Co., Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1427-3507","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huang Xu","orcid":"https://orcid.org/0009-0001-5405-5467"},"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":"Huang Xu","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-5405-5467","affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101661353","display_name":"Zhihui Hu","orcid":"https://orcid.org/0000-0003-3336-1817"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihui Hu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3336-1817","affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7498,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86299084,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3170","last_page":"3179"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9970999956130981,"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"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9661999940872192,"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":0.7235506772994995},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6840449571609497},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5553054809570312},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5303099155426025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4844363033771515},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.4194602966308594},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33986037969589233},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10147067904472351}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235506772994995},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6840449571609497},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5553054809570312},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5303099155426025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4844363033771515},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.4194602966308594},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33986037969589233},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10147067904472351},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681108","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":48,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W2133665775","https://openalex.org/W2187089797","https://openalex.org/W2525579820","https://openalex.org/W2565639579","https://openalex.org/W2738406145","https://openalex.org/W2886934227","https://openalex.org/W2914911817","https://openalex.org/W2962785568","https://openalex.org/W2963081548","https://openalex.org/W2985068832","https://openalex.org/W3019952993","https://openalex.org/W3034431451","https://openalex.org/W3035355202","https://openalex.org/W3035574324","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3159279967","https://openalex.org/W3173241699","https://openalex.org/W3175035459","https://openalex.org/W3176913662","https://openalex.org/W3178406257","https://openalex.org/W3180770160","https://openalex.org/W3197199219","https://openalex.org/W3201739204","https://openalex.org/W3201878193","https://openalex.org/W3211147706","https://openalex.org/W3217427959","https://openalex.org/W4210657261","https://openalex.org/W4297793551","https://openalex.org/W4310379947","https://openalex.org/W4310443798","https://openalex.org/W4312933868","https://openalex.org/W4312990833","https://openalex.org/W4378513185","https://openalex.org/W4382202818","https://openalex.org/W4386065999","https://openalex.org/W4386066256","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4386076699","https://openalex.org/W4387968213","https://openalex.org/W4390871703","https://openalex.org/W4390871723","https://openalex.org/W4390873467","https://openalex.org/W4393154048","https://openalex.org/W4402670354"],"related_works":["https://openalex.org/W4311681673","https://openalex.org/W3217114251","https://openalex.org/W4296973694","https://openalex.org/W4313154074","https://openalex.org/W4321766409","https://openalex.org/W4387969181","https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W4388660740","https://openalex.org/W2797823148"],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,75,97,161],"face":[2,19,162],"generation":[3],"aims":[4],"to":[5,12,40,69,106],"synthesize":[6,107],"video":[7,108,179],"with":[8],"lip":[9,42,184],"movements":[10,43],"synchronized":[11],"input":[13],"audio.":[14],"However,":[15],"current":[16],"generative":[17],"techniques":[18],"challenges":[20],"in":[21,183],"preserving":[22],"intricate":[23],"regional":[24],"textures":[25,46,115,143],"(skin,":[26],"teeth).":[27],"To":[28],"address":[29],"the":[30,55,67,71,94,137,141,191,197],"aforementioned":[31],"challenges,":[32],"we":[33,64,78,92],"propose":[34],"a":[35,61,88,103,145],"novel":[36],"framework":[37],"called":[38],"SegTalker":[39],"decouple":[41],"and":[44,73,99,127,139,175,187,193],"image":[45,58,83,148],"by":[47,60,135],"introducing":[48],"segmentation":[49,98],"as":[50],"intermediate":[51],"representation.":[52],"Specifically,":[53],"given":[54,146],"mask":[56,72,138],"of":[57,82,114,200],"employed":[59],"parsing":[62],"network,":[63],"first":[65],"leverage":[66],"speech":[68],"drive":[70],"generate":[74,176],"segmentation.":[76],"Then":[77],"disentangle":[79],"semantic":[80],"regions":[81],"into":[84,102],"style":[85,100],"codes":[86,101],"using":[87],"mask-guided":[89,104,129],"encoder.":[90],"Ultimately,":[91],"inject":[93],"previously":[95],"generated":[96],"StyleGAN":[105],"frame.":[109],"In":[110,133],"this":[111],"way,":[112],"most":[113],"are":[116],"fully":[117],"preserved.":[118],"Moreover,":[119],"our":[120,153,167,201],"approach":[121,154,169],"can":[122,170],"inherently":[123],"achieve":[124],"background":[125],"separation":[126],"facilitate":[128],"facial":[130,156],"local":[131],"editing.":[132],"particular,":[134],"editing":[136,157],"swapping":[140],"region":[142],"from":[144],"reference":[147],"(e.g.":[149],"hair,":[150],"lip,":[151],"eyebrows),":[152],"enables":[155],"seamlessly":[158],"when":[159],"generating":[160],"video.":[163],"Experiments":[164],"demonstrate":[165],"that":[166],"proposed":[168],"effectively":[171],"preserve":[172],"texture":[173],"details":[174],"temporally":[177],"consistent":[178],"while":[180],"remaining":[181],"competitive":[182],"synchronization.":[185],"Quantitative":[186],"qualitative":[188],"results":[189],"on":[190],"HDTF":[192],"MEAD":[194],"datasets":[195],"illustrate":[196],"superior":[198],"performance":[199],"method":[202],"over":[203],"existing":[204],"methods.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
