{"id":"https://openalex.org/W4206020382","doi":"https://doi.org/10.1145/3503047.3503054","title":"Few-shot Adversarial Audio Driving Talking Face Generation","display_name":"Few-shot Adversarial Audio Driving Talking Face Generation","publication_year":2021,"publication_date":"2021-11-26","ids":{"openalex":"https://openalex.org/W4206020382","doi":"https://doi.org/10.1145/3503047.3503054"},"language":"en","primary_location":{"id":"doi:10.1145/3503047.3503054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503047.3503054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","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/A5102820512","display_name":"Ruyi Chen","orcid":"https://orcid.org/0000-0002-8657-267X"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruyi Chen","raw_affiliation_strings":["Wuhan University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011707621","display_name":"Shengwu Xiong","orcid":"https://orcid.org/0000-0002-4006-7029"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwu Xiong","raw_affiliation_strings":["Wuhan University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology, China","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18602403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/T11448","display_name":"Face recognition and analysis","score":0.9990000128746033,"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":0.8594350814819336},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6705025434494019},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6604083180427551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.611671507358551},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5907976627349854},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5417912006378174},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5131352543830872},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48019134998321533},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4497605562210083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3437693119049072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8594350814819336},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6705025434494019},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6604083180427551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.611671507358551},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5907976627349854},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5417912006378174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5131352543830872},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48019134998321533},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4497605562210083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3437693119049072},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503047.3503054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503047.3503054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Advanced Information Science and System","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":13,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2133665775","https://openalex.org/W2738406145","https://openalex.org/W2808631503","https://openalex.org/W2914217321","https://openalex.org/W2944294033","https://openalex.org/W2963290645","https://openalex.org/W2963654155","https://openalex.org/W2990452356","https://openalex.org/W3034211329","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3186090335"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W2355833770","https://openalex.org/W3126451824","https://openalex.org/W3031039437"],"abstract_inverted_index":{"Talking-face":[0],"generation":[1],"is":[2],"an":[3],"interesting":[4],"and":[5,11,29,57,111,123,158,167,188],"challenging":[6],"problem":[7],"in":[8,49,185],"computer":[9],"vision":[10],"has":[12],"become":[13],"a":[14,36,66,78,91,119],"research":[15],"focus.":[16],"This":[17],"project":[18],"aims":[19],"to":[20,34,62,105,126],"generate":[21,159],"real":[22],"talking-face":[23,38,84],"video":[24,94],"sequences,":[25,152],"especially":[26],"lip":[27,68],"synchronization":[28,59,69,81],"head":[30],"motion.":[31],"In":[32,71],"order":[33],"create":[35],"personalized":[37,54,129],"model,":[39],"these":[40],"works":[41],"require":[42],"training":[43],"on":[44,117,134,149,170],"large-scale":[45],"audio-visual":[46],"datasets.":[47],"However,":[48],"many":[50],"practical":[51],"scenarios,":[52],"the":[53,97,102,107,128,135,137,141,150,153,182],"appearance":[55],"features,":[56],"audio-video":[58],"relationships":[60],"need":[61],"be":[63,115],"learned":[64],"from":[65],"few":[67,92,120,146],"sequences.":[70],"this":[72,112],"paper,":[73],"we":[74],"consider":[75],"it":[76],"as":[77,96],"few-shot":[79],"image":[80],"problem:":[82],"synthesizing":[83],"with":[85,145,163],"audio":[86],"if":[87],"there":[88],"are":[89],"additionally":[90],"lip-synchronized":[93],"sequences":[95,122],"learning":[98],"task?":[99],"We":[100],"apply":[101],"reptile":[103],"methods":[104,180,184],"train":[106],"meta":[108],"adversarial":[109],"networks":[110],"meta-model":[113],"could":[114],"adapted":[116],"just":[118],"references":[121,130],"done":[124],"quickly":[125,157],"learn":[127,140,156],"models.":[131],"With":[132],"meta-learning":[133],"dataset,":[136],"model":[138,154],"can":[139,155],"initialization":[142],"parameters.":[143],"And":[144],"adapt":[147],"steps":[148],"reference":[151],"highly":[160],"realistic":[161],"images":[162],"more":[164],"facial":[165],"texture":[166],"lip-sync.":[168],"Experiments":[169],"several":[171],"datasets":[172],"demonstrated":[173],"significantly":[174],"better":[175],"results":[176],"obtained":[177],"by":[178],"our":[179],"than":[181],"state-of-the-art":[183],"both":[186],"quantitative":[187,189],"comparisons.":[190]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
