{"id":"https://openalex.org/W4408352382","doi":"https://doi.org/10.1109/icassp49660.2025.10887606","title":"One-Shot Talking Face Generation with Expression Editing","display_name":"One-Shot Talking Face Generation with Expression Editing","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352382","doi":"https://doi.org/10.1109/icassp49660.2025.10887606"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5047484519","display_name":"Ganyu Huang","orcid":"https://orcid.org/0000-0001-8636-3221"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ganyu Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,X-Lance Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-Lance Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102871645","display_name":"Liping Shen","orcid":"https://orcid.org/0009-0001-2688-1868"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Shen","raw_affiliation_strings":["Shanghai Jiao Tong University,X-Lance Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,X-Lance Lab,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047484519"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04130257,"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":"5"},"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/T10828","display_name":"Biometric Identification and Security","score":0.9703999757766724,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.9592000246047974,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.697273850440979},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6310544610023499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6189043521881104},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5363045930862427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36873704195022583},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11018425226211548},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0885651707649231},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05641239881515503}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.697273850440979},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6310544610023499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6189043521881104},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5363045930862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36873704195022583},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11018425226211548},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0885651707649231},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05641239881515503},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":33,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2162220380","https://openalex.org/W2604379605","https://openalex.org/W2944294033","https://openalex.org/W3010526057","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3099284785","https://openalex.org/W3174763799","https://openalex.org/W3186090335","https://openalex.org/W3209059054","https://openalex.org/W4200631136","https://openalex.org/W4312444931","https://openalex.org/W4312933868","https://openalex.org/W4317496742","https://openalex.org/W4375868939","https://openalex.org/W4375869257","https://openalex.org/W4386065999","https://openalex.org/W4386066256","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4386075576","https://openalex.org/W4386076090","https://openalex.org/W4390872742","https://openalex.org/W4390873054","https://openalex.org/W4402754201","https://openalex.org/W4404199654","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6794269193","https://openalex.org/W6859110512","https://openalex.org/W6859319753"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574"],"abstract_inverted_index":{"The":[0],"task":[1],"of":[2,88],"talking":[3],"face":[4,23],"generation":[5,61],"has":[6],"advanced":[7],"significantly":[8],"with":[9,67],"deep":[10],"learning,":[11],"enhancing":[12],"applications":[13],"from":[14],"virtual":[15],"assistants":[16],"to":[17,45,58],"animated":[18],"movies.":[19],"However,":[20],"current":[21],"algorithms":[22],"challenges":[24],"in":[25],"controlling":[26],"facial":[27,49,64,76,89],"expressions":[28,50],"and":[29,37,51,62,83,97],"avoiding":[30],"unnatural,":[31],"rigid":[32],"movements,":[33],"limiting":[34],"their":[35],"realism":[36],"effectiveness.":[38],"Our":[39,91],"work":[40],"introduces":[41],"a":[42],"novel":[43],"approach":[44],"improve":[46],"control":[47,96],"over":[48],"overall":[52],"fluidity.":[53],"We":[54],"use":[55],"emotion":[56],"labels":[57],"guide":[59],"audio":[60],"corresponding":[63],"landmarks,":[65],"combined":[66],"ControlNet":[68],"for":[69],"smooth":[70],"transitions.":[71],"This":[72],"method":[73],"ensures":[74],"synchronized":[75],"landmarks":[77],"that":[78],"reflect":[79],"desired":[80],"emotional":[81,95],"states":[82],"enhances":[84],"the":[85],"natural":[86],"flow":[87],"movements.":[90],"experiments":[92],"demonstrate":[93],"precise":[94],"high-quality":[98],"visual":[99],"outputs.":[100]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
