{"id":"https://openalex.org/W4402981307","doi":"https://doi.org/10.1109/icme57554.2024.10688257","title":"Audio-driven High-resolution Seamless Talking Head Video Editing via StyleGAN","display_name":"Audio-driven High-resolution Seamless Talking Head Video Editing via StyleGAN","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402981307","doi":"https://doi.org/10.1109/icme57554.2024.10688257"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5113206108","display_name":"Jiacheng Su","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiacheng Su","raw_affiliation_strings":["Xiamen University,School of Film,Xiamen,China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Film,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066879706","display_name":"Kunhong Liu","orcid":"https://orcid.org/0000-0002-1222-8876"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunhong Liu","raw_affiliation_strings":["Xiamen University,School of Film,Xiamen,China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Film,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100772864","display_name":"Liyan Chen","orcid":"https://orcid.org/0000-0002-5255-0296"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyan Chen","raw_affiliation_strings":["Xiamen University,School of Film,Xiamen,China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Film,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051198154","display_name":"Junfeng Yao","orcid":"https://orcid.org/0000-0002-2330-7406"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Yao","raw_affiliation_strings":["Xiamen University,School of Film,Xiamen,China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Film,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714477","display_name":"Qingsong Liu","orcid":"https://orcid.org/0000-0002-6689-6407"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingsong Liu","raw_affiliation_strings":["Xiamen Unisound Intelligence Technology Co., Ltd.,Xiamen,China"],"affiliations":[{"raw_affiliation_string":"Xiamen Unisound Intelligence Technology Co., Ltd.,Xiamen,China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068584269","display_name":"Dongdong Lv","orcid":"https://orcid.org/0009-0007-7600-4517"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Lv","raw_affiliation_strings":["Xiamen Unisound Intelligence Technology Co., Ltd.,Xiamen,China"],"affiliations":[{"raw_affiliation_string":"Xiamen Unisound Intelligence Technology Co., Ltd.,Xiamen,China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113206108"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.7873,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73523881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"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/T11439","display_name":"Video Analysis and Summarization","score":0.996399998664856,"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/T11439","display_name":"Video Analysis and Summarization","score":0.996399998664856,"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":0.9843000173568726,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9789999723434448,"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":0.7643811702728271},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5473293662071228},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.5267633199691772},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.45433858036994934},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.44680750370025635},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.39621487259864807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23209506273269653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7643811702728271},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5473293662071228},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.5267633199691772},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.45433858036994934},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.44680750370025635},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.39621487259864807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23209506273269653},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1508766232","https://openalex.org/W2133665775","https://openalex.org/W2944294033","https://openalex.org/W2949662773","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2985068832","https://openalex.org/W3014852036","https://openalex.org/W3019952993","https://openalex.org/W3035355202","https://openalex.org/W3047371217","https://openalex.org/W3081492798","https://openalex.org/W3096831136","https://openalex.org/W3099284785","https://openalex.org/W3173102319","https://openalex.org/W3174763799","https://openalex.org/W3176913662","https://openalex.org/W3178406257","https://openalex.org/W3196904463","https://openalex.org/W3197199219","https://openalex.org/W3205904637","https://openalex.org/W3206008575","https://openalex.org/W4200150166","https://openalex.org/W4200174933","https://openalex.org/W4286611278","https://openalex.org/W4310379947","https://openalex.org/W4311034013","https://openalex.org/W4312301053","https://openalex.org/W6640963894","https://openalex.org/W6765779288","https://openalex.org/W6791579284","https://openalex.org/W6798149179","https://openalex.org/W6811548253","https://openalex.org/W7028580527"],"related_works":["https://openalex.org/W3097502728","https://openalex.org/W2113206756","https://openalex.org/W2751894797","https://openalex.org/W1517180214","https://openalex.org/W2082780921","https://openalex.org/W3009949491","https://openalex.org/W1927475415","https://openalex.org/W2368355376","https://openalex.org/W2388962967","https://openalex.org/W2365286546"],"abstract_inverted_index":{"The":[0],"existing":[1],"methods":[2],"for":[3],"audio-driven":[4],"talking":[5,25],"head":[6],"video":[7,84],"editing":[8,24,70],"have":[9],"the":[10,42,53,81,87,93],"limitations":[11],"of":[12,41,86],"poor":[13],"visual":[14,111],"effects.":[15],"This":[16],"paper":[17],"tries":[18],"to":[19,79],"tackle":[20],"this":[21],"problem":[22],"through":[23],"face":[26,73],"images":[27],"seamless":[28,82],"with":[29,101,109],"different":[30],"emotions":[31],"based":[32],"on":[33],"two":[34],"modules:":[35],"(1)":[36],"an":[37,47],"audio-to-landmark":[38],"module,":[39],"consisting":[40,85],"CrossReconstructed":[43],"Emotion":[44],"Disentanglement":[45],"and":[46,57,89],"alignment":[48],"network":[49],"module.":[50],"It":[51,77],"bridges":[52],"gap":[54],"between":[55],"speech":[56],"facial":[58],"motions":[59],"by":[60],"predicting":[61],"corresponding":[62],"emotional":[63],"landmarks":[64],"from":[65,92],"speech;":[66],"(2)":[67],"a":[68],"landmark-based":[69],"module":[71],"edits":[72],"videos":[74,108],"via":[75],"StyleGAN.":[76],"aims":[78],"generate":[80],"edited":[83],"emotion":[88],"content":[90],"components":[91],"input":[94],"audio.":[95],"Extensive":[96],"experiments":[97],"confirm":[98],"that":[99],"compared":[100],"state-of-the-arts":[102],"methods,":[103],"our":[104],"method":[105],"provides":[106],"high-resolution":[107],"high":[110],"quality.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}
