{"id":"https://openalex.org/W4372260045","doi":"https://doi.org/10.1109/icassp49357.2023.10095745","title":"Free-View Expressive Talking Head Video Editing","display_name":"Free-View Expressive Talking Head Video Editing","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260045","doi":"https://doi.org/10.1109/icassp49357.2023.10095745"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095745","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5043191940","display_name":"Yuantian Huang","orcid":"https://orcid.org/0000-0001-9775-7840"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuantian Huang","raw_affiliation_strings":["University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102829652","display_name":"Satoshi Iizuka","orcid":"https://orcid.org/0000-0001-9136-8297"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Iizuka","raw_affiliation_strings":["University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101567870","display_name":"Kazuhiro Fukui","orcid":"https://orcid.org/0000-0002-4201-1096"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Fukui","raw_affiliation_strings":["University of Tsukuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"10","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":0.9991000294685364,"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":0.9991000294685364,"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":0.9987000226974487,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9980000257492065,"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":0.8663831949234009},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6464695930480957},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6078886985778809},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5788048505783081},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5703224539756775},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5491450428962708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5243803858757019},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5184202194213867},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4252399504184723},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.41385534405708313},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4117348790168762},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3660420775413513},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34545236825942993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8663831949234009},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6464695930480957},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6078886985778809},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5788048505783081},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5703224539756775},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5491450428962708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5243803858757019},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5184202194213867},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4252399504184723},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.41385534405708313},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4117348790168762},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3660420775413513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34545236825942993},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"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:10.1109/icassp49357.2023.10095745","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7099999785423279,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2115252128","https://openalex.org/W2133665775","https://openalex.org/W2301937176","https://openalex.org/W2594690981","https://openalex.org/W2738406145","https://openalex.org/W2808631503","https://openalex.org/W2914217321","https://openalex.org/W2950689937","https://openalex.org/W2955058313","https://openalex.org/W2960274051","https://openalex.org/W2963081548","https://openalex.org/W2963644257","https://openalex.org/W2981767644","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3105763085","https://openalex.org/W3161346624","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200174933","https://openalex.org/W4281730245","https://openalex.org/W4312444931","https://openalex.org/W6677618333","https://openalex.org/W6838910027"],"related_works":["https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W4381885966","https://openalex.org/W2969399009","https://openalex.org/W4398186750","https://openalex.org/W3151498616"],"abstract_inverted_index":{"We":[0,106,120],"present":[1],"a":[2,33,59,72,99],"novel":[3],"framework":[4,66],"for":[5],"talking":[6,34,45,78],"head":[7,15,35,92],"video":[8,50],"editing,":[9],"allowing":[10],"users":[11],"to":[12,42,54,81,87,114],"freely":[13,88],"edit":[14,43],"pose,":[16,93],"emotion,":[17,94],"and":[18,51,95,111,129],"eye":[19,96],"blink":[20],"while":[21,85],"maintaining":[22],"audio-visual":[23],"synchronization.":[24,105],"Unlike":[25],"previous":[26],"approaches":[27,123],"that":[28,75,102],"mainly":[29],"focus":[30],"on":[31],"generating":[32],"video,":[36],"our":[37],"proposed":[38,65],"model":[39],"is":[40],"able":[41],"the":[44,82,116],"heads":[46,79],"of":[47,62,68],"an":[48],"input":[49],"restore":[52],"it":[53],"full":[55],"frames,":[56],"which":[57],"supports":[58],"broader":[60],"range":[61],"applications.":[63],"Our":[64],"consists":[67],"two":[69],"parts:":[70],"a)":[71],"reconstruction-based":[73],"generator":[74],"can":[76],"generate":[77],"fitting":[80],"original":[83],"frame":[84],"corresponding":[86],"controllable":[89],"attributes,":[90],"including":[91],"blink.":[97],"b)":[98],"multiple-attribute":[100],"discriminator":[101],"enforces":[103],"attribute-visual":[104],"additionally":[107],"introduce":[108],"attention":[109],"modules":[110],"perceptual":[112],"loss":[113],"improve":[115],"overall":[117],"generation":[118],"quality.":[119],"compare":[121],"existing":[122],"as":[124],"corroborated":[125],"by":[126],"quantitative":[127],"metrics":[128],"qualitative":[130],"comparisons.":[131]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
