{"id":"https://openalex.org/W2099178131","doi":"https://doi.org/10.1109/iscslp.2010.5684834","title":"Rendering a personalized photo-real talking head from short video footage","display_name":"Rendering a personalized photo-real talking head from short video footage","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2099178131","doi":"https://doi.org/10.1109/iscslp.2010.5684834","mag":"2099178131"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","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/A5100436501","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-2517-2728"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117823207","display_name":"Wei Han","orcid":"https://orcid.org/0000-0003-0759-1766"},"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"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["Department of Computer Science, Shanghai Jiaotong University, Shanghai, China","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101881032","display_name":"Xiaojun Qian","orcid":"https://orcid.org/0000-0002-6026-8928"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xiaojun Qian","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong Kong, China","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.22580645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"v","issue":null,"first_page":"129","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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":0.9847999811172485,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8458360433578491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8284088373184204},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6590660214424133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5899676084518433},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5349928736686707},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.519189715385437},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.47964364290237427},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.43271148204803467}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8458360433578491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8284088373184204},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6590660214424133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5899676084518433},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5349928736686707},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.519189715385437},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.47964364290237427},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.43271148204803467},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp.2010.5684834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.309.1713","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.309.1713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www1.se.cuhk.edu.hk/~hccl/publications/pub/101_paper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320333993","display_name":"Microsoft Research Asia","ror":"https://ror.org/0300m5276"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W71477782","https://openalex.org/W75668230","https://openalex.org/W158109762","https://openalex.org/W216012752","https://openalex.org/W1509899163","https://openalex.org/W1552213476","https://openalex.org/W1693261796","https://openalex.org/W1992287499","https://openalex.org/W2041812800","https://openalex.org/W2059658648","https://openalex.org/W2070604790","https://openalex.org/W2082229127","https://openalex.org/W2083792893","https://openalex.org/W2097924042","https://openalex.org/W2108033344","https://openalex.org/W2114659828","https://openalex.org/W2119085432","https://openalex.org/W2126511038","https://openalex.org/W2143072537","https://openalex.org/W2143132120","https://openalex.org/W2144139079","https://openalex.org/W2145379201","https://openalex.org/W2146145272","https://openalex.org/W2146614494","https://openalex.org/W2147885303","https://openalex.org/W2150658333","https://openalex.org/W2162598851","https://openalex.org/W2166823384","https://openalex.org/W2237250383","https://openalex.org/W2403351921","https://openalex.org/W2613407020","https://openalex.org/W3006295631","https://openalex.org/W4233118564","https://openalex.org/W6602918789","https://openalex.org/W6603100307","https://openalex.org/W6608647691","https://openalex.org/W6681253763","https://openalex.org/W6681384653","https://openalex.org/W6713743917","https://openalex.org/W6737323677"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5,76],"HMM":[6,39],"trajectory-guided,":[7],"real":[8],"image":[9],"sample":[10],"concatenation":[11],"approach":[12],"to":[13,43,69,87],"photo-real":[14,118],"talking":[15,119],"head":[16,90,120],"synthesis.":[17],"An":[18],"audio-visual":[19],"database":[20],"of":[21,35,48,79,108],"a":[22,29,67,88,116],"person":[23],"is":[24,40,63,95],"recorded":[25],"first":[26,136],"for":[27,51],"training":[28,74],"statistical":[30],"Hidden":[31],"Markov":[32],"Model":[33],"(HMM)":[34],"Lips":[36],"movement.":[37],"The":[38,60,92],"then":[41,64,84],"used":[42,65],"generate":[44],"the":[45,56,72,111,124,135,139],"dynamic":[46],"trajectory":[47,62],"lips":[49,80],"movement":[50],"given":[52,125],"speech":[53,126],"signals":[54,127],"in":[55,121,138,143],"maximum":[57],"probability":[58],"sense.":[59],"generated":[61],"as":[66,102,104],"guide":[68],"select,":[70],"from":[71],"original":[73],"database,":[75],"optimal":[77],"sequence":[78],"images":[81],"which":[82],"are":[83],"stitched":[85],"back":[86],"background":[89],"video.":[91],"whole":[93],"procedure":[94],"fully":[96],"automatic":[97],"and":[98],"data":[99],"driven.":[100],"For":[101],"short":[103],"20":[105],"minutes":[106],"recording":[107],"audio/video":[109],"footage,":[110],"proposed":[112],"system":[113,133],"can":[114],"synthesize":[115],"highly":[117],"sync":[122],"with":[123],"(natural":[128],"or":[129],"TTS":[130],"synthesized).":[131],"This":[132],"won":[134],"place":[137],"A/V":[140],"consistency":[141],"contest":[142],"LIPS":[144],"Challenge(2009),":[145],"perceptually":[146],"evaluated":[147],"by":[148],"recruited":[149],"human":[150],"subjects.":[151]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}