{"id":"https://openalex.org/W4296438045","doi":"https://doi.org/10.1109/tmm.2022.3207606","title":"Predicting Personalized Head Movement From Short Video and Speech Signal","display_name":"Predicting Personalized Head Movement From Short Video and Speech Signal","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4296438045","doi":"https://doi.org/10.1109/tmm.2022.3207606"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3207606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3207606","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5054879013","display_name":"Ran Yi","orcid":"https://orcid.org/0000-0003-1858-3358"},"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":"Ran Yi","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1858-3358","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101402532","display_name":"Zipeng Ye","orcid":"https://orcid.org/0000-0002-4322-7550"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zipeng Ye","raw_affiliation_strings":["BNRist, MOE-Key Laboratory of Pervasive Computing, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4322-7550","affiliations":[{"raw_affiliation_string":"BNRist, MOE-Key Laboratory of Pervasive Computing, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021093689","display_name":"Zhiyao Sun","orcid":"https://orcid.org/0000-0002-6377-7103"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyao Sun","raw_affiliation_strings":["BNRist, MOE-Key Laboratory of Pervasive Computing, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6377-7103","affiliations":[{"raw_affiliation_string":"BNRist, MOE-Key Laboratory of Pervasive Computing, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101904821","display_name":"Juyong Zhang","orcid":"https://orcid.org/0000-0002-1805-1426"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juyong Zhang","raw_affiliation_strings":["School of Mathematical Sciences, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1805-1426","affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730836","display_name":"Guoxin Zhang","orcid":"https://orcid.org/0000-0002-7531-0404"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoxin Zhang","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928510","display_name":"Pengfei Wan","orcid":"https://orcid.org/0000-0001-7225-565X"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Wan","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7225-565X","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059021869","display_name":"Hujun Bao","orcid":"https://orcid.org/0000-0002-2662-0334"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hujun Bao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2662-0334","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008076279","display_name":"Yong\u2010Jin Liu","orcid":"https://orcid.org/0000-0001-5774-1916"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong-Jin Liu","raw_affiliation_strings":["BNRist, MOE-Key Laboratory of Pervasive Computing, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5774-1916","affiliations":[{"raw_affiliation_string":"BNRist, MOE-Key Laboratory of Pervasive Computing, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.664,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85220729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"6315","last_page":"6328"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9976999759674072,"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":0.8801447153091431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5846880674362183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5643920302391052},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.517950177192688},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.500525951385498},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.49148762226104736},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48883312940597534},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.47935134172439575},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45069369673728943},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4398775100708008},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.42811501026153564},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4152320325374603},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41365110874176025},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4120594561100006},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.2532695233821869},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1287878155708313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8801447153091431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5846880674362183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5643920302391052},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.517950177192688},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.500525951385498},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.49148762226104736},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48883312940597534},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.47935134172439575},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45069369673728943},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4398775100708008},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.42811501026153564},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4152320325374603},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41365110874176025},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4120594561100006},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.2532695233821869},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1287878155708313},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3207606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3207606","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G1014109120","display_name":null,"funder_award_id":"72192821","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1736198338","display_name":null,"funder_award_id":"61725204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3087161604","display_name":null,"funder_award_id":"I8ZD22","funder_id":"https://openalex.org/F4320327557","funder_display_name":"National Office for Philosophy and Social Sciences"},{"id":"https://openalex.org/G3429353868","display_name":null,"funder_award_id":"21511101200","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G6165465362","display_name":null,"funder_award_id":"61972157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320327557","display_name":"National Office for Philosophy and Social Sciences","ror":"https://ror.org/04m0ms912"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1555698685","https://openalex.org/W1585160083","https://openalex.org/W1901129140","https://openalex.org/W2015143272","https://openalex.org/W2017107803","https://openalex.org/W2045831935","https://openalex.org/W2054721804","https://openalex.org/W2105649179","https://openalex.org/W2107037917","https://openalex.org/W2118004237","https://openalex.org/W2162220380","https://openalex.org/W2301937176","https://openalex.org/W2398381847","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2738406145","https://openalex.org/W2770534877","https://openalex.org/W2776121517","https://openalex.org/W2798291180","https://openalex.org/W2803705807","https://openalex.org/W2806379360","https://openalex.org/W2806833697","https://openalex.org/W2883861033","https://openalex.org/W2884460600","https://openalex.org/W2889214350","https://openalex.org/W2891205112","https://openalex.org/W2944294033","https://openalex.org/W2956024009","https://openalex.org/W2960274051","https://openalex.org/W2962780596","https://openalex.org/W2963073614","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2964559396","https://openalex.org/W2979157532","https://openalex.org/W2990452356","https://openalex.org/W2994892543","https://openalex.org/W3008653537","https://openalex.org/W3019952993","https://openalex.org/W3039250377","https://openalex.org/W3044842458","https://openalex.org/W3081492798","https://openalex.org/W3087121792","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3120743815","https://openalex.org/W3167297682","https://openalex.org/W3186090335","https://openalex.org/W3195529437","https://openalex.org/W3197199219","https://openalex.org/W3202128205","https://openalex.org/W4200174933","https://openalex.org/W6737896281","https://openalex.org/W6751750676","https://openalex.org/W6754420807","https://openalex.org/W6767264202","https://openalex.org/W6769148693","https://openalex.org/W6788439838"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2532377291","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2617644139","https://openalex.org/W4400097232","https://openalex.org/W1976926596","https://openalex.org/W4310844315","https://openalex.org/W3020604125","https://openalex.org/W577858612"],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,20,32,50,173,198],"face":[2,174,199],"video":[3,100,161,175],"generation":[4],"has":[5,203],"attracted":[6],"much":[7],"attention":[8,15],"recently.":[9],"However,":[10],"few":[11],"existing":[12],"works":[13],"pay":[14],"to":[16],"machine":[17],"learning":[18],"of":[19,97,101,131,154,162],"head":[21,37,51,83,94,118,178,194],"movement,":[22,38,52],"especially":[23],"based":[24],"on":[25,137],"the":[26,44,73,93,107,123,128,138,214],"phonetic":[27],"study.":[28],"Observing":[29],"that":[30,80,114,149,187],"real-world":[31],"faces":[33],"often":[34],"accompany":[35],"natural":[36],"in":[39,72,106,196],"this":[40,62],"paper,":[41],"we":[42,64,76,110,142],"model":[43,148],"relation":[45],"between":[46],"speech":[47,134,152],"signal":[48,153],"and":[49,104,127,158,168,182,201,211],"which":[53],"is":[54],"a":[55,66,82,89,98,112,116,144,151,155,159,163,170,183],"typical":[56],"one-to-many":[57],"mapping":[58,69,140],"problem.":[59],"To":[60],"solve":[61],"problem,":[63],"propose":[65],"novel":[67],"two-step":[68],"strategy:":[70],"(1)":[71],"first":[74],"step,":[75,109],"train":[77,111],"an":[78,132],"encoder":[79],"predicts":[81],"motion":[84,95,119,124],"behavior":[85,125],"pattern":[86,126],"(modeled":[87],"as":[88,166],"feature":[90],"vector)":[91],"from":[92,121],"sequence":[96,120],"short":[99,160],"10\u201315":[102],"seconds,":[103],"(2)":[105],"second":[108],"decoder":[113],"predict":[115],"unique":[117],"both":[122],"auditory":[129],"features":[130],"arbitrary":[133],"signal.":[135],"Based":[136],"proposed":[139],"strategy,":[141],"build":[143],"deep":[145],"neural":[146],"network":[147],"takes":[150],"source":[156],"person":[157,165],"target":[164],"input,":[167],"outputs":[169],"synthesized":[171,197],"high-fidelity":[172],"with":[176,213],"personalized":[177,193],"pose.":[179],"Extensive":[180],"experiments":[181],"user":[184],"study":[185],"show":[186],"our":[188],"method":[189],"can":[190],"generate":[191],"high-quality":[192],"movement":[195],"videos,":[200],"meanwhile,":[202],"comparable":[204],"facial":[205],"animation":[206],"quality":[207],"(e.g.,":[208],"lip":[209],"synchronization":[210],"expression)":[212],"state-of-the-art":[215],"methods.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
