{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T05:57:17Z","timestamp":1780725437487,"version":"3.54.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171317"],"award-info":[{"award-number":["62171317"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122058"],"award-info":[{"award-number":["62122058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771339"],"award-info":[{"award-number":["61771339"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tvcg.2021.3107669","type":"journal-article","created":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T20:04:29Z","timestamp":1630094669000},"page":"4873-4886","source":"Crossref","is-referenced-by-count":27,"title":["Geometry-Guided Dense Perspective Network for Speech-Driven Facial Animation"],"prefix":"10.1109","volume":"28","author":[{"given":"Jingying","family":"Liu","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binyuan","family":"Hui","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2326-0166","authenticated-orcid":false,"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunke","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-5680","authenticated-orcid":false,"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3215-0225","authenticated-orcid":false,"given":"Yebin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7521-7920","authenticated-orcid":false,"given":"Jingyu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964972"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/191940"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_616"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_43"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243017"},{"key":"ref37","first-page":"275","article-title":"Dynamic units of visual speech","author":"taylor","year":"2012","journal-title":"Proc ACM SIGGRAPH\/Eurographics Symp Comput Animation"},{"key":"ref36","first-page":"1","article-title":"A deep learning approach for generalized speech animation","volume":"36","author":"taylor","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-483"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073640","article-title":"Synthesizing obama: Learning lip sync from audio","volume":"36","author":"suwajanakorn","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref10","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00766"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"},{"key":"ref12","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2002.1021892"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref16","first-page":"2261","article-title":"Densely connected convolutional networks","author":"huang","year":"2016","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01223"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/971478.971488"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2007.22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126510"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5950"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1095878.1095881"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2156-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.287"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref8","first-page":"93","article-title":"The DARPA speech recognition research database: Specifications and status","author":"fisher","year":"1986","journal-title":"Proc DARPA Workshop Speech Recognize"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925984","article-title":"JALI: An animator-centric viseme model for expressive lip synchronization","volume":"35","author":"edwards","year":"2016","journal-title":"ACM Trans Graph"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298657"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024163"},{"key":"ref1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073658","article-title":"Audio-driven facial animation by joint end-to-end learning of pose and emotion","volume":"36","author":"karras","year":"2017","journal-title":"ACM Trans Graph"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref21","first-page":"1","article-title":"Deep video portraits","volume":"37","author":"kim","year":"2018","journal-title":"ACM Trans Graph"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2006.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13830"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015525"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418815"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818122"},{"key":"ref43","first-page":"1","article-title":"Visemenet: Audio-driven animator-centric speech animation","volume":"37","author":"zhou","year":"2018","journal-title":"ACM Trans Graph"},{"key":"ref25","first-page":"1","article-title":"Learning a model of facial shape and expression from 4D scans","volume":"36","author":"li","year":"2017","journal-title":"ACM Trans Graph"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/2945\/9930678\/09524465.pdf?arnumber=9524465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T00:15:08Z","timestamp":1670372108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9524465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2021.3107669","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]}}}