{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T17:08:08Z","timestamp":1730221688731,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,27]]},"DOI":"10.1109\/fg59268.2024.10582043","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T17:40:08Z","timestamp":1720719608000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Embedded Representation Learning Network for Animating Styled Video Portrait"],"prefix":"10.1109","author":[{"given":"Tianyong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Automation, Southeast University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangguandong","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Niu","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyu","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICCV48922.2021.00580"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1016\/j.imavis.2024.104911"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/FG57933.2023.10042567"},{"key":"ref5","article-title":"Talking head generation driven by speech-related facial action units and audio-based on multimodal representation fusion","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/CVPR52688.2022.01967"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR52688.2022.01821"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/3607541.3616812"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICCV48922.2021.00573"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1145\/3528233.3530745"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref12","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/CVPR46437.2021.00278"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/3130800.3130813"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR52688.2022.00338"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref17","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref19","first-page":"32","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1145\/3394171.3413532"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CVPR52729.2023.00445"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICCV48922.2021.00121"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1007\/978-3-031-19775-8_39"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/CVPR52729.2023.00197"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR.2016.207"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"ref27","first-page":"30","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1007\/978-3-030-58589-1_42"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref30","article-title":"Voice2mesh: Cross-modal 3d face model generation from voices","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1145\/3474085.3475280"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1007\/978-3-030-58583-9_4"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1016\/j.patrec.2018.08.025"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.24963\/ijcai.2022\/501"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref36","article-title":"Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Dynamic neural textures: Generating talking-face videos with continuously controllable expressions","author":"Ye","year":"2022","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/ICCV48922.2021.00384"},{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/CVPR52729.2023.00836"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1609\/aaai.v37i3.25464"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1109\/CVPR46437.2021.00366"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/CVPR46437.2021.00416"}],"event":{"name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","start":{"date-parts":[[2024,5,27]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2024,5,31]]}},"container-title":["2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10581880\/10581860\/10582043.pdf?arnumber=10582043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:05:17Z","timestamp":1721279117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10582043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,27]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/fg59268.2024.10582043","relation":{},"subject":[],"published":{"date-parts":[[2024,5,27]]}}}