{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T17:32:57Z","timestamp":1776792777728,"version":"3.51.2"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887890","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Realistic Real-Time Talking Head Synthesis with Grid Encoding and Progressive Conditioning"],"prefix":"10.1109","author":[{"given":"Zhiling","family":"Ye","sequence":"first","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd.,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang-Guo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dingheng","family":"Zeng","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Lu","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/141"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3305243"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"ref7","author":"Yao","year":"2022","journal-title":"DFA-NeRF: Personalized talking head generation via disentangled face attributes neural rendering"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/FG57933.2023.10042567"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref12","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475280"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01357"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.287"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.12987\/9780300280289-018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596787"},{"key":"ref28","article-title":"Visualizing data using t-SNE","author":"Van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480487"},{"key":"ref30","article-title":"GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation","author":"Ye","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref36","volume-title":"pytorch-fid: FID Score for PyTorch","author":"Seitzer","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02481-9"},{"key":"ref45","author":"Ye","year":"2023","journal-title":"GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887890.pdf?arnumber=10887890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:53Z","timestamp":1774416353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887890\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887890","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}