{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:01Z","timestamp":1761894661030,"version":"build-2065373602"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209876","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["VividPose: Vividly 3D-driven Stable Pose Diffusion of High Facial Fidelity"],"prefix":"10.1109","author":[{"given":"Qilin","family":"Wang","sequence":"first","affiliation":[{"name":"Fudan University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengkai","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengming","family":"Xu","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Cao","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijian","family":"Cao","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanxiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Fudan University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref2","article-title":"Disco: Disentangled control for referring human dance generation in real world","author":"Wang","year":"2024","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref6","article-title":"First order motion model for image animation","author":"Siarohin","year":"2019","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref9","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref13","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2023","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688119"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687813"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref18","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref19","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","volume":"abs\/2311.15127","author":"Blattmann","year":"2023","journal-title":"CoRR"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref23","article-title":"Smpler-x: Scaling up expressive human pose and shape estimation","author":"Cai","year":"2023","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Dwnet: Dense warp-based network for pose-guided human video generation","author":"Zablotskaia","year":"2019","journal-title":"BMVC"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref29","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref31","article-title":"Towards accurate generative models of video: A new metric & challenges","volume":"abs\/1812.01717","author":"Unterthiner","year":"2018","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00690"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209876.pdf?arnumber=11209876","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:32:50Z","timestamp":1761888770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209876\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209876","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}