{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:10Z","timestamp":1776931210957,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,12]]},"DOI":"10.1145\/3756884.3768420","type":"proceedings-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T07:52:48Z","timestamp":1764921168000},"page":"1-3","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Generative and Expressive 3D Facial Animations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5013-8074","authenticated-orcid":false,"given":"Yushu","family":"Jiang","sequence":"first","affiliation":[{"name":"Institute of Communication, Culture, Information and Technology, University of Toronto, Mississauga, Ontario, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8522-6207","authenticated-orcid":false,"given":"Jilliane","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute of Communication, Culture, Information and Technology, University of Toronto, Mississauga, Ontario, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9452-6913","authenticated-orcid":false,"given":"Bree L","family":"McEwan","sequence":"additional","affiliation":[{"name":"Institute of Communication, Culture, Information and Technology, University of Toronto, Mississauga, Ontario, Canada"}]}],"member":"320","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Apple Inc.2025. ARFaceAnchor.BlendShapeLocation. https:\/\/developer.apple.com\/documentation\/arkit\/arfaceanchor\/blendshapelocation. Accessed: 2025-08-31."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"e_1_3_3_1_5_2","volume-title":"Daz3D","author":"Inc. Daz Productions,","year":"2025","unstructured":"Daz Productions, Inc.2025. Daz3D. https:\/\/www.daz3d.com\/ Accessed: August 31, 2025."},{"key":"e_1_3_3_1_6_2","unstructured":"Qijun Gan Ruizi Yang Jianke Zhu Shaofei Xue and Steven Hoi. 2025. OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation. arxiv:https:\/\/arXiv.org\/abs\/2506.18866\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2506.18866"},{"key":"e_1_3_3_1_7_2","unstructured":"Google. 2025. MediaPipe. https:\/\/google.github.io\/mediapipe\/. Accessed: August 31 2025."},{"key":"e_1_3_3_1_8_2","unstructured":"Tianqi Li Ruobing Zheng Minghui Yang Jingdong Chen and Ming Yang. 2025. Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis. arxiv:https:\/\/arXiv.org\/abs\/2411.19509\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2411.19509"},{"key":"e_1_3_3_1_9_2","unstructured":"Xinyang Li Gen Li Zhihui Lin Yichen Qian Gongxin Yao Weinan Jia Weihua Chen and Fan Wang. 2025. MoDA: Multi-modal Diffusion Architecture for Talking Head Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.03256 (2025)."},{"key":"e_1_3_3_1_10_2","unstructured":"Yaron Lipman Ricky T.\u00a0Q. Chen Heli Ben-Hamu Maximilian Nickel and Matt Le. 2023. Flow Matching for Generative Modeling. arxiv:https:\/\/arXiv.org\/abs\/2210.02747\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2210.02747"},{"key":"e_1_3_3_1_11_2","unstructured":"Meta Platforms Inc.2025. Oculus Lipsync for Unity Development. Meta Horizon OS Developers Documentation. https:\/\/developers.meta.com\/horizon\/documentation\/unity\/audio-ovrlipsync-unity\/ Accessed: August 31 2025."},{"key":"e_1_3_3_1_12_2","volume-title":"Audio2Face-3D","author":"Corporation NVIDIA","year":"2025","unstructured":"NVIDIA Corporation. 2025. Audio2Face-3D. NVIDIA Omniverse. https:\/\/build.nvidia.com\/nvidia\/audio2face-3d Accessed on August 31, 2025. Version details available on the site.."},{"key":"e_1_3_3_1_13_2","volume-title":"The SAGE Encyclopedia of Communication Research Methods","author":"Prince Emily","year":"2015","unstructured":"Emily Prince, Kathryn Martin, and Daniel Messinger. 2015. Facial Action Coding System. In The SAGE Encyclopedia of Communication Research Methods. SAGE Publications, Inc."},{"key":"e_1_3_3_1_14_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Tao Xu Greg Brockman Christine McLeavey and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. arxiv:https:\/\/arXiv.org\/abs\/2212.04356\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2212.04356"},{"key":"e_1_3_3_1_15_2","volume-title":"Unity Game Engine","author":"Technologies Unity","year":"2025","unstructured":"Unity Technologies. 2025. Unity Game Engine. https:\/\/unity.com\/ Accessed: August 31, 2025."},{"key":"e_1_3_3_1_16_2","unstructured":"Team Wan Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang Jianyuan Zeng Jiayu Wang Jingfeng Zhang Jingren Zhou Jinkai Wang Jixuan Chen Kai Zhu Kang Zhao Keyu Yan Lianghua Huang Mengyang Feng Ningyi Zhang Pandeng Li Pingyu Wu Ruihang Chu Ruili Feng Shiwei Zhang Siyang Sun Tao Fang Tianxing Wang Tianyi Gui Tingyu Weng Tong Shen Wei Lin Wei Wang Wei Wang Wenmeng Zhou Wente Wang Wenting Shen Wenyuan Yu Xianzhong Shi Xiaoming Huang Xin Xu Yan Kou Yangyu Lv Yifei Li Yijing Liu Yiming Wang Yingya Zhang Yitong Huang Yong Li You Wu Yu Liu Yulin Pan Yun Zheng Yuntao Hong Yupeng Shi Yutong Feng Zeyinzi Jiang Zhen Han Zhi-Fan Wu and Ziyu Liu. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. arxiv:https:\/\/arXiv.org\/abs\/2503.20314\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2503.20314"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Thibaut Weise Sofien Bouaziz Hao Li and Mark Pauly. 2011. Realtime performance-based facial animation. ACM Trans. Graph. 30 4 Article 77 (July 2011) 10\u00a0pages. 10.1145\/2010324.1964972","DOI":"10.1145\/2010324.1964972"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Sicheng Xu Guojun Chen Yu-Xiao Guo Jiaolong Yang Chong Li Zhenyu Zang Yizhong Zhang Xin Tong and Baining Guo. 2024. VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time. arxiv:https:\/\/arXiv.org\/abs\/2404.10667\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2404.10667","DOI":"10.52202\/079017-0021"}],"event":{"name":"VRST '25: 31st ACM Symposium on Virtual Reality Software and Technology","location":"Montreal QC Canada","acronym":"VRST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 2025 31st ACM Symposium on Virtual Reality Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3756884.3768420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T09:13:39Z","timestamp":1764926019000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3756884.3768420"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":17,"alternative-id":["10.1145\/3756884.3768420","10.1145\/3756884"],"URL":"https:\/\/doi.org\/10.1145\/3756884.3768420","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]},"assertion":[{"value":"2025-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}