{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T22:21:42Z","timestamp":1776291702702,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687669","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T08:14:37Z","timestamp":1733213677000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["FreeAvatar: Robust 3D Facial Animation Transfer by Learning an Expression Foundation Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4333-5957","authenticated-orcid":false,"given":"Feng","family":"Qiu","sequence":"first","affiliation":[{"name":"Netease, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5907-7342","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Netease, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3159-0034","authenticated-orcid":false,"given":"Chen","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Queensland, Hangzhou, China and Netease, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8575-8229","authenticated-orcid":false,"given":"Rudong","family":"An","sequence":"additional","affiliation":[{"name":"Netease, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3626-4094","authenticated-orcid":false,"given":"Lincheng","family":"Li","sequence":"additional","affiliation":[{"name":"Netease, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1834-4429","authenticated-orcid":false,"given":"Yu","family":"Ding","sequence":"additional","affiliation":[{"name":"Netease, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5420-0516","authenticated-orcid":false,"given":"Changjie","family":"Fan","sequence":"additional","affiliation":[{"name":"Netease, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4367-0816","authenticated-orcid":false,"given":"Zhipeng","family":"Hu","sequence":"additional","affiliation":[{"name":"Netease, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-5649","authenticated-orcid":false,"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00024"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02009"},{"key":"e_1_3_3_2_4_1","volume-title":"ARKit","author":"Inc. Apple","year":"2022","unstructured":"Apple Inc.2022. ARKit. https:\/\/developer.apple.com\/augmented-reality\/arkit\/"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Chen Cao Yanlin Weng Shun Zhou Yiying Tong and Kun Zhou. 2013. Facewarehouse: A 3d facial expression database for visual computing. IEEE Transactions on Visualization and Computer Graphics 20 3 (2013) 413\u2013425.","DOI":"10.1109\/TVCG.2013.249"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00044"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"Prashanth Chandran Lo\u00efc Ciccone Markus Gross and Derek Bradley. 2022. Local anatomically-constrained facial performance retargeting. ACM Transactions on Graphics (TOG) 41 4 (2022) 1\u201314.","DOI":"10.1145\/3528223.3530114"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555398"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Alanah Davis John Murphy Dawn Owens Deepak Khazanchi and Ilze Zigurs. 2009. Avatars people and virtual worlds: Foundations for research in metaverses. Journal of the Association for Information Systems 10 2 (2009) 1.","DOI":"10.17705\/1jais.00183"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Paul Ekman. 1992. An argument for basic emotions. Cognition & emotion 6 3-4 (1992) 169\u2013200.","DOI":"10.1080\/02699939208411068"},{"key":"e_1_3_3_2_14_1","unstructured":"FriesenW\u00a0V EkmanP. 1978. A tech\u2014niqueforthem easurem entoffacialm ovement. Palo Alto. CA: ConsultingPsychologistsPress 12 1 (1978) 271."},{"key":"e_1_3_3_2_15_1","volume-title":"MetaHuman Animator","author":"Inc. Epic Games,","year":"2023","unstructured":"Epic Games, Inc.2023. MetaHuman Animator. https:\/\/www.unrealengine.com\/en-US\/metahuman Accessed: 2023-10-01."},{"key":"e_1_3_3_2_16_1","volume-title":"Faceware","author":"Inc. Faceware Technologies,","year":"2023","unstructured":"Faceware Technologies, Inc.2023. Faceware. https:\/\/facewaretech.com\/ Accessed: 2023-10-01."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"crossref","unstructured":"Yao Feng Haiwen Feng Michael\u00a0J Black and Timo Bolkart. 2021. Learning an animatable detailed 3D face model from in-the-wild images. ACM Transactions on Graphics (ToG) 40 4 (2021) 1\u201313.","DOI":"10.1145\/3476576.3476646"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206868"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_10"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMPTELIX.2017.8004002"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Tero Karras Timo Aila Samuli Laine Antti Herva and Jaakko Lehtinen. 2017. Audio-driven facial animation by joint end-to-end learning of pose and emotion. ACM Transactions on Graphics (ToG) 36 4 (2017) 1\u201312.","DOI":"10.1145\/3072959.3073658"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00259"},{"key":"e_1_3_3_2_26_1","unstructured":"Ariel Larey Omri Asraf Adam Kelder Itzik Wilf Ofer Kruzel and Nati Daniel. 2023. Facial Expression Re-targeting from a Single Character. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.12188 (2023)."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00046"},{"key":"e_1_3_3_2_28_1","unstructured":"John\u00a0P Lewis Ken Anjyo Taehyun Rhee Mengjie Zhang Frederic\u00a0H Pighin and Zhigang Deng. 2014. Practice and theory of blendshape facial models. Eurographics (State of the Art Reports) 1 8 (2014) 2."},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","unstructured":"Tianye Li Timo Bolkart Michael.\u00a0J. Black Hao Li and Javier Romero. 2017. Learning a model of facial shape and expression from 4D scans. ACM Transactions on Graphics (Proc. SIGGRAPH Asia) 36 6 (2017) 194:1\u2013194:17. 10.1145\/3130800.3130813https:\/\/dl.acm.org\/doi\/10.1145\/3130800.3130813","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_3_2_31_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.05101 (2017)."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Ali Mollahosseini Behzad Hasani and Mohammad\u00a0H Mahoor. 2017. Affectnet: A database for facial expression valence and arousal computing in the wild. IEEE Transactions on Affective Computing 10 1 (2017) 18\u201331.","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Lucio Moser Chinyu Chien Mark Williams Jose Serra Darren Hendler and Doug Roble. 2021. Semi-supervised video-driven facial animation transfer for production. ACM Transactions on Graphics (TOG) 40 6 (2021) 1\u201318.","DOI":"10.1145\/3478513.3480515"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Arsha Nagrani Joon\u00a0Son Chung and Andrew Zisserman. 2017. Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.08612 (2017).","DOI":"10.21437\/Interspeech.2017-950"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Kristine\u00a0L Nowak and Jesse Fox. 2018. Avatars and computer-mediated communication: a review of the definitions uses and effects of digital representations. Review of Communication Research 6 (2018) 30\u201353.","DOI":"10.12840\/issn.2255-4165.2018.06.01.015"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613803"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1185657.1185842"},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"crossref","unstructured":"Soujanya Poria Erik Cambria Rajiv Bajpai and Amir Hussain. 2017. A review of affective computing: From unimodal analysis to multimodal fusion. Information fusion 37 (2017) 98\u2013125.","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"e_1_3_3_2_40_1","unstructured":"Alec Radford Luke Metz and Soumith Chintala. 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1511.06434 (2015)."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"crossref","unstructured":"Roger Blanco\u00a0I Ribera Eduard Zell John\u00a0P Lewis Junyong Noh and Mario Botsch. 2017. Facial retargeting with automatic range of motion alignment. ACM Transactions on graphics (TOG) 36 4 (2017) 1\u201312.","DOI":"10.1145\/3072959.3073674"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"crossref","unstructured":"Rasmus Rothe Radu Timofte and Luc Van\u00a0Gool. 2018. Deep expectation of real and apparent age from a single image without facial landmarks. International Journal of Computer Vision 126 2 (2018) 144\u2013157.","DOI":"10.1007\/s11263-016-0940-3"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"crossref","unstructured":"James\u00a0A Russell Maria Lewicka and Toomas Niit. 1989. A cross-cultural study of a circumplex model of affect. Journal of personality and social psychology 57 5 (1989) 848.","DOI":"10.1037\/\/0022-3514.57.5.848"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/1951602"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_43"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"crossref","unstructured":"Robert\u00a0W Sumner and Jovan Popovi\u0107. 2004. Deformation transfer for triangle meshes. ACM Transactions on graphics (TOG) 23 3 (2004) 399\u2013405.","DOI":"10.1145\/1015706.1015736"},{"key":"e_1_3_3_2_47_1","first-page":"3361","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Tewari Ayush","year":"2021","unstructured":"Ayush Tewari, Hans-Peter Seidel, Mohamed Elgharib, Christian Theobalt, et\u00a0al. 2021. Learning complete 3d morphable face models from images and videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3361\u20133371."},{"key":"e_1_3_3_2_48_1","first-page":"1274","volume-title":"Proceedings of the IEEE international conference on computer vision workshops","author":"Tewari Ayush","year":"2017","unstructured":"Ayush Tewari, Michael Zollhofer, Hyeongwoo Kim, Pablo Garrido, Florian Bernard, Patrick Perez, and Christian Theobalt. 2017. Mofa: Model-based deep convolutional face autoencoder for unsupervised monocular reconstruction. In Proceedings of the IEEE international conference on computer vision workshops. 1274\u20131283."},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"crossref","unstructured":"Antoine Toisoul Jean Kossaifi Adrian Bulat Georgios Tzimiropoulos and Maja Pantic. 2021. Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Nature Machine Intelligence 3 1 (2021) 42\u201350.","DOI":"10.1038\/s42256-020-00280-0"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00122"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"crossref","unstructured":"Alex Trevithick Matthew Chan Michael Stengel Eric Chan Chao Liu Zhiding Yu Sameh Khamis Ravi Ramamoorthi and Koki Nagano. 2023. Real-time radiance fields for single-image portrait view synthesis. (2023).","DOI":"10.1145\/3592460"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00583"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01969"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"crossref","unstructured":"Xin Yan and Xiao\u00a0Gang Su. 2010. Stratified Wilson and Newcombe confidence intervals for multiple binomial proportions. Statistics in Biopharmaceutical Research 2 3 (2010) 329\u2013335.","DOI":"10.1198\/sbr.2009.0049"},{"key":"e_1_3_3_2_55_1","unstructured":"Dong Yi Zhen Lei Shengcai Liao and Stan\u00a0Z Li. 2014. Learning face representation from scratch. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1411.7923 (2014)."},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"crossref","unstructured":"Juyong Zhang Keyu Chen and Jianmin Zheng. 2020. Facial expression retargeting from human to avatar made easy. IEEE Transactions on Visualization and Computer Graphics 28 2 (2020) 1274\u20131287.","DOI":"10.1109\/TVCG.2020.3013876"},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00669"},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01035"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13382"}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Conference Papers","location":"Tokyo Japan","acronym":"SA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2024 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687669","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:20Z","timestamp":1750295900000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687669"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":58,"alternative-id":["10.1145\/3680528.3687669","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687669","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}