{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:57:58Z","timestamp":1776931078227,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763985","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1971-1975","authenticated-orcid":false,"given":"Chenxu","family":"Zhang","sequence":"first","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7794-5358","authenticated-orcid":false,"given":"Zenan","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4455-5632","authenticated-orcid":false,"given":"Hongyi","family":"Xu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-6518","authenticated-orcid":false,"given":"You","family":"Xie","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8976-7723","authenticated-orcid":false,"given":"Xiaochen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3173-8895","authenticated-orcid":false,"given":"Tianpei","family":"Gu","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3664-572X","authenticated-orcid":false,"given":"Guoxian","family":"Song","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9347-1367","authenticated-orcid":false,"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6923-4505","authenticated-orcid":false,"given":"Chao","family":"Liang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9495-5590","authenticated-orcid":false,"given":"Jianwen","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance Inc., Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6322-1175","authenticated-orcid":false,"given":"Linjie","family":"Luo","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_1_2_1","unstructured":"Alexei Baevski Yuhao Zhou Abdelrahman Mohamed and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems 33 (2020) 12449\u201312460."},{"key":"e_1_3_3_1_3_1","unstructured":"Mingdeng Cao Xintao Wang Zhongang Qi Ying Shan Xiaohu Qie and Yinqiang Zheng. 2023. MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.08465 (2023)."},{"key":"e_1_3_3_1_4_1","unstructured":"Xuyang Cao Guoxin Wang Sheng Shi Jun Zhao Yang Yao Jintao Fei and Minyu Gao. 2024. JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation. arxiv:https:\/\/arXiv.org\/abs\/2411.09209\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2411.09209"},{"key":"e_1_3_3_1_5_1","doi-asserted-by":"crossref","unstructured":"Boyuan Chen Diego Mart\u00ed\u00a0Mons\u00f3 Yilun Du Max Simchowitz Russ Tedrake and Vincent Sitzmann. 2024b. Diffusion forcing: Next-token prediction meets full-sequence diffusion. Advances in Neural Information Processing Systems 37 (2024) 24081\u201324125.","DOI":"10.52202\/079017-0759"},{"key":"e_1_3_3_1_6_1","doi-asserted-by":"crossref","unstructured":"Boyuan Chen Diego Mart\u00ed\u00a0Mons\u00f3 Yilun Du Max Simchowitz Russ Tedrake and Vincent Sitzmann. 2025b. Diffusion forcing: Next-token prediction meets full-sequence diffusion. Advances in Neural Information Processing Systems 37 (2025) 24081\u201324125.","DOI":"10.52202\/079017-0759"},{"key":"e_1_3_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"e_1_3_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"e_1_3_3_1_9_1","unstructured":"Zigeng Chen Xinyin Ma Gongfan Fang Zhenxiong Tan and Xinchao Wang. 2024a. Asyncdiff: Parallelizing diffusion models by asynchronous denoising. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.06911 (2024)."},{"key":"e_1_3_3_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"e_1_3_3_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"e_1_3_3_1_12_1","unstructured":"Jiahao Cui Hui Li Yao Yao Hao Zhu Hanlin Shang Kaihui Cheng Hang Zhou Siyu Zhu and Jingdong Wang. 2024a. Hallo2: Long-duration and high-resolution audio-driven portrait image animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.07718 (2024)."},{"key":"e_1_3_3_1_13_1","doi-asserted-by":"crossref","unstructured":"Jiahao Cui Hui Li Yun Zhan Hanlin Shang Kaihui Cheng Yuqi Ma Shan Mu Hang Zhou Jingdong Wang and Siyu Zhu. 2024b. Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.00733 (2024).","DOI":"10.1109\/CVPR52734.2025.01964"},{"key":"e_1_3_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"e_1_3_3_1_15_1","unstructured":"Yuwei Guo Ceyuan Yang Anyi Rao Yaohui Wang Yu Qiao Dahua Lin and Bo Dai. 2023. Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.04725 (2023)."},{"key":"e_1_3_3_1_16_1","unstructured":"Tianyu He Junliang Guo Runyi Yu Yuchi Wang Jialiang Zhu Kaikai An Leyi Li Xu Tan Chunyu Wang Han Hu et\u00a0al. 2023. Gaia: Zero-shot talking avatar generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.15230 (2023)."},{"key":"e_1_3_3_1_17_1","first-page":"8153","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu Li","year":"2024","unstructured":"Li Hu. 2024. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8153\u20138163."},{"key":"e_1_3_3_1_18_1","unstructured":"Xiaozhong Ji Xiaobin Hu Zhihong Xu Junwei Zhu Chuming Lin Qingdong He Jiangning Zhang Donghao Luo Yi Chen Qin Lin et\u00a0al. 2024. Sonic: Shifting Focus to Global Audio Perception in Portrait Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.16331 (2024)."},{"key":"e_1_3_3_1_19_1","unstructured":"Jianwen Jiang Chao Liang Jiaqi Yang Gaojie Lin Tianyun Zhong and Yanbo Zheng. 2024. Loopy: Taming audio-driven portrait avatar with long-term motion dependency. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.02634 (2024)."},{"key":"e_1_3_3_1_20_1","unstructured":"Gaojie Lin Jianwen Jiang Jiaqi Yang Zerong Zheng and Chao Liang. 2025. OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01061 (2025)."},{"key":"e_1_3_3_1_21_1","doi-asserted-by":"publisher","unstructured":"Steven\u00a0R. Livingstone and Frank\u00a0A. Russo. 2019. RAVDESS Emotional speech audio. 10.34740\/KAGGLE\/DSV\/256618","DOI":"10.34740\/KAGGLE\/DSV\/256618"},{"key":"e_1_3_3_1_22_1","unstructured":"Yifeng Ma Shiwei Zhang Jiayu Wang Xiang Wang Yingya Zhang and Zhidong Deng. 2023. Dreamtalk: When expressive talking head generation meets diffusion probabilistic models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.09767 2 3 (2023)."},{"key":"e_1_3_3_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_3_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_25_1","volume-title":"International Conference on Learning Representations","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"e_1_3_3_1_26_1","unstructured":"Kiwhan Song Boyuan Chen Max Simchowitz Yilun Du Russ Tedrake and Vincent Sitzmann. 2025. History-Guided Video Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2502.06764\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2502.06764"},{"key":"e_1_3_3_1_27_1","unstructured":"Xusen Sun Longhao Zhang Hao Zhu Peng Zhang Bang Zhang Xinya Ji Kangneng Zhou Daiheng Gao Liefeng Bo and Xun Cao. 2023. Vividtalk: One-shot audio-driven talking head generation based on 3d hybrid prior. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.01841 (2023)."},{"key":"e_1_3_3_1_28_1","doi-asserted-by":"crossref","unstructured":"Supasorn Suwajanakorn Steven\u00a0M Seitz and Ira Kemelmacher-Shlizerman. 2017. Synthesizing obama: learning lip sync from audio. ACM Transactions on Graphics (ToG) 36 4 (2017) 1\u201313.","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_3_3_1_29_1","unstructured":"Linrui Tian Siqi Hu Qi Wang Bang Zhang and Liefeng Bo. 2025. EMO2: End-Effector Guided Audio-Driven Avatar Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.10687 (2025)."},{"key":"e_1_3_3_1_30_1","doi-asserted-by":"crossref","unstructured":"Linrui Tian Qi Wang Bang Zhang and Liefeng Bo. 2024. Emo: Emote portrait alive-generating expressive portrait videos with audio2video diffusion model under weak conditions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17485 (2024).","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"e_1_3_3_1_31_1","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 (2021). https:\/\/www.nature.com\/articles\/s42256-020-00280-0"},{"key":"e_1_3_3_1_32_1","unstructured":"Thomas Unterthiner Sjoerd Van\u00a0Steenkiste Karol Kurach Rapha\u00ebl Marinier Marcin Michalski and Sylvain Gelly. 2019. FVD: A new metric for video generation. (2019)."},{"key":"e_1_3_3_1_33_1","unstructured":"Cong Wang Kuan Tian Jun Zhang Yonghang Guan Feng Luo Fei Shen Zhiwei Jiang Qing Gu Xiao Han and Wei Yang. 2024. V-express: Conditional dropout for progressive training of portrait video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.02511 (2024)."},{"key":"e_1_3_3_1_34_1","unstructured":"Mengchao Wang Qiang Wang Fan Jiang Yaqi Fan Yunpeng Zhang Yonggang Qi Kun Zhao and Mu Xu. 2025. FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.04842 (2025)."},{"key":"e_1_3_3_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_3_1_36_1","unstructured":"Huawei Wei Zejun Yang and Zhisheng Wang. 2024. Aniportrait: Audio-driven synthesis of photorealistic portrait animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.17694 (2024)."},{"key":"e_1_3_3_1_37_1","unstructured":"Mingwang Xu Hui Li Qingkun Su Hanlin Shang Liwei Zhang Ce Liu Jingdong Wang Luc Van\u00a0Gool Yao Yao and Siyu Zhu. 2024b. Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.08801 (2024)."},{"key":"e_1_3_3_1_38_1","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. 2024a. Vasa-1: Lifelike audio-driven talking faces generated in real time. Advances in Neural Information Processing Systems 37 (2024) 660\u2013684.","DOI":"10.52202\/079017-0021"},{"key":"e_1_3_3_1_39_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei Huan Lin Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jingren Zhou Junyang Lin Kai Dang Keming Lu Keqin Bao Kexin Yang Le Yu Mei Li Mingfeng Xue Pei Zhang Qin Zhu Rui Men Runji Lin Tianhao Li Tingyu Xia Xingzhang Ren Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yu Wan Yuqiong Liu Zeyu Cui Zhenru Zhang and Zihan Qiu. 2024. Qwen2.5 Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15115 (2024)."},{"key":"e_1_3_3_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"e_1_3_3_1_41_1","doi-asserted-by":"crossref","unstructured":"Chenxu Zhang Chao Wang Jianfeng Zhang Hongyi Xu Guoxian Song You Xie Linjie Luo Yapeng Tian Jiashi Feng and Xiaohu Guo. 2025. MagicTalk: Implicit and explicit correlation learning for diffusion-based emotional talking face generation. Computational Visual Media (2025).","DOI":"10.26599\/CVM.2025.9450491"},{"key":"e_1_3_3_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"e_1_3_3_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"e_1_3_3_1_44_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhao Xiaochen","year":"2025","unstructured":"Xiaochen Zhao, Hongyi Xu, Guoxian Song, You Xie, Chenxu Zhang, Xiu Li, Linjie Luo, Jinli Suo, and Yebin Liu. 2025. X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_3_1_45_1","doi-asserted-by":"crossref","unstructured":"Dingcheng Zhen Shunshun Yin Shiyang Qin Hou Yi Ziwei Zhang Siyuan Liu Gan Qi and Ming Tao. 2025. Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.18429 (2025).","DOI":"10.1109\/CVPR52734.2025.01963"},{"key":"e_1_3_3_1_46_1","unstructured":"Longtao Zheng Yifan Zhang Hanzhong Guo Jiachun Pan Zhenxiong Tan Jiahao Lu Chuanxin Tang Bo An and Shuicheng Yan. 2024. MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.04448 (2024)."},{"key":"e_1_3_3_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00295"},{"key":"e_1_3_3_1_48_1","doi-asserted-by":"crossref","unstructured":"Yang Zhou Xintong Han Eli Shechtman Jose Echevarria Evangelos Kalogerakis and Dingzeyu Li. 2020. Makelttalk: speaker-aware talking-head animation. ACM Transactions On Graphics (TOG) 39 6 (2020) 1\u201315.","DOI":"10.1145\/3414685.3417774"},{"key":"e_1_3_3_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:36:00Z","timestamp":1765251360000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":48,"alternative-id":["10.1145\/3757377.3763985","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763985","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}