{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:58:17Z","timestamp":1776931097007,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"name":"Natural Science Foundation of Shanghai","award":["24ZR1407200"],"award-info":[{"award-number":["24ZR1407200"]}]},{"name":"Shanghai Oriental Talents Project","award":["QNKJ2024060"],"award-info":[{"award-number":["QNKJ2024060"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763914","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4263-4842","authenticated-orcid":false,"given":"Jiahao","family":"Cui","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5291-0364","authenticated-orcid":false,"given":"Baoyou","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5842-6941","authenticated-orcid":false,"given":"Mingwang","family":"Xu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9382-6085","authenticated-orcid":false,"given":"Hanlin","family":"Shang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5680-6345","authenticated-orcid":false,"given":"Yuxuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6977-9989","authenticated-orcid":false,"given":"Qinkun","family":"Su","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-9102","authenticated-orcid":false,"given":"Zilong","family":"Dong","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9866-4291","authenticated-orcid":false,"given":"Yao","family":"Yao","sequence":"additional","affiliation":[{"name":"Nanjing University, SuZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4888-4445","authenticated-orcid":false,"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6852-0888","authenticated-orcid":false,"given":"Siyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China and Shanghai Innovative Institute, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Daechul Ahn Yura Choi Youngjae Yu Dongyeop Kang and Jonghyun Choi. 2024. Tuning large multimodal models for videos using reinforcement learning from ai feedback. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.03746 (2024)."},{"key":"e_1_3_3_2_3_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et\u00a0al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems 35 (2022) 23716\u201323736."},{"key":"e_1_3_3_2_4_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_2_5_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts Varun Jampani and Robin Rombach. 2023. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.15127 (2023)."},{"key":"e_1_3_3_2_6_1","unstructured":"Zhiyuan Chen Jiajiong Cao Zhiquan Chen Yuming Li and Chenguang Ma. 2024. Echomimic: Lifelike audio-driven portrait animations through editable landmark conditions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.08136 (2024)."},{"key":"e_1_3_3_2_7_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. 2024. 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_2_8_1","volume-title":"Forty-first international conference on machine learning","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et\u00a0al. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning."},{"key":"e_1_3_3_2_9_1","unstructured":"Jianzhu Guo Dingyun Zhang Xiaoqiang Liu Zhizhou Zhong Yuan Zhang Pengfei Wan and Di Zhang. 2024. Liveportrait: Efficient portrait animation with stitching and retargeting control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.03168 (2024)."},{"key":"e_1_3_3_2_10_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_2_11_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_2_12_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_2_13_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_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_15_1","first-page":"19730","volume-title":"International conference on machine learning","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730\u201319742."},{"key":"e_1_3_3_2_16_1","unstructured":"Rui Li Xiaohan Wang Yuhui Zhang Zeyu Wang and Serena Yeung-Levy. 2025. Temporal Preference Optimization for Long-Form Video Understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.13919 (2025)."},{"key":"e_1_3_3_2_17_1","unstructured":"Gaojie Lin Jianwen Jiang Chao Liang Tianyun Zhong Jiaqi Yang and Yanbo Zheng. 2024. CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.01876 (2024)."},{"key":"e_1_3_3_2_18_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_2_19_1","unstructured":"Jie Liu Gongye Liu Jiajun Liang Ziyang Yuan Xiaokun Liu Mingwu Zheng Xiele Wu Qiulin Wang Wenyu Qin Menghan Xia et\u00a0al. 2025. Improving Video Generation with Human Feedback. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.13918 (2025)."},{"key":"e_1_3_3_2_20_1","unstructured":"Runtao Liu Haoyu Wu Zheng Ziqiang Chen Wei Yingqing He Renjie Pi and Qifeng Chen. 2024b. Videodpo: Omni-preference alignment for video diffusion generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.14167 (2024)."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Yue Liu Yunjie Tian Yuzhong Zhao Hongtian Yu Lingxi Xie Yaowei Wang Qixiang Ye Jianbin Jiao and Yunfan Liu. 2024a. Vmamba: Visual state space model. Advances in neural information processing systems 37 (2024) 103031\u2013103063.","DOI":"10.52202\/079017-3273"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"e_1_3_3_2_23_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 (2023)."},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"crossref","unstructured":"Rang Meng Xingyu Zhang Yuming Li and Chenguang Ma. 2024. EchoMimicV2: Towards Striking Simplified and Semi-Body Human Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.10061 (2024).","DOI":"10.1109\/CVPR52734.2025.00516"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"e_1_3_3_2_27_1","unstructured":"Xusen Sun Longhao Zhang Hao Zhu Peng Zhang Bang Zhang Xinya Ji Kangneng Zhou Daiheng Gao Liefeng Bo and Xun Cao. 2023b. 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_2_28_1","unstructured":"Zhiqing Sun Sheng Shen Shengcao Cao Haotian Liu Chunyuan Li Yikang Shen Chuang Gan Liang-Yan Gui Yu-Xiong Wang Yiming Yang et\u00a0al. 2023a. Aligning large multimodal models with factually augmented rlhf. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.14525 (2023)."},{"key":"e_1_3_3_2_29_1","first-page":"244","volume-title":"European Conference on Computer Vision","author":"Tian Linrui","year":"2024","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. In European Conference on Computer Vision. Springer, 244\u2013260."},{"key":"e_1_3_3_2_30_1","unstructured":"Yu Tian Jian Ren Menglei Chai Kyle Olszewski Xi Peng Dimitris\u00a0N Metaxas and Sergey Tulyakov. 2021. A good image generator is what you need for high-resolution video synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.15069 (2021)."},{"key":"e_1_3_3_2_31_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"e_1_3_3_2_33_1","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 preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20314 (2025)."},{"key":"e_1_3_3_2_34_1","unstructured":"Cong Wang Jiaxi Gu Panwen Hu Haoyu Zhao Yuanfan Guo Jianhua Han Hang Xu and Xiaodan Liang. 2024. Easycontrol: Transfer controlnet to video diffusion for controllable generation and interpolation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.13005 (2024)."},{"key":"e_1_3_3_2_35_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_2_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_2_37_1","unstructured":"Mingwang Xu Hui Li Qingkun Su Hanlin Shang Liwei Zhang Ce Liu Jingdong Wang Yao Yao and Siyu zhu. 2024b. Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation. arxiv:https:\/\/arXiv.org\/abs\/2406.08801\u00a0[cs.CV]"},{"key":"e_1_3_3_2_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_2_39_1","unstructured":"Chenxu Zhang Chao Wang Jianfeng Zhang Hongyi Xu Guoxian Song You Xie Linjie Luo Yapeng Tian Xiaohu Guo and Jiashi Feng. 2023c. Dream-talk: Diffusion-based realistic emotional audio-driven method for single image talking face generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.13578 (2023)."},{"key":"e_1_3_3_2_40_1","unstructured":"Jiacheng Zhang Jie Wu Weifeng Chen Yatai Ji Xuefeng Xiao Weilin Huang and Kai Han. 2024c. Onlinevpo: Align video diffusion model with online video-centric preference optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15159 (2024)."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_42_1","unstructured":"Ruohong Zhang Liangke Gui Zhiqing Sun Yihao Feng Keyang Xu Yuanhan Zhang Di Fu Chunyuan Li Alexander Hauptmann Yonatan Bisk et\u00a0al. 2024b. Direct preference optimization of video large multimodal models from language model reward. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.01258 (2024)."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"e_1_3_3_2_44_1","unstructured":"Yuang Zhang Jiaxi Gu Li-Wen Wang Han Wang Junqi Cheng Yuefeng Zhu and Fangyuan Zou. 2024a. Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.19680 (2024)."},{"key":"e_1_3_3_2_45_1","unstructured":"Shenhao Zhu Junming\u00a0Leo Chen Zuozhuo Dai Yinghui Xu Xun Cao Yao Yao Hao Zhu and Siyu Zhu. 2024. Champ: Controllable and consistent human image animation with 3d parametric guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.14781 (2024)."}],"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\/3757377.3763914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:30:50Z","timestamp":1765251050000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":44,"alternative-id":["10.1145\/3757377.3763914","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763914","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"}}]}}