{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:06:11Z","timestamp":1765343171763,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755671","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"10437-10446","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FLAP: Fully-controllable Audio-driven Portrait Video Generation through 3D head conditioned diffusion model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0184-0664","authenticated-orcid":false,"given":"Lingzhou","family":"Mu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8102-9015","authenticated-orcid":false,"given":"Baiji","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology, guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7960-2588","authenticated-orcid":false,"given":"Ruonan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8658-5348","authenticated-orcid":false,"given":"Guiming","family":"Mo","sequence":"additional","affiliation":[{"name":"XVERSE Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3501-3034","authenticated-orcid":false,"given":"Jiawei","family":"Jin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5826-3765","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3925-0237","authenticated-orcid":false,"given":"Haozhi","family":"Huang","sequence":"additional","affiliation":[{"name":"XVERSE Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Egor Burkov Igor Pasechnik Artur Grigorev and Victor Lempitsky. 2020. Neural head reenactment with latent pose descriptors. 13786-13795.","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00283"},{"key":"e_1_3_2_1_6_1","volume-title":"Echomimic: Lifelike audio-driven portrait animations through editable landmark conditions. arXiv preprint arXiv:2407.08136","author":"Chen Zhiyuan","year":"2024","unstructured":"Zhiyuan Chen, Jiajiong Cao, Zhiquan Chen, Yuming Li, and Chenguang Ma. 2024a. Echomimic: Lifelike audio-driven portrait animations through editable landmark conditions. arXiv preprint arXiv:2407.08136 (2024)."},{"volume-title":"Workshop on Multi-view Lip-reading, ACCV.","author":"Chung J. S.","key":"e_1_3_2_1_7_1","unstructured":"J. S. Chung and A. Zisserman. 2016. Out of time: automated lip sync in the wild. In Workshop on Multi-view Lip-reading, ACCV."},{"key":"e_1_3_2_1_8_1","volume-title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation. arXiv preprint arXiv:2410.07718","author":"Cui Jiahao","year":"2024","unstructured":"Jiahao Cui, Hui Li, Yao Yao, Hao Zhu, Hanlin Shang, Kaihui Cheng, Hang Zhou, Siyu Zhu, and Jingdong Wang. 2024. Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation. arXiv preprint arXiv:2410.07718 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01967"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00707"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_15_1","volume-title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control. arXiv preprint arXiv:2407.03168","author":"Guo Jianzhu","year":"2024","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:2407.03168 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725","author":"Guo Yuwei","year":"2023","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2023. Animatediff: Animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221","author":"He Yingqing","year":"2022","unstructured":"Yingqing He, Tianyu Yang, Yong Zhang, Ying Shan, and Qifeng Chen. 2022. Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_19_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02108"},{"key":"e_1_3_2_1_21_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8153-8163","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. 8153-8163."},{"key":"e_1_3_2_1_23_1","volume-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency. arXiv preprint arXiv:2409.02634","author":"Jiang Jianwen","year":"2024","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:2409.02634 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"ControlNet: Improving Conditional Controls with Efficient Consistency Feedback. In European Conference on Computer Vision. Springer, 129-147","author":"Li Ming","year":"2025","unstructured":"Ming Li, Taojiannan Yang, Huafeng Kuang, Jie Wu, Zhaoning Wang, Xuefeng Xiao, and Chen Chen. 2025. ControlNet: Improving Conditional Controls with Efficient Consistency Feedback. In European Conference on Computer Vision. Springer, 129-147."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Yue Ma Hongyu Liu Hongfa Wang Heng Pan Yingqing He Junkun Yuan Ailing Zeng Chengfei Cai Heung-Yeung Shum Wei Liu et al. 2024b. Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation. arXiv preprint arXiv:2406.01900 (2024).","DOI":"10.1145\/3680528.3687587"},{"key":"e_1_3_2_1_29_1","first-page":"296","article-title":"A 3D face model for pose and illumination invariant face recognition. In 2009 sixth IEEE international conference on advanced video and signal based surveillance","author":"Paysan Pascal","year":"2009","unstructured":"Pascal Paysan, Reinhard Knothe, Brian Amberg, Sami Romdhani, and Thomas Vetter. 2009. A 3D face model for pose and illumination invariant face recognition. In 2009 sixth IEEE international conference on advanced video and signal based surveillance. Ieee, 296-301.","journal-title":"Ieee"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01919"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00241"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_37_1","volume-title":"ACM SIGGRAPH 2024 Conference Papers. 1-11","author":"Qin Hongwei","year":"2024","unstructured":"Xiaoyu Shi, Zhaoyang Huang, Fu-Yun Wang, Weikang Bian, Dasong Li, Yi Zhang, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin, et al., 2024. Motion-i2v: Consistent and controllable image-to-video generation with explicit motion modeling. In ACM SIGGRAPH 2024 Conference Papers. 1-11."},{"key":"e_1_3_2_1_38_1","volume-title":"First order motion model for image animation. Advances in neural information processing systems","author":"Siarohin Aliaksandr","year":"2019","unstructured":"Aliaksandr Siarohin, St\u00e9phane Lathuili\u00e8re, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019. First order motion model for image animation. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_39_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_23"},{"key":"e_1_3_2_1_43_1","volume-title":"Emo: Emote portrait alive-generating expressive portrait videos with audio2video diffusion model under weak conditions. arXiv preprint arXiv:2402.17485","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. arXiv preprint arXiv:2402.17485 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly.","author":"Unterthiner Thomas","year":"2018","unstructured":"Thomas Unterthiner, Sjoerd Van Steenkiste, Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)."},{"key":"e_1_3_2_1_45_1","volume-title":"V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation. arXiv preprint arXiv:2406.02511","author":"Wang Cong","year":"2024","unstructured":"Cong Wang, Kuan Tian, Jun Zhang, Yonghang Guan, Feng Luo, Fei Shen, Zhiwei Jiang, Qing Gu, Xiao Han, and Wei Yang. 2024c. V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation. arXiv preprint arXiv:2406.02511 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"e_1_3_2_1_47_1","volume-title":"Animatelcm: Accelerating the animation of personalized diffusion models and adapters with decoupled consistency learning. arXiv preprint arXiv:2402.00769","author":"Wang Fu-Yun","year":"2024","unstructured":"Fu-Yun Wang, Zhaoyang Huang, Xiaoyu Shi, Weikang Bian, Guanglu Song, Yu Liu, and Hongsheng Li. 2024b. Animatelcm: Accelerating the animation of personalized diffusion models and adapters with decoupled consistency learning. arXiv preprint arXiv:2402.00769 (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_2_1_49_1","volume-title":"InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation. arXiv preprint arXiv:2405.15758","author":"Wang Yuchi","year":"2024","unstructured":"Yuchi Wang, Junliang Guo, Jianhong Bai, Runyi Yu, Tianyu He, Xu Tan, Xu Sun, and Jiang Bian. 2024a. InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation. arXiv preprint arXiv:2405.15758 (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"Aniportrait: Audio-driven synthesis of photorealistic portrait animation. arXiv preprint arXiv:2403.17694","author":"Wei Huawei","year":"2024","unstructured":"Huawei Wei, Zejun Yang, and Zhisheng Wang. 2024. Aniportrait: Audio-driven synthesis of photorealistic portrait animation. arXiv preprint arXiv:2403.17694 (2024)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"e_1_3_2_1_54_1","volume-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation. arXiv preprint arXiv:2406.08801","author":"Xu Mingwang","year":"2024","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 preprint arXiv:2406.08801 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"Vasa-1: Lifelike audio-driven talking faces generated in real time. arXiv preprint arXiv:2404.10667","author":"Xu Sicheng","year":"2024","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. arXiv preprint arXiv:2404.10667 (2024)."},{"key":"e_1_3_2_1_56_1","unstructured":"Shurong Yang Huadong Li Juhao Wu Minhao Jing Linze Li Renhe Ji Jiajun Liang Haoqiang Fan and Jin Wang. 2024. MegActor-\u03a3: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer. arXiv:2408.14975 [cs.CV] https:\/\/arxiv.org\/abs\/2408.14975"},{"key":"e_1_3_2_1_57_1","volume-title":"Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis. arXiv preprint arXiv:2301.13430","author":"Ye Zhenhui","year":"2023","unstructured":"Zhenhui Ye, Ziyue Jiang, Yi Ren, Jinglin Liu, Jinzheng He, and Zhou Zhao. 2023. Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis. arXiv preprint arXiv:2301.13430 (2023)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"e_1_3_2_1_60_1","volume-title":"Controlvideo: Training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077","author":"Zhang Yabo","year":"2023","unstructured":"Yabo Zhang, Yuxiang Wei, Dongsheng Jiang, Xiaopeng Zhang, Wangmeng Zuo, and Qi Tian. 2023c. Controlvideo: Training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3414685.3417774","article-title":"Makelttalk: speaker-aware talking-head animation","volume":"39","author":"Zhou Yang","year":"2020","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), Vol. 39, 6 (2020), 1-15.","journal-title":"ACM Transactions On Graphics (TOG)"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_15"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:03:03Z","timestamp":1765342983000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755671"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":63,"alternative-id":["10.1145\/3746027.3755671","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755671","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}