{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:57:50Z","timestamp":1781539070110,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Science and Technology Development Fund, Macau SAR","award":["0193\/2023\/RIA3"],"award-info":[{"award-number":["0193\/2023\/RIA3"]}]},{"name":"Science and Technology Development Fund, Macau SAR","award":["0079\/2025\/AFJ"],"award-info":[{"award-number":["0079\/2025\/AFJ"]}]},{"name":"University of Macau","award":["MYRG-GRG2024-00065-FST-UMDF"],"award-info":[{"award-number":["MYRG-GRG2024-00065-FST-UMDF"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810854","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"2314-2322","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Decoupling Vocal and Rhythmic Conditioning for Music-Driven Singing Avatar Animation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9336-8123","authenticated-orcid":false,"given":"Yiguo","family":"Jiang","sequence":"first","affiliation":[{"name":"University of Macau, Macau, Macao"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3607-2236","authenticated-orcid":false,"given":"Xiaodong","family":"Cun","sequence":"additional","affiliation":[{"name":"Great Bay University, Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2957-2792","authenticated-orcid":false,"given":"Chenbin","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, Macao"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6270-2698","authenticated-orcid":false,"given":"Jian","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, Macao"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1788-3746","authenticated-orcid":false,"given":"Chi-Man","family":"Pun","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, Macao"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"e_1_3_3_1_5_2","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:https:\/\/arXiv.org\/abs\/2410.07718 (2024)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"e_1_3_3_1_8_2","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:https:\/\/arXiv.org\/abs\/2307.04725 (2023)."},{"key":"e_1_3_3_1_9_2","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 30 (2017)."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Fa-Ting Hong Li Shen and Dan Xu. 2023. DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 5 (2023) 2997\u20133012.","DOI":"10.1109\/TPAMI.2023.3339964"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410700.3425435"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"e_1_3_3_1_13_2","unstructured":"Yiguo Jiang Xiaodong Cun Yong Zhang Yudian Zheng Fan Tang and Chi-Man Pun. 2025. EmoCAST: Emotional Talking Portrait via Emotive Text Description. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.20615 (2025)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Sunjin Jung Yeongho Seol Kwanggyoon Seo Hyeonho Na Seonghyeon Kim Vanessa Tan and Jun yong Noh. 2024. Speed-Aware Audio-Driven Speech Animation using Adaptive Windows. ACM Transactions on Graphics 44 (2024) 1 \u2013 14.","DOI":"10.1145\/3691341"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Pengfei Liu Wenjin Deng Hengda Li Jintai Wang Yinglin Zheng Yiwei Ding Xiaohu Guo and Ming Zeng. 2024. MusicFace: Music-driven expressive singing face synthesis. Computational Visual Media 10 1 (2024) 119\u2013136.","DOI":"10.1007\/s41095-023-0343-7"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02104"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687925"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25280"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Niranjan\u00a0D. Narvekar and Lina\u00a0J. Karam. 2011. A No-Reference Image Blur Metric Based on the Cumulative Probability of Blur Detection (CPBD). IEEE Transactions on Image Processing 20 9 (2011) 2678\u20132683. 10.1109\/TIP.2011.2131660","DOI":"10.1109\/TIP.2011.2131660"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Steffen Schneider Alexei Baevski Ronan Collobert and Michael Auli. 2019. wav2vec: Unsupervised pre-training for speech recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.05862 (2019).","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Kwanggyoon Seo Rene Culaway Byeong-Uk Lee and Jun yong Noh. 2025. Emotion Manipulation for Talking-Head Videos via Facial Landmarks. ACM Transactions on Graphics 45 (2025) 1 \u2013 15.","DOI":"10.1145\/3770576"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Zhicheng Sheng Liqiang Nie Meng Liu Yinwei Wei and Zan Gao. 2023. Toward fine-grained talking face generation. IEEE Transactions on Image Processing 32 (2023) 5794\u20135807.","DOI":"10.1109\/TIP.2023.3323452"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"e_1_3_3_1_29_2","first-page":"398","volume-title":"European Conference on Computer Vision","author":"Tan Shuai","year":"2024","unstructured":"Shuai Tan, Bin Ji, Mengxiao Bi, and Ye Pan. 2024. Edtalk: Efficient disentanglement for emotional talking head synthesis. In European Conference on Computer Vision. Springer, 398\u2013416."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Anni Tang Tianyu He Xu Tan Jun Ling Runnan Li Sheng Zhao Jiang Bian and Li Song. 2024. Memories are one-to-many mapping alleviators in talking face generation. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 12 (2024) 8758\u20138770.","DOI":"10.1109\/TPAMI.2024.3409380"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Muyu Wang Sanyuan Zhao Xingping Dong and Jianbing Shen. 2024. High-Fidelity and High-Efficiency Talking Portrait Synthesis With Detail-Aware Neural Radiance Fields. IEEE Transactions on Visualization and Computer Graphics (2024).","DOI":"10.1109\/TVCG.2024.3488960"},{"key":"e_1_3_3_1_34_2","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_35_2","doi-asserted-by":"crossref","unstructured":"Sijing Wu Yunhao Li Weitian Zhang Jun Jia Yucheng Zhu Yichao Yan Guangtao Zhai and Xiaokang Yang. 2026. SingingHead: A Large-Scale 4D Dataset for Singing Head Animation. IEEE Transactions on Multimedia 28 (2026) 700\u2013714.","DOI":"10.1109\/TMM.2025.3623560"},{"key":"e_1_3_3_1_36_2","unstructured":"Mingwang Xu Hui Li Qingkun Su Hanlin Shang Liwei Zhang Ce Liu Jingdong Wang Yao Yao and Siyu Zhu. 2024. 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_37_2","unstructured":"Hu Ye Jun Zhang Sibo Liu Xiao Han and Wei Yang. 2023. Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.06721 (2023)."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Haiming Zhang Zhihao Yuan Chaoda Zheng Xu Yan Baoyuan Wang Guanbin Li Song Wu Shuguang Cui and Zhen Li. 2025. Gsmoothface: Generalized smooth talking face generation via fine grained 3d face guidance. IEEE Transactions on Visualization and Computer Graphics (2025).","DOI":"10.1109\/TVCG.2025.3566382"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"e_1_3_3_1_42_2","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"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:44:07Z","timestamp":1781538247000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":41,"alternative-id":["10.1145\/3805622.3810854","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810854","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}