{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T23:24:22Z","timestamp":1783639462505,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T00:00:00Z","timestamp":1720828800000},"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":[[2024,7,13]]},"DOI":"10.1145\/3641519.3657440","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T10:39:28Z","timestamp":1720780768000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Taming Diffusion Probabilistic Models for Character Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7122-5207","authenticated-orcid":false,"given":"Rui","family":"Chen","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5180-600X","authenticated-orcid":false,"given":"Mingyi","family":"Shi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1445-3196","authenticated-orcid":false,"given":"Shaoli","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4506-6973","authenticated-orcid":false,"given":"Ping","family":"Tan","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2729-5860","authenticated-orcid":false,"given":"Taku","family":"Komura","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0158-9469","authenticated-orcid":false,"given":"Xuelin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"e_1_3_2_2_2_1","volume-title":"ONNX: Open Neural Network Exchange. https:\/\/github.com\/onnx\/onnx.","author":"Bai Junjie","year":"2019","unstructured":"Junjie Bai, Fang Lu, Ke Zhang, 2019. ONNX: Open Neural Network Exchange. https:\/\/github.com\/onnx\/onnx."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356536"},{"key":"e_1_3_2_2_4_1","unstructured":"Michael B\u00fcttner and Simon Clavet. 2015. Motion Matching - The Road to Next Gen Animation.https:\/\/www.youtube.com\/watch?v=z_wpgHFSWss&t=658s"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480512"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Zhiyang Dou Xuelin Chen Qingnan Fan Taku Komura and Wenping Wang. 2023. C\u00b7 ase: Learning conditional adversarial skill embeddings for physics-based characters. In SIGGRAPH Asia. 1\u201311.","DOI":"10.1145\/3610548.3618205"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480527"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417836"},{"key":"e_1_3_2_2_11_1","volume-title":"Classifier-Free Diffusion Guidance. ArXiv abs\/2207.12598","author":"Jonathan Ho.","year":"2022","unstructured":"Jonathan Ho. 2022. Classifier-Free Diffusion Guidance. ArXiv abs\/2207.12598 (2022)."},{"key":"e_1_3_2_2_12_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS), H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems (NeurIPS), H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., 6840\u20136851. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_2_2_13_1","volume-title":"Learned motion matching. 39, 4","author":"Holden Daniel","year":"2020","unstructured":"Daniel Holden, Oussama Kanoun, Maksym Perepichka, and Tiberiu Popa. 2020. Learned motion matching. 39, 4 (2020), 53\u20131."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073663"},{"key":"e_1_3_2_2_15_1","volume-title":"MotionGPT: Human Motion as a Foreign Language. arXiv preprint arXiv:2306.14795","author":"Jiang Biao","year":"2023","unstructured":"Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, and Tao Chen. 2023. MotionGPT: Human Motion as a Foreign Language. arXiv preprint arXiv:2306.14795 (2023)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Yongjoon Lee Kevin Wampler Gilbert Bernstein Jovan Popovi\u0107 and Zoran Popovi\u0107. 2010. Motion fields for interactive character locomotion. (2010) 1\u20138.","DOI":"10.1145\/1882261.1866160"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392422"},{"key":"e_1_3_2_2_20_1","volume-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378","author":"Luo Simian","year":"2023","unstructured":"Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao. 2023. Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3522618"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"e_1_3_2_2_23_1","volume-title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning (ICML). PMLR, 16784\u201316804","author":"Nichol Alexander\u00a0Quinn","year":"2022","unstructured":"Alexander\u00a0Quinn Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob Mcgrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. In International Conference on Machine Learning (ICML). PMLR, 16784\u201316804."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"e_1_3_2_2_27_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. arxiv:2204.06125\u00a0[cs.CV]"},{"key":"e_1_3_2_2_28_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 8821\u20138831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning (ICML). PMLR, 8821\u20138831."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_30_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily\u00a0L Denton, Kamyar Ghasemipour, Raphael Gontijo\u00a0Lopes, Burcu Karagol\u00a0Ayan, Tim Salimans, 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems (NeurIPS) 35 (2022), 36479\u201336494.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_2_31_1","volume-title":"Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418","author":"Shafir Yonatan","year":"2023","unstructured":"Yonatan Shafir, Guy Tevet, Roy Kapon, and Amit\u00a0H Bermano. 2023. Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418 (2023)."},{"key":"e_1_3_2_2_32_1","volume-title":"Controllable Motion Diffusion Model. arXiv preprint arXiv:2306.00416","author":"Shi Yi","year":"2023","unstructured":"Yi Shi, Jingbo Wang, Xuekun Jiang, and Bo Dai. 2023. Controllable Motion Diffusion Model. arXiv preprint arXiv:2306.00416 (2023)."},{"key":"e_1_3_2_2_33_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_2_34_1","volume-title":"Consistency models. arXiv preprint arXiv:2303.01469","author":"Song Yang","year":"2023","unstructured":"Yang Song, Prafulla Dhariwal, Mark Chen, and Ilya Sutskever. 2023. Consistency models. arXiv preprint arXiv:2303.01469 (2023)."},{"key":"e_1_3_2_2_35_1","unstructured":"Sebastian Starke. 2024. AI4Animation. https:\/\/github.com\/sebastianstarke\/AI4Animation."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530178"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392450"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591541"},{"key":"e_1_3_2_2_39_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tevet Guy","year":"2023","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit\u00a0H Bermano. 2023. Human motion diffusion model. International Conference on Learning Representations (ICLR) (2023)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392381"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530067"},{"key":"e_1_3_2_2_43_1","volume-title":"Omnicontrol: Control any joint at any time for human motion generation. arXiv preprint arXiv:2310.08580","author":"Xie Yiming","year":"2023","unstructured":"Yiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, and Huaizu Jiang. 2023. Omnicontrol: Control any joint at any time for human motion generation. arXiv preprint arXiv:2310.08580 (2023)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555434"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201366"},{"key":"e_1_3_2_2_47_1","volume-title":"Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001","author":"Zhang Mingyuan","year":"2022","unstructured":"Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, and Ziwei Liu. 2022. Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"}],"event":{"name":"SIGGRAPH '24: Special Interest Group on Computer Graphics and Interactive Techniques Conference","location":"Denver CO USA","acronym":"SIGGRAPH '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657440","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641519.3657440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:36Z","timestamp":1750295376000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641519.3657440"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,13]]},"references-count":48,"alternative-id":["10.1145\/3641519.3657440","10.1145\/3641519"],"URL":"https:\/\/doi.org\/10.1145\/3641519.3657440","relation":{},"subject":[],"published":{"date-parts":[[2024,7,13]]},"assertion":[{"value":"2024-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}