{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:17:36Z","timestamp":1771701456640,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0904700"],"award-info":[{"award-number":["2023YFF0904700"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20020484222"],"award-info":[{"award-number":["20020484222"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China","award":["62276031"],"award-info":[{"award-number":["62276031"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681657","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"224-232","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2972-8492","authenticated-orcid":false,"given":"Yiheng","family":"Huang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3161-3768","authenticated-orcid":false,"given":"Hui","family":"Yang","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence and Robotics, HKISI_CAS, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4360-7035","authenticated-orcid":false,"given":"Chuanchen","family":"Luo","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1579-2357","authenticated-orcid":false,"given":"Yuxi","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence and Robotics, HKISI_CAS, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4037-9900","authenticated-orcid":false,"given":"Shibiao","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2648-3875","authenticated-orcid":false,"given":"Zhaoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences & Centre for Artificial Intelligence and Robotics, HKISI_CAS, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3043-2122","authenticated-orcid":false,"given":"Man","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5276-0114","authenticated-orcid":false,"given":"Junran","family":"Peng","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A Survey on Generative Diffusion Model. arXiv preprint arXiv:2209.02646","author":"Cao Hanqun","year":"2022","unstructured":"Hanqun Cao, Cheng Tan, Zhangyang Gao, Yilun Xu, Guangyong Chen, Pheng-Ann Heng, and Stan Z Li. 2022. A Survey on Generative Diffusion Model. arXiv preprint arXiv:2209.02646 (2022)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"e_1_3_2_1_4_1","volume-title":"Diffusion Models Beat Gans on Image synthesis. Advances in neural information processing systems 34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion Models Beat Gans on Image synthesis. Advances in neural information processing systems 34 (2021), 8780--8794."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_2_1_6_1","volume-title":"GroundLink: A Dataset Unifying Human Body Movement and Ground Reaction Dynamics. In ACM SIGGRAPH Asia 2023 Conference Proceedings. 1--10","author":"Han Xingjian","year":"2023","unstructured":"Xingjian Han, Benjamin Senderling, Stanley To, Deepak Kumar, Emily Whiting, and Jun Saito. 2023. GroundLink: A Dataset Unifying Human Body Movement and Ground Reaction Dynamics. In ACM SIGGRAPH Asia 2023 Conference Proceedings. 1--10."},{"key":"e_1_3_2_1_7_1","volume-title":"Denoising Diffusion Probabilistic Models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_8_1","volume-title":"Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36","author":"Jiang Biao","year":"2024","unstructured":"Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, and Tao Chen. 2024. Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"DROP: Dynamics Responses from Human Motion Prior and Projective Dynamics. SIGGRAPH Asia","author":"Jiang Yifeng","year":"2023","unstructured":"Yifeng Jiang, Jungdam Won, Yuting Ye, and C Karen Liu. 2023. DROP: Dynamics Responses from Human Motion Prior and Projective Dynamics. SIGGRAPH Asia (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"GMD: Controllable Human Motion Synthesis via Guided Diffusion Models. arXiv preprint arXiv:2305.12577","author":"Karunratanakul Korrawe","year":"2023","unstructured":"Korrawe Karunratanakul, Konpat Preechakul, Supasorn Suwajanakorn, and Siyu Tang. 2023. GMD: Controllable Human Motion Synthesis via Guided Diffusion Models. arXiv preprint arXiv:2305.12577 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"e_1_3_2_1_12_1","volume-title":"DPM-Solver: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. arXiv preprint arXiv:2211.01095","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. DPM-Solver: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. arXiv preprint arXiv:2211.01095 (2022)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14635"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_15_1","volume-title":"The KIT Motion-Language Dataset. arXiv preprint arXiv:1607.03827","author":"Plappert Matthias","year":"2016","unstructured":"Matthias Plappert, Christian Mandery, and Tamim Asfour. 2016. The KIT Motion-Language Dataset. arXiv preprint arXiv:1607.03827 (2016)."},{"key":"e_1_3_2_1_16_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_18_1","volume-title":"Retentive Network: A Successor to Transformer for Large Language Models. arXiv preprint arXiv:2307.08621","author":"Sun Yutao","year":"2023","unstructured":"Yutao Sun, Li Dong, Shaohan Huang, Shuming Ma, Yuqing Xia, Jilong Xue, Jianyong Wang, and Furu Wei. 2023. Retentive Network: A Successor to Transformer for Large Language Models. arXiv preprint arXiv:2307.08621 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Human Motion Diffusion Model. arXiv preprint arXiv:2209.14916","author":"Tevet Guy","year":"2022","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H Bermano. 2022. Human Motion Diffusion Model. arXiv preprint arXiv:2209.14916 (2022)."},{"key":"e_1_3_2_1_20_1","volume-title":"EDGE: Editable Dance Generation From Music. arXiv preprint arXiv:2211.10658","author":"Tseng Jonathan","year":"2022","unstructured":"Jonathan Tseng, Rodrigo Castellon, and C Karen Liu. 2022. EDGE: Editable Dance Generation From Music. arXiv preprint arXiv:2211.10658 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"e_1_3_2_1_22_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Xie Yiming","year":"2024","unstructured":"Yiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, and Huaizu Jiang. 2024. OmniControl: Control Any Joint at Any Time for Human Motion Generation. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_23_1","volume-title":"Restart Sampling for Improving Generative Processes. arXiv preprint arXiv:2306.14878","author":"Xu Yilun","year":"2023","unstructured":"Yilun Xu, Mingyang Deng, Xiang Cheng, Yonglong Tian, Ziming Liu, and Tommi Jaakkola. 2023. Restart Sampling for Improving Generative Processes. arXiv preprint arXiv:2306.14878 (2023)."},{"key":"e_1_3_2_1_24_1","unstructured":"Ye Yuan and Kris Kitani. 2020. Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"e_1_3_2_1_26_1","volume-title":"T2m-gpt: Generating Human Motion from Textual Descriptions with Discrete Representations. arXiv preprint arXiv:2301.06052","author":"Zhang Jianrong","year":"2023","unstructured":"Jianrong Zhang, Yangsong Zhang, Xiaodong Cun, Shaoli Huang, Yong Zhang, Hongwei Zhao, Hongtao Lu, and Xi Shen. 2023. T2m-gpt: Generating Human Motion from Textual Descriptions with Discrete Representations. arXiv preprint arXiv:2301.06052 (2023)."},{"key":"e_1_3_2_1_27_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_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681657","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681657"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":28,"alternative-id":["10.1145\/3664647.3681657","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681657","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}