{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T11:49:44Z","timestamp":1769514584241,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","funder":[{"name":"the National Natural Science Foundation of China","award":["62302167, U23A20343, 62222602, 62176092, 62476090, 72192821"],"award-info":[{"award-number":["62302167, U23A20343, 62222602, 62176092, 62476090, 72192821"]}]},{"name":"the Open Research Fund of Key Laboratory of Advanced Theory and Application in Statistics and Data Science-MOE, ECNU"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770934","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:06:16Z","timestamp":1765008376000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Wandering and feeling the Scenes: Body-Aware Diffusion for 3D Human Motion Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4481-5677","authenticated-orcid":false,"given":"Chong","family":"Zhang","sequence":"first","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-0953","authenticated-orcid":false,"given":"Jingyu","family":"Gong","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0284-9940","authenticated-orcid":false,"given":"Shaohui","family":"Lin","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9427-7665","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6905-4478","authenticated-orcid":false,"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"e_1_3_3_2_5_2","unstructured":"Angel\u00a0X Chang Thomas Funkhouser Leonidas Guibas Pat Hanrahan Qixing Huang Zimo Li Silvio Savarese Manolis Savva Shuran Song Hao Su et\u00a0al. 2015. Shapenet: An information-rich 3d model repository. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1512.03012 (2015)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"e_1_3_3_2_12_2","unstructured":"Fangzhou Hong Mingyuan Zhang Liang Pan Zhongang Cai Lei Yang and Ziwei Liu. 2022. Avatarclip: Zero-shot text-driven generation and animation of 3d avatars. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.08535 (2022)."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00886"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25206"},{"key":"e_1_3_3_2_18_2","first-page":"54","volume-title":"European Conference on Computer Vision","author":"Li Jiaman","year":"2024","unstructured":"Jiaman Li, Alexander Clegg, Roozbeh Mottaghi, Jiajun Wu, Xavier Puig, and C\u00a0Karen Liu. 2024. Controllable human-object interaction synthesis. In European Conference on Computer Vision. Springer, 54\u201372."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00053"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00462"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00061"},{"key":"e_1_3_3_2_24_2","first-page":"8162","volume-title":"International conference on machine learning","author":"Nichol Alexander\u00a0Quinn","year":"2021","unstructured":"Alexander\u00a0Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International conference on machine learning. PMLR, 8162\u20138171."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00149"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"e_1_3_3_2_30_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25308"},{"key":"e_1_3_3_2_32_2","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.02502 (2020)."},{"key":"e_1_3_3_2_33_2","unstructured":"Julian Straub Thomas Whelan Lingni Ma Yufan Chen Erik Wijmans Simon Green Jakob\u00a0J Engel Raul Mur-Artal Carl Ren Shobhit Verma et\u00a0al. 2019. The Replica dataset: A digital replica of indoor spaces. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.05797 (2019)."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"e_1_3_3_2_35_2","unstructured":"Guy Tevet Sigal Raab Brian Gordon Yonatan Shafir Daniel Cohen-Or and Amit\u00a0H Bermano. 2023. Human motion diffusion model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14916 (2023)."},{"key":"e_1_3_3_2_36_2","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_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"e_1_3_3_2_39_2","volume-title":"ICLR","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 ICLR."},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00074"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00623"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01983"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_18"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:09:41Z","timestamp":1765008581000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770934"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":43,"alternative-id":["10.1145\/3743093.3770934","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770934","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}