{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:18:07Z","timestamp":1777655887424,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612276","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"2817-2828","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["GraMMaR: Ground-aware Motion Model for 3D Human Motion Reconstruction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0887-9633","authenticated-orcid":false,"given":"Sihan","family":"Ma","sequence":"first","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8750-3505","authenticated-orcid":false,"given":"Qiong","family":"Cao","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8669-2009","authenticated-orcid":false,"given":"Hongwei","family":"Yi","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.464"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00236"},{"key":"e_1_3_2_2_4_1","volume-title":"A survey of full-body motion reconstruction in immersive virtual reality applications","author":"Caserman Polona","year":"2019","unstructured":"Polona Caserman, Augusto Garcia-Agundez, and Stefan G\u00f6bel. 2019. A survey of full-body motion reconstruction in immersive virtual reality applications. IEEE transactions on visualization and computer graphics, Vol. 26, 10 (2019), 3089--3108."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459932","article-title":"Choreomaster: choreography-oriented music-driven dance synthesis","volume":"40","author":"Chen Kang","year":"2021","unstructured":"Kang Chen, Zhipeng Tan, Jin Lei, Song-Hai Zhang, Yuan-Chen Guo, Weidong Zhang, and Shi-Min Hu. 2021. Choreomaster: choreography-oriented music-driven dance synthesis. ACM Transactions on Graphics (TOG), Vol. 40, 4 (2021), 1--13.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_41"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01214"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.447"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299005"},{"key":"e_1_3_2_2_11_1","volume-title":"Kwang In Kim, and Christian Theobalt","author":"Elhayek Ahmed","year":"2015","unstructured":"Ahmed Elhayek, Carsten Stoll, Kwang In Kim, and Christian Theobalt. 2015b. Outdoor human motion capture by simultaneous optimization of pose and camera parameters. In Computer Graphics Forum, Vol. 34. Wiley Online Library, 86--98."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01284"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01074"},{"key":"e_1_3_2_2_14_1","volume-title":"International Conference on Computer Vision. 2282--2292","author":"Hassan Mohamed","unstructured":"Mohamed Hassan, Vasileios Choutas, Dimitrios Tzionas, and Michael J. Black. 2019. Resolving 3D Human Pose Ambiguities with 3D Scene Constraints. In International Conference on Computer Vision. 2282--2292. https:\/\/prox.is.tue.mpg.de"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00631"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). 13274--13285","author":"Huang Chun-Hao P.","unstructured":"Chun-Hao P. Huang, Hongwei Yi, Markus H\u00f6schle, Matvey Safroshkin, Tsvetelina Alexiadis, Senya Polikovsky, Daniel Scharstein, and Michael J. Black. 2022b. Capturing and Inferring Dense Full-Body Human-Scene Contact. In Proceedings IEEE\/CVF Conf. on Computer Vision and Pattern Recognition (CVPR). 13274--13285."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00018"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"e_1_3_2_2_19_1","volume-title":"Proceedings International Conference on Computer Vision (ICCV). IEEE, 11127--11137","author":"Kocabas Muhammed","unstructured":"Muhammed Kocabas, Chun-Hao P. Huang, Otmar Hilliges, and Michael J. Black. 2021. PARE: Part Attention Regressor for 3D Human Body Estimation. In Proceedings International Conference on Computer Vision (ICCV). IEEE, 11127--11137."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00800"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01243"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"e_1_3_2_2_24_1","unstructured":"Ruilong Li Shan Yang David A. Ross and Angjoo Kanazawa. 2021b. Learn to Dance with AIST: Music Conditioned 3D Dance Generation. arxiv: 2101.08779 [cs.CV]"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_2_28_1","first-page":"25019","article-title":"Dynamics-regulated kinematic policy for egocentric pose estimation","volume":"34","author":"Luo Zhengyi","year":"2021","unstructured":"Zhengyi Luo, Ryo Hachiuma, Ye Yuan, and Kris Kitani. 2021. Dynamics-regulated kinematic policy for egocentric pose estimation. Advances in Neural Information Processing Systems, Vol. 34 (2021), 25019--25032.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_29_1","volume-title":"International Conference on Computer Vision. 5442--5451","author":"Mahmood Naureen","unstructured":"Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, and Michael J. Black. 2019. AMASS: Archive of Motion Capture as Surface Shapes. In International Conference on Computer Vision. 5442--5451."},{"key":"e_1_3_2_2_30_1","volume-title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning.","author":"Makoviychuk Viktor","year":"2021","unstructured":"Viktor Makoviychuk, Lukasz Wawrzyniak, Yunrong Guo, Michelle Lu, Kier Storey, Miles Macklin, David Hoeller, Nikita Rudin, Arthur Allshire, Ankur Handa, and Gavriel State. 2021. Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392410"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073596"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3068736"},{"key":"e_1_3_2_2_34_1","volume-title":"Mitra","author":"Monszpart Aron","year":"2019","unstructured":"Aron Monszpart, Paul Guerrero, Duygu Ceylan, Ersin Yumer, and Niloy J. Mitra. 2019. iMapper: Interaction-guided Scene Mapping from Monocular Videos. ACM SIGGRAPH (2019)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300340"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2020.04.093"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_5"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459825"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417877"},{"key":"e_1_3_2_2_42_1","volume-title":"Learning structured output representation using deep conditional generative models. Advances in neural information processing systems","author":"Sohn Kihyuk","year":"2015","unstructured":"Kihyuk Sohn, Honglak Lee, and Xinchen Yan. 2015. Learning structured output representation using deep conditional generative models. Advances in neural information processing systems, Vol. 28 (2015)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2981989"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00457"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02119"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01133"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"e_1_3_2_2_49_1","first-page":"38571","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","volume":"35","author":"Xu Yufei","year":"2022","unstructured":"Yufei Xu, Jing Zhang, Qiming Zhang, and Dacheng Tao. 2022a. Vitpose: Simple vision transformer baselines for human pose estimation. Advances in Neural Information Processing Systems, Vol. 35 (2022), 38571--38584.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_50_1","volume-title":"Vitpose: Vision transformer foundation model for generic body pose estimation. arXiv preprint arXiv:2212.04246","author":"Xu Yufei","year":"2022","unstructured":"Yufei Xu, Jing Zhang, Qiming Zhang, and Dacheng Tao. 2022b. Vitpose: Vision transformer foundation model for generic body pose estimation. arXiv preprint arXiv:2212.04246 (2022)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00708"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3039359"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01115"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_41"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00070"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612276","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:08:01Z","timestamp":1755821281000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":56,"alternative-id":["10.1145\/3581783.3612276","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612276","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}