{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T12:53:02Z","timestamp":1776084782814,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1145\/3680528.3687565","type":"proceedings-article","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T08:14:37Z","timestamp":1733213677000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["World-Grounded Human Motion Recovery via Gravity-View Coordinates"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7232-793X","authenticated-orcid":false,"given":"Zehong","family":"Shen","sequence":"first","affiliation":[{"name":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7076-1321","authenticated-orcid":false,"given":"Huaijin","family":"Pi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4927-2189","authenticated-orcid":false,"given":"Yan","family":"Xia","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0836-1533","authenticated-orcid":false,"given":"Zhi","family":"Cen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6546-4525","authenticated-orcid":false,"given":"Sida","family":"Peng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5350-0313","authenticated-orcid":false,"given":"Zechen","family":"Hu","sequence":"additional","affiliation":[{"name":"Deep Glint, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2662-0334","authenticated-orcid":false,"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6798-0336","authenticated-orcid":false,"given":"Ruizhen","family":"Hu","sequence":"additional","affiliation":[{"name":"Shenzhen University (SZU), Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1926-5597","authenticated-orcid":false,"given":"Xiaowei","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of CAD & CG, Zhejiang University, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"e_1_3_3_1_2_1","doi-asserted-by":"crossref","unstructured":"Andreas Aristidou and Joan Lasenby. 2011. FABRIK: A fast iterative solver for the Inverse Kinematics problem. Graphical Models 73 5 (2011) 243\u2013260.","DOI":"10.1016\/j.gmod.2011.05.003"},{"key":"e_1_3_3_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"e_1_3_3_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"e_1_3_3_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"e_1_3_3_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"e_1_3_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_3_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801984"},{"key":"e_1_3_3_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01292"},{"key":"e_1_3_3_1_10_1","doi-asserted-by":"crossref","unstructured":"Catalin Ionescu Dragos Papava Vlad Olaru and Cristian Sminchisescu. 2014. Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments. IEEE Transactions on Pattern Analysis and Machine Intelligence 36 7 (jul 2014) 1325\u20131339.","DOI":"10.1109\/TPAMI.2013.248"},{"key":"e_1_3_3_1_11_1","volume-title":"Ultralytics YOLOv8","author":"Jocher Glenn","year":"2023","unstructured":"Glenn Jocher, Ayush Chaurasia, and Jing Qiu. 2023. Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_3_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"e_1_3_3_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00576"},{"key":"e_1_3_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01345"},{"key":"e_1_3_3_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"e_1_3_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"e_1_3_3_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01085"},{"key":"e_1_3_3_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00103"},{"key":"e_1_3_3_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00234"},{"key":"e_1_3_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01243"},{"key":"e_1_3_3_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_28"},{"key":"e_1_3_3_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"e_1_3_3_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"e_1_3_3_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"e_1_3_3_1_25_1","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV)","author":"Luo Zhengyi","year":"2020","unstructured":"Zhengyi Luo, S.\u00a0Alireza Golestaneh, and Kris\u00a0M. Kitani. 2020. 3D Human Motion Estimation via Motion Compression and Refinement. In Proceedings of the Asian Conference on Computer Vision (ACCV)."},{"key":"e_1_3_3_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"e_1_3_3_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_1_28_1","volume-title":"International Conference on Learning Representations","author":"Press Ofir","year":"2022","unstructured":"Ofir Press, Noah Smith, and Mike Lewis. 2022. Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=R8sQPpGCv0"},{"key":"e_1_3_3_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"e_1_3_3_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00858"},{"key":"e_1_3_3_1_31_1","doi-asserted-by":"crossref","unstructured":"Mingyi Shi Kfir Aberman Andreas Aristidou Taku Komura Dani Lischinski Daniel Cohen-Or and Baoquan Chen. 2020. Motionet: 3d human motion reconstruction from monocular video with skeleton consistency. Acm transactions on graphics (tog) 40 1 (2020) 1\u201315.","DOI":"10.1145\/3407659"},{"key":"e_1_3_3_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00202"},{"key":"e_1_3_3_1_33_1","doi-asserted-by":"crossref","unstructured":"Sebastian Starke He Zhang Taku Komura and Jun Saito. 2019. Neural state machine for character-scene interactions. ACM Transactions on Graphics 38 6 (2019) 178.","DOI":"10.1145\/3355089.3356505"},{"key":"e_1_3_3_1_34_1","doi-asserted-by":"crossref","unstructured":"Jianlin Su Murtadha Ahmed Yu Lu Shengfeng Pan Wen Bo and Yunfeng Liu. 2024. Roformer: Enhanced transformer with rotary position embedding. Neurocomputing 568 (2024) 127063.","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_3_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00855"},{"key":"e_1_3_3_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00545"},{"key":"e_1_3_3_1_37_1","unstructured":"Zachary Teed and Jia Deng. 2021. DROID-SLAM: Deep Visual SLAM for Monocular Stereo and RGB-D Cameras. Advances in neural information processing systems (2021)."},{"key":"e_1_3_3_1_38_1","unstructured":"Zachary Teed Lahav Lipson and Jia Deng. 2024. Deep patch visual odometry. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_39_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet Guy","year":"2023","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yoni Shafir, Daniel Cohen-or, and Amit\u00a0Haim Bermano. 2023. Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu"},{"key":"e_1_3_3_1_40_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141\u00a0ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems , I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf https:\/\/dl.acm.org\/doi\/10.5555\/3295222.3295349"},{"key":"e_1_3_3_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"e_1_3_3_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01279"},{"key":"e_1_3_3_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01346"},{"key":"e_1_3_3_1_44_1","unstructured":"Yufu Wang Ziyun Wang Lingjie Liu and Kostas Daniilidis. 2024. TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.17346 (2024)."},{"key":"e_1_3_3_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01286"},{"key":"e_1_3_3_1_46_1","volume-title":"Advances in Neural Information Processing Systems","author":"Xu Yufei","year":"2022","unstructured":"Yufei Xu, Jing Zhang, Qiming Zhang, and Dacheng Tao. 2022. ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02033"},{"key":"e_1_3_3_1_48_1","doi-asserted-by":"crossref","unstructured":"Xinyu Yi Yuxiao Zhou and Feng Xu. 2021. TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors. ACM Transactions on Graphics 40 4 Article 86 (08 2021).","DOI":"10.1145\/3450626.3459786"},{"key":"e_1_3_3_1_49_1","doi-asserted-by":"crossref","unstructured":"Wanqi Yin Zhongang Cai Ruisi Wang Fanzhou Wang Chen Wei Haiyi Mei Weiye Xiao Zhitao Yang Qingping Sun Atsushi Yamashita et\u00a0al. 2024. WHAC: World-grounded Humans and Cameras. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.12959 (2024).","DOI":"10.1007\/978-3-031-72754-2_2"},{"key":"e_1_3_3_1_50_1","doi-asserted-by":"publisher","unstructured":"Ri Yu Hwangpil Park and Jehee Lee. 2021. Human dynamics from monocular video with dynamic camera movements. ACM Trans. Graph. 40 6 Article 208 (dec 2021) 14\u00a0pages. 10.1145\/3478513.3480504https:\/\/dl.acm.org\/doi\/10.1145\/3478513.3480504","DOI":"10.1145\/3478513.3480504"},{"key":"e_1_3_3_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01076"},{"key":"e_1_3_3_1_52_1","doi-asserted-by":"crossref","unstructured":"Hongwen Zhang Yating Tian Yuxiang Zhang Mengcheng Li Liang An Zhenan Sun and Yebin Liu. 2023. PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).","DOI":"10.1109\/TPAMI.2023.3271691"}],"event":{"name":"SA '24: SIGGRAPH Asia 2024 Conference Papers","location":"Tokyo Japan","acronym":"SA '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2024 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687565","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3680528.3687565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:26Z","timestamp":1750294706000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3680528.3687565"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":51,"alternative-id":["10.1145\/3680528.3687565","10.1145\/3680528"],"URL":"https:\/\/doi.org\/10.1145\/3680528.3687565","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}