{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:24:41Z","timestamp":1784737481804,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"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":[[2022,11,29]]},"DOI":"10.1145\/3550469.3555428","type":"proceedings-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T11:07:54Z","timestamp":1669806474000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":97,"title":["Transformer Inertial Poser: Real-time Human Motion Reconstruction from Sparse IMUs with Simultaneous Terrain Generation"],"prefix":"10.1145","author":[{"given":"Yifeng","family":"Jiang","sequence":"first","affiliation":[{"name":"Computer Science, Stanford University, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Ye","sequence":"additional","affiliation":[{"name":"Meta Reality Labs, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deepak","family":"Gopinath","sequence":"additional","affiliation":[{"name":"Meta AI, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungdam","family":"Won","sequence":"additional","affiliation":[{"name":"Meta AI, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander W.","family":"Winkler","sequence":"additional","affiliation":[{"name":"Meta Reality Labs, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C. Karen","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer Science, Stanford University, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,11,30]]},"reference":[{"key":"e_1_3_2_3_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"e_1_3_2_3_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998559.2998564"},{"key":"e_1_3_2_3_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/505008.505011"},{"key":"e_1_3_2_3_4_1","unstructured":"Tom\u00a0B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel\u00a0M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. (2020). arxiv:2005.14165\u00a0[cs.CL]"},{"key":"e_1_3_2_3_5_1","volume-title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","author":"Cao Z.","year":"2019","unstructured":"Z. Cao, G. Hidalgo Martinez, T. Simon, S. Wei, and Y.\u00a0A. Sheikh. 2019. OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)."},{"key":"e_1_3_2_3_6_1","volume-title":"Adrian Ilie, and Henry Fuchs.","author":"Cha Young-Woon","year":"2021","unstructured":"Young-Woon Cha, Husam Shaik, Qian Zhang, Fan Feng, Andrei State, Adrian Ilie, and Henry Fuchs. 2021. Mobile. Egocentric Human Body Motion Reconstruction Using Only Eyeglasses-mounted Cameras and a Few Body-worn Inertial Sensors. In 2021 IEEE Virtual Reality and 3D User Interfaces (VR)."},{"key":"e_1_3_2_3_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01270-5"},{"key":"e_1_3_2_3_8_1","unstructured":"Vasileios Choutas Federica Bogo Jingjing Shen and Julien Valentin. 2021. Learning to Fit Morphable Models. CoRR abs\/2111.14824(2021). arXiv:2111.14824https:\/\/arxiv.org\/abs\/2111.14824"},{"key":"e_1_3_2_3_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2864989"},{"key":"e_1_3_2_3_10_1","volume-title":"Jukebox: A Generative Model for Music. arxiv:2005.00341\u00a0[eess.AS]","author":"Dhariwal Prafulla","year":"2020","unstructured":"Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong\u00a0Wook Kim, Alec Radford, and Ilya Sutskever. 2020. Jukebox: A Generative Model for Music. arxiv:2005.00341\u00a0[eess.AS]"},{"key":"e_1_3_2_3_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01148"},{"key":"e_1_3_2_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2006.1638022"},{"key":"e_1_3_2_3_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/VRAIS.1996.490527"},{"key":"e_1_3_2_3_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1118-y"},{"key":"e_1_3_2_3_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"e_1_3_2_3_16_1","doi-asserted-by":"crossref","unstructured":"Vladimir Guzov Aymen Mir Torsten Sattler and Gerard Pons-Moll. 2021. Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00430"},{"key":"e_1_3_2_3_17_1","volume-title":"Real-Time Body Tracking with One Depth Camera and Inertial Sensors. In 2013 IEEE International Conference on Computer Vision. 1105\u20131112","author":"Helten Thomas","year":"2013","unstructured":"Thomas Helten, Meinard M\u00fcller, Hans-Peter Seidel, and Christian Theobalt. 2013. Real-Time Body Tracking with One Depth Camera and Inertial Sensors. In 2013 IEEE International Conference on Computer Vision. 1105\u20131112."},{"key":"e_1_3_2_3_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392440"},{"key":"e_1_3_2_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275108"},{"key":"e_1_3_2_3_20_1","doi-asserted-by":"crossref","unstructured":"Angjoo Kanazawa Jason\u00a0Y. Zhang Panna Felsen and Jitendra Malik. 2019. Learning 3D Human Dynamics from Video. In Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00576"},{"key":"e_1_3_2_3_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01131"},{"key":"e_1_3_2_3_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.06.018"},{"key":"e_1_3_2_3_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1218064.1218103"},{"key":"e_1_3_2_3_24_1","unstructured":"Ruilong Li Shan Yang David\u00a0A. Ross and Angjoo Kanazawa. 2021. AI Choreographer: Music Conditioned 3D Dance Generation with AIST++."},{"key":"e_1_3_2_3_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1944745.1944768"},{"key":"e_1_3_2_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_3_27_1","unstructured":"Zhengyi Luo Ryo Hachiuma Ye Yuan and Kris Kitani. 2021. Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation. In NeurIPS."},{"key":"e_1_3_2_3_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00058"},{"key":"e_1_3_2_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3378184.3378228"},{"key":"e_1_3_2_3_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"e_1_3_2_3_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126375"},{"key":"e_1_3_2_3_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540153"},{"key":"e_1_3_2_3_33_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_3_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"e_1_3_2_3_35_1","unstructured":"Rokoko. n\u00a0d. Rokoko https:\/\/www.rokoko.com\/. Last visited: 08\/26\/2022."},{"key":"e_1_3_2_3_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417877"},{"key":"e_1_3_2_3_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_3_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247664"},{"key":"e_1_3_2_3_39_1","doi-asserted-by":"crossref","unstructured":"Matt Trumble Andrew Gilbert Charles Malleson Adrian Hilton and John Collomosse. 2017. Total Capture: 3D Human Pose Estimation Fusing Video and Inertial Sensors. In BMVC.","DOI":"10.5244\/C.31.14"},{"key":"e_1_3_2_3_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480570"},{"key":"e_1_3_2_3_41_1","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 Vol.\u00a030."},{"key":"e_1_3_2_3_42_1","unstructured":"Vicon. n\u00a0d. Vicon Motion Systems https:\/\/www.vicon.com\/. Last visited: 08\/26\/2022."},{"key":"e_1_3_2_3_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3026895"},{"key":"e_1_3_2_3_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276421"},{"key":"e_1_3_2_3_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"e_1_3_2_3_46_1","volume-title":"Human Pose Estimation from Video and IMUs. Transactions on Pattern Analysis and Machine Intelligence (PAMI) (jan","author":"von Marcard Timo","year":"2016","unstructured":"Timo von Marcard, Gerard Pons-Moll, and Bodo Rosenhahn. 2016. Human Pose Estimation from Video and IMUs. Transactions on Pattern Analysis and Machine Intelligence (PAMI) (jan 2016)."},{"key":"e_1_3_2_3_47_1","volume-title":"Proceedings of the 38th Annual Conference of the European Association for Computer Graphics (Eurographics)","author":"von Marcard Timo","year":"2017","unstructured":"Timo von Marcard, Bodo Rosenhahn, Michael Black, and Gerard Pons-Moll. 2017. Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs. Computer Graphics Forum 36(2), Proceedings of the 38th Annual Conference of the European Association for Computer Graphics (Eurographics) (2017), 349\u2013360."},{"key":"e_1_3_2_3_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366207"},{"key":"e_1_3_2_3_49_1","unstructured":"Xsens. n\u00a0d. Xsens https:\/\/www.xsens.com\/. Last visited: 08\/26\/2022."},{"key":"e_1_3_2_3_50_1","doi-asserted-by":"publisher","unstructured":"Dongseok Yang Doyeon Kim and Sung-Hee Lee. 2021. LoBSTr: Real-time Lower-body Pose Prediction from Sparse Upper-body Tracking Signals. Computer Graphics Forum(2021). https:\/\/doi.org\/10.1111\/cgf.142631","DOI":"10.1111\/cgf.142631"},{"key":"e_1_3_2_3_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01282"},{"key":"e_1_3_2_3_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459786"},{"key":"e_1_3_2_3_53_1","doi-asserted-by":"crossref","unstructured":"Zhe Zhang Chunyu Wang Wenhu Qin and Wenjun Zeng. 2020. Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00227"},{"key":"e_1_3_2_3_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_24"},{"key":"e_1_3_2_3_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"}],"event":{"name":"SA '22: SIGGRAPH Asia 2022","location":"Daegu Republic of Korea","acronym":"SA '22","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["SIGGRAPH Asia 2022 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550469.3555428","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3550469.3555428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:44Z","timestamp":1750182704000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3550469.3555428"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,29]]},"references-count":55,"alternative-id":["10.1145\/3550469.3555428","10.1145\/3550469"],"URL":"https:\/\/doi.org\/10.1145\/3550469.3555428","relation":{},"subject":[],"published":{"date-parts":[[2022,11,29]]},"assertion":[{"value":"2022-11-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}