{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:16Z","timestamp":1750309516278,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":67,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071216,62231002"],"award-info":[{"award-number":["62071216,62231002"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681180","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"8932-8941","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging RGB-Pressure for Whole-body Human-to-Humanoid Motion Imitation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0130-487X","authenticated-orcid":false,"given":"Yi","family":"Lu","sequence":"first","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2819-982X","authenticated-orcid":false,"given":"Shenghao","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3057-0608","authenticated-orcid":false,"given":"Qiu","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University & Key Laboratory of Optoelectronic Devices and Systems with Extreme Performances of MOE, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3094-4371","authenticated-orcid":false,"given":"Xun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University & Key Laboratory of Optoelectronic Devices and Systems with Extreme Performances of MOE, Nanjing University, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024. Vicon Systems. https:\/\/www.vicon.com\/hardware\/cameras\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593521"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12115557"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2752711"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722000169"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings, Part V 14","author":"Black Michael J","year":"2016","unstructured":"FedericaBogo,AngjooKanazawa,ChristophLassner,PeterGehler,JavierRomero, and Michael J Black. 2016. Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image. In Computer Vision--ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part V 14. Springer, 561--578."},{"key":"e_1_3_2_1_8_1","volume-title":"ASME International Mechanical Engineering Congress and Exposition","volume":"85628","author":"Vaz Jean Chagas","year":"2021","unstructured":"Jean Chagas Vaz, Dylan Wallace, and Paul Y Oh. 2021. Humanoid loco manipulation of pushed carts utilizing virtual reality teleoperation. In ASME International Mechanical Engineering Congress and Exposition, Vol. 85628. Ameri can Society of Mechanical Engineers, V07BT07A027."},{"key":"e_1_3_2_1_9_1","volume-title":"Paolo Maria Viceconte, et al","author":"Darvish Kourosh","year":"2024","unstructured":"StefanoDafarra,UgoPattacini,GiulioRomualdi,LorenzoRapetti,RiccardoGrieco, Kourosh Darvish, Gianluca Milani, Enrico Valli, Ines Sorrentino, Paolo Maria Viceconte, et al. 2024. iCub3 avatar system: Enabling remote fully immersive embodiment of humanoid robots. Science Robotics 9, 86 (2024), eadh3834."},{"key":"e_1_3_2_1_10_1","volume-title":"2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI). IEEE, 1--8.","author":"Dajles D","year":"2018","unstructured":"D Dajles, F Siles, et al. 2018. Teleoperation of a humanoid robot using an optical motion capture system. In 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI). IEEE, 1--8."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3236952"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids43949.2019.9035059"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29513-4_80"},{"key":"e_1_3_2_1_14_1","volume-title":"Industrial Robot: the international journal of robotics research and application 50, 5","author":"Fan Xinyang","year":"2023","unstructured":"Xinyang Fan, Xin Shu, Baoxu Tu, Changyuan Liu, Fenglei Ni, and Zainan Jiang. 2023. Ahumanoidrobotteleoperationapproachbasedonwaist--armcoordination. Industrial Robot: the international journal of robotics research and application 50, 5 (2023), 804--813."},{"key":"e_1_3_2_1_15_1","unstructured":"David Gouaillier Vincent Hugel Pierre Blazevic Chris Kilner Jerome Monceaux Pascal Lafourcade Brice Marnier Julien Serre and Bruno Maisonnier. [n.d.]. The nao humanoid: a combination of performance and affordability. ([n.d.])."},{"key":"e_1_3_2_1_16_1","volume-title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation. arXiv preprint arXiv:2403.04436","author":"He Tairan","year":"2024","unstructured":"Tairan He, Zhengyi Luo, Wenli Xiao, Chong Zhang, Kris Kitani, Changliu Liu, and Guanya Shi. 2024. Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation. arXiv preprint arXiv:2403.04436 (2024)."},{"volume-title":"Online human walking imitation in taskandjointspacebasedonquadraticprogramming.In2014IEEEInternational Conference on Robotics and Automation (ICRA)","author":"Hu Kai","key":"e_1_3_2_1_17_1","unstructured":"Kai Hu, Christian Ott, and Dongheui Lee. 2014. Online human walking imitation in taskandjointspacebasedonquadraticprogramming.In2014IEEEInternational Conference on Robotics and Automation (ICRA). IEEE, 3458--3464."},{"key":"e_1_3_2_1_18_1","first-page":"5841","article-title":"High speed whole body dynamic motion experiment with real time master-slave humanoid robot system. In 2018 IEEE International Conference on Robotics and Automation (ICRA)","volume":"5835","author":"Ishiguro Yasuhiro","year":"2018","unstructured":"Yasuhiro Ishiguro, Kunio Kojima, Fumihito Sugai, Shunichi Nozawa, Yohei Kaki uchi, Kei Okada, and Masayuki Inaba. 2018. High speed whole body dynamic motion experiment with real time master-slave humanoid robot system. In 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 5835 5841.","journal-title":"IEEE"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013863"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21674"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids43949.2019.9034993"},{"key":"e_1_3_2_1_22_1","volume-title":"Humanoid robots","author":"Kajita Shuuji","year":"2005","unstructured":"Shuuji Kajita, Hirohisa Hirukawa, Kazuhito Yokoi, and Kensuke Harada. 2005. Humanoid robots. Ohmsha Ltd (2005), 3--1."},{"volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 7122--7131","key":"e_1_3_2_1_23_1","unstructured":"AngjooKanazawa,MichaelJBlack,DavidWJacobs,andJitendraMalik.2018. End to-end recovery of human shape and pose. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7122--7131."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907261"},{"key":"e_1_3_2_1_25_1","volume-title":"Forward and inverse kinematics for the NAO humanoid robot","author":"Kofinas Nikolaos","year":"2012","unstructured":"Nikolaos Kofinas. 2012. Forward and inverse kinematics for the NAO humanoid robot. Technical University of Crete (2012)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00234"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2860628"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2014.08.030"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2023.3253856"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00884"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25240"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1049\/ccs.2020.0005"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"volume-title":"Advanced robotics: redundancy and optimization","author":"Nakamura Yoshihiko","key":"e_1_3_2_1_36_1","unstructured":"Yoshihiko Nakamura. 1990. Advanced robotics: redundancy and optimization. Addison-Wesley Longman Publishing Co., Inc."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2019.1581658"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246911"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0296-9"},{"key":"e_1_3_2_1_40_1","volume-title":"Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture. In SIGGRAPH Asia 2023 Conference Papers. 1--11","author":"Pan Shaohua","year":"2023","unstructured":"Shaohua Pan, Qi Ma, Xinyu Yi, Weifeng Hu, Xiong Wang, Xingkang Zhou, Jijunnan Li, and Feng Xu. 2023. Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture. In SIGGRAPH Asia 2023 Conference Papers. 1--11."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624943"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2019.2941245"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings, Part V 16","author":"Rempe Davis","year":"2020","unstructured":"Davis Rempe, Leonidas J Guibas, Aaron Hertzmann, Bryan Russell, Ruben Ville gas, and Jimei Yang. 2020. Contact and human dynamics from monocular video. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part V 16. Springer, 71--87."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Emily-Jane Rolley-Parnell Dimitrios Kanoulas Arturo Laurenzi Brian Delhaisse Leonel Rozo Darwin G Caldwell and Nikos G Tsagarakis. 2018. Bi-manual articulated robot teleoperation using an external RGB-Drangesensor.In201815th International Conference on Control Automation Robotics and Vision (ICARCV)","DOI":"10.1109\/ICARCV.2018.8581174"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings, Part XXIII 16","author":"Scott Jesse","year":"2020","unstructured":"Jesse Scott, Bharadwaj Ravichandran, Christopher Funk, Robert T Collins, and Yanxi Liu. 2020. From image to stability: Learning dynamics from human pose. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXIII 16. Springer, 536--554."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3100603"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375203"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459825"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417877"},{"key":"e_1_3_2_1_51_1","unstructured":"SoftBank 2021. Nao document. SoftBank. http:\/\/doc.aldebaran.com\/2--8\/home_ nao.html."},{"key":"e_1_3_2_1_52_1","volume-title":"Proc. Australasian Conference on Robotics and Automa tion","volume":"8","author":"Stanton Christopher","year":"2012","unstructured":"Christopher Stanton, Anton Bogdanovych, and Edward Ratanasena. 2012. Teleop eration of a humanoid robot using full-body motion capture, example movements, and machine learning. In Proc. Australasian Conference on Robotics and Automa tion, Vol. 8. 51."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1142\/S021984362050019X"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.124140"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00457"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843604000083"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics8080591"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989632"},{"key":"e_1_3_2_1_61_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 7159--7169","author":"Saragih Jason","year":"2021","unstructured":"YeYuan,Shih-EnWei,TomasSimon,KrisKitani, andJason Saragih. 2021. Simpoe: Simulated character control for 3d human pose estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 7159--7169."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.9"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151433"},{"key":"e_1_3_2_1_64_1","volume-title":"MMVP: A Multimodal MoCapDataset with Vision and Pressure Sensors. arXiv preprint arXiv:2403.17610","author":"Zhang He","year":"2024","unstructured":"He Zhang, Shenghao Ren, Haolei Yuan, Jianhui Zhao, Fan Li, Shuangpeng Sun, Zhenghao Liang, Tao Yu, Qiu Shen, and Xun Cao. 2024. MMVP: A Multimodal MoCapDataset with Vision and Pressure Sensors. arXiv preprint arXiv:2403.17610 (2024)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2016.7866528"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.5430\/ijrc.v2n1p49"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.3390\/app8102005"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681180","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:02Z","timestamp":1750295882000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681180"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":67,"alternative-id":["10.1145\/3664647.3681180","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681180","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"}}]}}