{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:51:32Z","timestamp":1772905892747,"version":"3.50.1"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,30]]},"DOI":"10.1109\/humanoids65713.2025.11203143","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:50Z","timestamp":1761326150000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Universal Humanoid Robot Pose Learning from Internet Human Videos"],"prefix":"10.1109","author":[{"given":"Jiageng","family":"Mao","sequence":"first","affiliation":[{"name":"University of Southern California"}]},{"given":"Siheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Siqi","family":"Song","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Chuye","family":"Hong","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Tianheng","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Junjie","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Mingtong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Southern California"}]},{"given":"Haoran","family":"Geng","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Jitendra","family":"Malik","sequence":"additional","affiliation":[{"name":"UC Berkeley"}]},{"given":"Vitor","family":"Guizilini","sequence":"additional","affiliation":[{"name":"Toyota Research Institute"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Southern California"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML. PMLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref3","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"TMLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref5","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Openvla: An opensource vision-language-action model","author":"Kim","year":"2024","journal-title":"CoRL"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref8","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"CoRL"},{"key":"ref9","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2023","journal-title":"ICRA"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref12","article-title":"Flow as the cross-domain manipulation interface","author":"Xu","year":"2024","journal-title":"CoRL"},{"key":"ref13","article-title":"General flow as foundation affordance for scalable robot learning","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Learning interactive real-world simulators","author":"Yang","year":"2024","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.052"},{"key":"ref17","article-title":"Humanoid-gym: Reinforcement learning for humanoid robot with zero-shot sim2real transfer","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.058"},{"key":"ref19","article-title":"Learning smooth humanoid locomotion through lipschitz-constrained policies","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.107"},{"key":"ref21","article-title":"Learning humanoid locomotion over challenging terrain","author":"Radosavovic","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Omnih2o: Universal and dexterous human-to-humanoid whole-body teleoperation and learning","author":"He","year":"2024","journal-title":"CoRL"},{"key":"ref23","article-title":"Humanplus: Humanoid shadowing and imitation from humans","author":"Fu","year":"2024","journal-title":"CoRL"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801984"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375203"},{"key":"ref26","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"CoRL"},{"key":"ref27","article-title":"Masked visual pretraining for motor control","author":"Xiao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.012"},{"key":"ref30","article-title":"Video language planning","author":"Du","year":"2024","journal-title":"ICLR"},{"key":"ref31","article-title":"Humanoid locomotion as next token prediction","author":"Radosavovic","year":"2024","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610449"},{"key":"ref33","article-title":"Okami: Teaching humanoid robots manipulation skills through single video imitation","author":"Li","year":"2024","journal-title":"CoRL"},{"key":"ref34","article-title":"Generalizable humanoid manipulation with improved 3d diffusion policies","author":"Ze","year":"2024","journal-title":"RSS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128549"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"issue":"5","key":"ref37","article-title":"Aist dance video database: Multi-genre, multi-dancer, and multi-camera database for dance information processing","volume":"1","author":"Tsuchida","year":"2019","journal-title":"ISMIR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01321"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_33"},{"key":"ref43","article-title":"Motion-x: A large-scale 3d expressive whole-body human motion dataset","volume":"36","author":"Lin","year":"2024","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46448-0_31","article-title":"Hollywood in homes: Crowdsourcing data collection for activity understanding","volume-title":"ECCV","author":"Sigurdsson","year":"2016"},{"key":"ref45","article-title":"A short note on the kinetics-700 human action dataset","author":"Carreira","year":"2019","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Real-time flying object detection with yolov8","author":"Reis","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref50","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref52","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref53","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML.","author":"Radford","year":"2021"},{"key":"ref54","article-title":"Human motion diffusion model","volume-title":"ICLR","author":"Tevet","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"}],"event":{"name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2025,9,30]]},"end":{"date-parts":[[2025,10,2]]}},"container-title":["2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11202977\/11203009\/11203143.pdf?arnumber=11203143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:46:52Z","timestamp":1761367612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11203143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/humanoids65713.2025.11203143","relation":{},"subject":[],"published":{"date-parts":[[2025,9,30]]}}}