{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T01:42:34Z","timestamp":1769737354156,"version":"3.49.0"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2327973,2006388,2312956"],"award-info":[{"award-number":["2327973,2006388,2312956"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128834","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"8802-8810","source":"Crossref","is-referenced-by-count":6,"title":["Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning"],"prefix":"10.1109","author":[{"given":"Juntao","family":"Ren","sequence":"first","affiliation":[{"name":"Cornell University"}]},{"given":"Priya","family":"Sundaresan","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Dorsa","family":"Sadigh","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Sanjiban","family":"Choudhury","sequence":"additional","affiliation":[{"name":"Cornell University"}]},{"given":"Jeannette","family":"Bohg","sequence":"additional","affiliation":[{"name":"Stanford University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning from demonstration","volume":"9","author":"Schaal","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref5","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"Padalkar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref8","volume-title":"Oculus reader: Robotic teleoperation interface","author":"Jedrzej Orbik","year":"2021"},{"key":"ref9","article-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Gello: A general, low-cost, and intuitive teleoperation framework for robot manipulators","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref13","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.032"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611331"},{"key":"ref16","first-page":"1183","article-title":"An unbiased look at datasets for visuo-motor pre-training","author":"Dasari","year":"2023","journal-title":"Conference on Robot Learning. PMLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.092"},{"key":"ref18","article-title":"Track2act: Predicting point tracks from internet videos enables diverse zero-shot robot manipulation","author":"Bharadhwaj","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.052"},{"key":"ref20","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"537","article-title":"Xirl: Cross-embodiment inverse reinforcement learning","author":"Zakka","year":"2022","journal-title":"Conference on Robot Learning. PMLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref23","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"12","article-title":"Robot learning from demonstration","volume":"97","author":"Atkeson","year":"1997","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref27","article-title":"One-shot imitation learning","volume":"30","author":"Duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Bunny-visionpro: Real-time bimanual dexterous teleoperation for imitation learning","author":"Ding","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241227559"},{"key":"ref30","author":"Park","year":"2024","journal-title":"Using apple vision pro to train and control robots"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref32","article-title":"Open-world object manipulation using pre-trained vision-language models","author":"Stone","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Kite: Keypoint-conditioned policies for semantic manipulation","author":"Sundaresan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.067"},{"key":"ref36","first-page":"694","article-title":"Rvt: Robotic view transformer for 3d object manipulation","author":"Goyal","year":"2023","journal-title":"Conference on Robot Learning. PMLR"},{"key":"ref37","article-title":"Sparsedff: Sparse-view feature distillation for one-shot dexterous manipulation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Language embedded radiance fields for zero-shot task-oriented grasping","volume-title":"7th Annual Conference on Robot Learning","author":"Rashid","year":"2023"},{"key":"ref39","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","author":"Shridhar","year":"2023","journal-title":"Conference on Robot Learning. PMLR"},{"key":"ref40","article-title":"General flow as foundation affordance for scalable robot learning","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Flowretrieval: Flow-guided data retrieval for few-shot imitation learning","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Learning to act from actionless videos through dense correspondences","author":"Ko","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Manipulate-anything: Automating real-world robots using vision-language models","author":"Duan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610288"},{"key":"ref45","article-title":"Flow as the cross-domain manipulation interface","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref47","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Damen","year":"2018"},{"key":"ref48","first-page":"24 639","article-title":"Video pretraining (vpt): Learning to act by watching unlabeled online videos","volume":"35","author":"Baker","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","first-page":"3536","article-title":"Xskill: Cross embodiment skill discovery","author":"Xu","year":"2023","journal-title":"Conference on Robot Learning. PMLR"},{"key":"ref50","article-title":"Third-person visual imitation learning via decoupled hierarchical controller","volume":"32","author":"Sharma","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","article-title":"Vip: Towards universal visual reward and representation via value-implicit pre-training","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.024"},{"key":"ref53","article-title":"View: Visual imitation learning with waypoints","author":"Jonnavittula","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Language-model-assisted bi-level programming for reward learning from internet videos","author":"Mahesheka","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01358"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00154"},{"key":"ref57","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611491"},{"key":"ref59","article-title":"Equibot: Sim (3)-equivariant diffusion policy for generalizable and data efficient learning","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"R+ x: Retrieval and execution from everyday human videos","author":"Papagiannis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Vision-based manipulation from single human video with open-world object graphs","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611409"},{"key":"ref63","article-title":"Learning wheelchair tennis navigation from broadcast videos with domain knowledge transfer and diffusion motion planning","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref65","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"Ganin","year":"2015","journal-title":"International conference on machine learning. PMLR"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128834.pdf?arnumber=11128834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:15:00Z","timestamp":1756880100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128834","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}