{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:43:11Z","timestamp":1778496191125,"version":"3.51.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611409","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"5397-5403","source":"Crossref","is-referenced-by-count":37,"title":["RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation"],"prefix":"10.1109","author":[{"given":"Mel","family":"Vecerik","sequence":"first","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carl","family":"Doersch","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todor","family":"Davchev","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuf","family":"Aytar","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raia","family":"Hadsell","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lourdes","family":"Agapito","sequence":"additional","affiliation":[{"name":"University College London,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jon","family":"Scholz","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Tap-vid: A benchmark for tracking any point in a video","volume-title":"Proceedings of Neural Information Processing Systems (NeurIPS)","author":"Doersch"},{"key":"ref2","author":"Michael","year":"2022","journal-title":"Do as i can and not as i say: Grounding language in robotic affordances"},{"key":"ref3","author":"Bousmalis","year":"2023","journal-title":"Robocat: A self-improving foundation agent for robotic manipulation"},{"key":"ref4","author":"Michael","year":"2022","journal-title":"RT-1: Robotics transformer for real-world control at scale"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref6","author":"Kalashnikov","year":"2018","journal-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197331"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2959445"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.088"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907430"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196714"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_31"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00469"},{"key":"ref15","first-page":"233","article-title":"Real time control of a robot with a mobile camera","volume-title":"Proc. 9th Int. Symp. on Industrial Robots","author":"Hill"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8111298"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2008.4755985"},{"key":"ref18","first-page":"2002","article-title":"Survey on visual servoing for manipulation","volume":"15","author":"Kragic","year":"2002","journal-title":"Computational Vision and Active Perception Laboratory, Fiskartorpsv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103757"},{"key":"ref20","first-page":"132","article-title":"kpam: Keypoint affordances for category-level robotic manipulation","volume-title":"The International Symposium of Robotics Research","author":"Manuelli"},{"key":"ref21","article-title":"S3k: Self-supervised semantic keypoints for robotic manipulation via multi-view consistency","volume-title":"Conference on Robotic Learning (CoRL)","author":"Vecerik"},{"key":"ref22","first-page":"1930","article-title":"Model-based inverse reinforcement learning from visual demonstrations","author":"Das","year":"2021","journal-title":"CoRL."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812209"},{"key":"ref24","author":"Florence","year":"2018","journal-title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref26","article-title":"Cliport: What and where pathways for robotic manipulation","author":"Shridhar","year":"2022","journal-title":"CoRL."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0960-9822(98)70314-8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198524724.001.0001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00190"},{"key":"ref34","article-title":"Wish you were here: Hindsight goal selection for long-horizon dexterous manipulation","author":"Davchev","year":"2022","journal-title":"ICLR"},{"key":"ref35","first-page":"537","article-title":"Xirl: Cross-embodiment inverse reinforcement learning","volume-title":"Conference on Robot Learning","author":"Zakka"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref37","first-page":"11 525","article-title":"Object-centric learning with slot attention","author":"Locatello","year":"2020","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44480-7_21"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF01934122"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.076"},{"issue":"11","key":"ref42","first-page":"120","article-title":"The opencv library","volume":"25","author":"Bradski","year":"2000","journal-title":"Dr. Dobb\u2019s Journal: Software Tools for the Professional Programmer"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611409.pdf?arnumber=10611409","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:17:32Z","timestamp":1723349852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611409\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611409","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}