{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:00:25Z","timestamp":1775325625888,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"German Federal Ministry of Education and Research"},{"DOI":"10.13039\/100007569","name":"Carl-Zeiss-Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007569","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tro.2023.3286074","type":"journal-article","created":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T18:12:37Z","timestamp":1689876757000},"page":"3888-3908","source":"Crossref","is-referenced-by-count":24,"title":["K-VIL: Keypoints-Based Visual Imitation Learning"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6371-505X","authenticated-orcid":false,"given":"Jianfeng","family":"Gao","sequence":"first","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1095-725X","authenticated-orcid":false,"given":"Zhi","family":"Tao","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3565-9414","authenticated-orcid":false,"given":"No\u00e9mie","family":"Jaquier","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-7680","authenticated-orcid":false,"given":"Tamim","family":"Asfour","sequence":"additional","affiliation":[{"name":"Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Karlsruhe, Germany"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Social Learning Theory","volume":"1","author":"Bandura","year":"1977"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1003111107"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref5","first-page":"373","article-title":"Dense Object Nets: Learning dense visual object descriptors by and for robotic manipulation","volume-title":"Proc. 2nd Conf. Robot Learn.","volume":"87","author":"Florence","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12416"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062315"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062560"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561577"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196971"},{"key":"ref11","first-page":"822","article-title":"Learning to compose hierarchical object-centric controllers for robotic manipulation","volume-title":"Proc. 4th Conf. Robot Learn.","volume":"155","author":"Sharma","year":"2021"},{"key":"ref12","first-page":"2504","article-title":"Generalizable task representation learning from human demonstration videos: A geometric approach","volume-title":"Proc. IEEE Int. Conf. Robot. Autom.","author":"Jin","year":"2022"},{"key":"ref13","first-page":"4301","article-title":"Learning via-point movement primitives with inter- and extrapolation capabilities","volume-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst.","author":"Zhou","year":"2019"},{"key":"ref14","first-page":"2593","article-title":"Third-person visual imitation learning via decoupled hierarchical controller","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sharma","year":"2019"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2020.XVI.024","article-title":"AVID: Learning multi-stage tasks via pixel-level translation of human videos","volume-title":"Proc. Robot.: Sci. Syst.","author":"Smith","year":"2020"},{"key":"ref16","first-page":"979","article-title":"Graph-structured visual imitation","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Sieb","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593951"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811570"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812146"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00278"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812402"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/497"},{"key":"ref26","article-title":"Generative adversarial imitation from observation","volume-title":"Proc. ICML Workshop Imitation, Intent, Interact.","author":"Torabi","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812316"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5353894"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2495003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49256-9_19"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008111128520"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487521"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341758"},{"key":"ref35","first-page":"693","article-title":"Keypoints into the future: Self-supervised correspondence in model-based reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Manuelli","year":"2020"},{"key":"ref36","article-title":"MediaPipe: A Framework for Perceiving and Processing Reality","volume-title":"Proc. 3rd Workshop Comput. Vis. AR\/VR IEEE Comput. Vis. Pattern Recognit.","author":"Lugaresi","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9648-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/090771806"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref40","article-title":"Open3D: A modern library for 3D data processing","author":"Zhou","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2019.2941246"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812291"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00651"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981068"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3446370"},{"key":"ref46","first-page":"550","article-title":"One-shot transfer of affordance regions? AffCorrs!","volume-title":"Proc. Conf. Robot Learn.","author":"Hadjivelichkov","year":"2023"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2021.XVII.024","article-title":"Synergies between affordance and geometry: 6-DoF grasp detection via implicit representations","volume-title":"Proc. Robot.: Sci. Syst.","author":"Jiang","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS47582.2021.9555802"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196158"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142397"},{"key":"ref52","article-title":"VAT-mart: Learning visual action trajectory proposals for manipulating 3D articulated objects","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2022"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/10271771\/10189175.pdf?arnumber=10189175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T19:03:10Z","timestamp":1750100590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10189175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":52,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tro.2023.3286074","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}