{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:14:00Z","timestamp":1778184840620,"version":"3.51.4"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019033","name":"Key Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2025CXGC010111"],"award-info":[{"award-number":["2025CXGC010111"]}],"id":[{"id":"10.13039\/501100019033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019033","name":"Key Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2025CXGC010210"],"award-info":[{"award-number":["2025CXGC010210"]}],"id":[{"id":"10.13039\/501100019033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019033","name":"Key Research and Development Program of Shandong Province","doi-asserted-by":"publisher","award":["2024CXGC010212"],"award-info":[{"award-number":["2024CXGC010212"]}],"id":[{"id":"10.13039\/501100019033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2057"],"award-info":[{"award-number":["U22A2057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403277"],"award-info":[{"award-number":["62403277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science and Technology Major Project of China","award":["2024YFB3309301"],"award-info":[{"award-number":["2024YFB3309301"]}]},{"DOI":"10.13039\/501100020196","name":"Shandong Provincial Natural Science Foundation, China","doi-asserted-by":"publisher","award":["2024YFB3309301"],"award-info":[{"award-number":["2024YFB3309301"]}],"id":[{"id":"10.13039\/501100020196","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3686977","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:00:46Z","timestamp":1776974446000},"page":"8697-8709","source":"Crossref","is-referenced-by-count":0,"title":["CoVA-IL: Zero-Shot Imitation Learning via Contrastive Viewpoint Alignment on Object-Centric Representation"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9205-0254","authenticated-orcid":false,"given":"Jiangtao","family":"Luo","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3126-8021","authenticated-orcid":false,"given":"Shuo","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenchen","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1065-4127","authenticated-orcid":false,"given":"Jinqiu","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Future Technology, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Jinan Preschool Education College, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1344-4415","authenticated-orcid":false,"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref2","article-title":"Data scaling laws in imitation learning for robotic manipulation","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref3","first-page":"4066","article-title":"Mobile ALOHA: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","volume-title":"Proc. CoRL","author":"Fu"},{"key":"ref4","first-page":"26991","article-title":"Behavior generation with latent actions","volume-title":"Proc. ICML","author":"Lee"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00103-5"},{"key":"ref10","first-page":"892","article-title":"R3M: A universal visual representation for robot manipulation","volume-title":"Proc. CoRL","author":"Nair"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-030323-022510"},{"key":"ref12","first-page":"557","article-title":"MT-opt: Continuous multi-task robotic reinforcement learning at scale","volume-title":"Proc. CoRL","author":"Kalashnikov"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10212658"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref15","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. ICML","author":"Driess"},{"key":"ref16","first-page":"334","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","volume-title":"Proc. CoRL","author":"James"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref18","first-page":"11393","article-title":"Deep reinforcement learning amidst continual structured non-stationarity","volume-title":"Proc. ICML","author":"Xie"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref21","article-title":"Learning an embedding space for transferable robot skills","volume-title":"Proc. ICLR","author":"Hausman"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref25","first-page":"23192","article-title":"PointNeXt: Revisiting PointNet+$ with improved training and scaling strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Elhoseiny"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.157"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.146"},{"key":"ref28","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","volume":"1","author":"Chen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref34","volume-title":"Grounded SAM 2: Ground and Track Anything in Videos With Grounding Dino, Florence-2 and SAM 2","author":"Ren","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246340"},{"key":"ref36","volume-title":"VisionProTeleop: Using Apple Vision Pro to Train and Control Robots","author":"Park","year":"2024"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11494064.pdf?arnumber=11494064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:56:14Z","timestamp":1778183774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11494064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3686977","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}