{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T17:02:28Z","timestamp":1791478948894,"version":"4.3.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC)","doi-asserted-by":"publisher","award":["92470202,U21A20471"],"award-info":[{"award-number":["92470202,U21A20471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Guangdong Natural Science Foundation (NSF) Project","doi-asserted-by":"publisher","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01289","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13890-13900","source":"Crossref","is-referenced-by-count":1,"title":["iManip: Skill-Incremental Learning for Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Zexin","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,china"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia-Feng","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,china"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,china"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Lin","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,china"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Ming","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,china"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ancong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,china"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,china"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.753"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref6","volume-title":"Real-to-sim grasp: Rethinking the gap between simulation and real world in grasp detection","author":"Cai","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_15"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref9","article-title":"On tiny episodic memories in continual learning","author":"Chaudhry","year":"2019","journal-title":"arXiv preprintarXiv"},{"key":"ref10","article-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref11","article-title":"Polarnet: 3d point clouds for language-guided robotic manipulation","author":"Chen","year":"2023","journal-title":"arXiv preprintarXiv"},{"key":"ref12","article-title":"Open-television: Teleoperation with immersive active visual feedback","author":"Cheng","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636069"},{"key":"ref16","article-title":"Act3d: 3d feature field transformers for multi-task robotic manipulation","author":"Gervet","year":"2023","journal-title":"arXiv preprintarXiv"},{"key":"ref17","article-title":"Rvt: Robotic view transformer for 3d object manipulation","volume-title":"Conference on Robot Learning","author":"Goyal"},{"key":"ref18","article-title":"Instruction-driven history-aware policies for robotic manipulations","volume-title":"Conference on Robot Learning","author":"Guhur"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00092"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00395"},{"key":"ref21","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref22","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref24","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01560"},{"key":"ref26","article-title":"3d diffuser actor: Policy diffusion with 3d scene representations","author":"Ke","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref28","article-title":"Environments for lifelong reinforcement learning","author":"Khetarpal","year":"2018","journal-title":"arXiv preprintarXiv"},{"key":"ref29","article-title":"Online continual learning for interactive instruction following agents","author":"Kim","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref30","volume-title":"Openvla: An opensource vision-language-action model","author":"Kim","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00040"},{"key":"ref32","article-title":"Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3396692"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00257"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01712"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref40","article-title":"Lifelong inverse reinforcement learning","author":"Mendez","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-00983-2"},{"key":"ref42","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv preprintarXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01158"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3324203"},{"key":"ref45","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01705"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref50","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref51","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00924"},{"key":"ref53","article-title":"Languageconditioned imitation learning for robot manipulation tasks","author":"Stepputtis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00933"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104264"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128749"},{"key":"ref59","article-title":"Grasp as you say: Language-guided dexterous grasp generation","author":"Wei","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01099"},{"key":"ref61","article-title":"Continual world: A robotic benchmark for continual reinforcement learning","author":"Wo\u0142czyk","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801581"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_21"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref65","article-title":"Chaineddiffuser: Unifying trajectory diffusion and keypose prediction for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Xian"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref67","article-title":"Gnfactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Conference on Robot Learning","author":"Ze"},{"key":"ref68","article-title":"Cotransport for class-incremental learning","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia","author":"Zhou"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02100"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445215.pdf?arnumber=11445215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:25:41Z","timestamp":1777613141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01289","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}