{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:20:18Z","timestamp":1766132418040,"version":"3.48.0"},"reference-count":42,"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","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/iros60139.2025.11247097","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"7622-7629","source":"Crossref","is-referenced-by-count":0,"title":["RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation"],"prefix":"10.1109","author":[{"given":"Chengbo","family":"Yuan","sequence":"first","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences"}]},{"given":"Suraj","family":"Joshi","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Shaoting","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences"}]},{"given":"Hang","family":"Su","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology"}]},{"given":"Hang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0960-9822(98)70314-8"},{"article-title":"Aloha unleashed: A simple recipe for robot dexterity","year":"2024","author":"Zhao","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611331"},{"article-title":"Green screen augmentation enables scene generalisation in robotic manipulation","year":"2024","author":"Teoh","key":"ref5"},{"year":"2023","key":"ref6","article-title":"Open X-Embodiment: Robotic learning datasets and RT-X models"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"article-title":"Data scaling laws in imitation learning for robotic manipulation","year":"2024","author":"Lin","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273686"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"article-title":"Cacti: A framework for scalable multi-task multi-scene visual imitation learning","year":"2022","author":"Mandi","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00705"},{"article-title":"Rovi-aug: Robot and viewpoint augmentation for cross-embodiment robot learning","year":"2024","author":"Chen","key":"ref13"},{"article-title":"Evf-sam: Early vision-language fusion for text-prompted segment anything model","year":"2024","author":"Zhang","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00744"},{"article-title":"Open-television: Teleoperation with immersive active visual feedback","year":"2024","author":"Cheng","key":"ref16"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref17"},{"article-title":"Open-vla: An open-source vision-language-action model","year":"2024","author":"Kim","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.067"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246340"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801678"},{"article-title":"R3m: A universal visual representation for robot manipulation","year":"2022","author":"Nair","key":"ref23"},{"article-title":"Robots pre-train robots: Manipulation-centric robotic representation from large-scale robot datasets","year":"2024","author":"Jiang","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01700"},{"article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","year":"2023","author":"O\u2019Neill","key":"ref26"},{"article-title":"Enhancing visual domain robustness in behaviour cloning via saliency-guided augmentation","volume-title":"CoRL Workshop on Safe and Robust Robot Learning for Operation in the Real World","author":"Zhuang","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00438"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.027"},{"article-title":"Sam 2: Segment anything in images and videos","year":"2024","author":"Ravi","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"article-title":"Roboexp: Action-conditioned scene graph via interactive exploration for robotic manipulation","year":"2024","author":"Jiang","key":"ref32"},{"article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","year":"2024","author":"Huang","key":"ref33"},{"article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","year":"2024","author":"Liu","key":"ref34"},{"article-title":"Gpt-4o system card","year":"2024","author":"Hurst","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref39","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","volume-title":"Conference on robot learning","author":"Finn"},{"article-title":"Dinov2: Learning robust visual features without supervision","year":"2023","author":"Oquab","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00684"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02126"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11247097.pdf?arnumber=11247097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T08:17:21Z","timestamp":1766132241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247097","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}