{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T21:19:33Z","timestamp":1771708773046,"version":"3.50.1"},"reference-count":33,"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","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\/iros60139.2025.11246600","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"13154-13161","source":"Crossref","is-referenced-by-count":3,"title":["VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Kui","family":"Wu","sequence":"first","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"}]},{"given":"Shuhang","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Normal University,School of Artificial Intelligence,Beijing,China"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"City University of Macau,China"}]},{"given":"Churan","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Computer Science, Inst. for Artificial Intelligence, State Key Laboratory of General Artificial Intelligence,Beijing,China"}]},{"given":"Zhoujun","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Complex & Critical Software Environment,Beijing,China"}]},{"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Computer Science, Inst. for Artificial Intelligence, State Key Laboratory of General Artificial Intelligence,Beijing,China"}]},{"given":"Fangwei","family":"Zhong","sequence":"additional","affiliation":[{"name":"Beijing Normal University,School of Artificial Intelligence,Beijing,China"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912437213"},{"key":"ref5","article-title":"Proactive multi-camera collaboration for 3d human pose estimation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ci"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103799"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150866"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3385700"},{"key":"ref9","article-title":"Memory sharing for large language model based agents","author":"Gao","year":"2024"},{"key":"ref10","article-title":"An embodied generalist agent in 3d world","volume-title":"The Twelfth International Conference on Learning Representations Workshop: How Far Are We From AGI","author":"Huang"},{"key":"ref11","article-title":"Conquering ghosts: Relation learning for information reliability representation and end-to-end robust navigation","author":"Jin","year":"2022"},{"key":"ref12","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"8th Annual Conference on Robot Learning","author":"Kim"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2516982"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICoNSIP49665.2022.10007460"},{"key":"ref15","first-page":"19730","article-title":"Blip-2: Boot-strapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref16","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"3286","article-title":"End-to-end active object tracking via reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Luo"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.03.008"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461181"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IAS.1994.377694"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3129396"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932850"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2018.2820172"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25482"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952590"},{"key":"ref29","first-page":"12782","article-title":"Towards distraction-robust active visual tracking","volume-title":"International Conference on Machine Learning","author":"Zhong"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_9"},{"key":"ref31","article-title":"Unrealzoo: Enriching photo-realistic virtual worlds for embodied ai","author":"Zhong","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3282792"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"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\/11246600.pdf?arnumber=11246600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:12:24Z","timestamp":1765519944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246600","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}