{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T22:21:47Z","timestamp":1771366907930,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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","award":["62206288"],"award-info":[{"award-number":["62206288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3662560","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:09:14Z","timestamp":1770671354000},"page":"3708-3715","source":"Crossref","is-referenced-by-count":0,"title":["Agent as Student: Learning From Informative Cues for Active Open-Vocabulary Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3513-2297","authenticated-orcid":false,"given":"Ruizhe","family":"Zeng","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6240-5300","authenticated-orcid":false,"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0553-4581","authenticated-orcid":false,"given":"Xu","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2148-1846","authenticated-orcid":false,"given":"Zhiyong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160946"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01547"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1205"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01551"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00213"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247705"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28281"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01444"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamericanmind0310-38"},{"key":"ref13","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","author":"Ramakrishnan","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00133571"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341988"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_30"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1500-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_19"},{"key":"ref20","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref21","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3361862"},{"key":"ref23","first-page":"15099","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref25","first-page":"41175","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16234"},{"key":"ref27","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989164"},{"key":"ref29","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Szot","year":"2021"},{"key":"ref30","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda","year":"2000"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11373848.pdf?arnumber=11373848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:10:24Z","timestamp":1771362624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11373848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":33,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3662560","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}