{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:45:00Z","timestamp":1766061900909,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247345","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"9606-9613","source":"Crossref","is-referenced-by-count":0,"title":["QueryAdapter: Rapid Adaptation of Vision-Language Models in Response to Natural Language Queries"],"prefix":"10.1109","author":[{"given":"Nicolas Harvey","family":"Chapman","sequence":"first","affiliation":[{"name":"Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feras","family":"Dayoub","sequence":"additional","affiliation":[{"name":"University of Adelaide,School of Computer Science and the Australian Institute of Machine Learning,Adelaide,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Will","family":"Browne","sequence":"additional","affiliation":[{"name":"Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Lehnert","sequence":"additional","affiliation":[{"name":"Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3451395"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"article-title":"The bare necessities: Designing simple, effective open-vocabulary scene graphs","year":"2024","author":"Kassab","key":"ref7"},{"article-title":"Ovo-slam: Open-vocabulary online simultaneous localization and mapping","year":"2024","author":"Martins","key":"ref8"},{"key":"ref9","first-page":"13 086","article-title":"Seal: Self-supervised embodied active learning using exploration and 3d consistency","volume":"34","author":"Chaplot","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16338"},{"article-title":"Self-improving object detection via disagreement reconciliation","year":"2023","author":"Scarpellini","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5244\/c.35.174"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01444"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"article-title":"Unsupervised prompt learning for vision-language models","year":"2022","author":"Huang","key":"ref16"},{"article-title":"Realistic unsupervised clip fine-tuning with universal entropy optimization","volume-title":"Forty-first International Conference on Machine Learning","author":"Liang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811877"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref27","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Language-driven semantic segmentation","year":"2022","author":"Li","key":"ref28"},{"key":"ref29","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"article-title":"Llava-3d: A simple yet effective pathway to empowering lmms with 3d-awareness","year":"2024","author":"Zhu","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00673"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"article-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling","year":"2021","author":"Zhang","key":"ref34"},{"article-title":"Prompt tuning based adapter for vision-language model adaption","year":"2023","author":"Sun","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3400066"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3290420"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00352"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00182"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02237"}],"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\/11247345.pdf?arnumber=11247345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:39Z","timestamp":1766061639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247345","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}