{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T23:13:40Z","timestamp":1784070820387,"version":"3.55.0"},"reference-count":50,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB3906102"],"award-info":[{"award-number":["2023YFB3906102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176017"],"award-info":[{"award-number":["62176017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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\/iccv51701.2025.00785","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8384-8394","source":"Crossref","is-referenced-by-count":3,"title":["OpenRSD: Towards Open-Prompts for Object Detection in Remote Sensing Images"],"prefix":"10.1109","author":[{"given":"Ziyue","family":"Huang","sequence":"first","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongchao","family":"Feng","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Yang","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingjie","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University,State Key Laboratory of Virtual Reality Technology and Systems,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3183022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00646"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117983"},{"key":"ref11","first-page":"6","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref12","first-page":"2","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"International Conference on Learning Representations","author":"Gu","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3123666"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_1"},{"key":"ref16","first-page":"2","article-title":"T-rex: Counting by visual prompting","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","article-title":"xview: Objects in context in overhead imagery","author":"Lam","year":"2018","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_25"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2016.2565705"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"ref27","first-page":"5","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3268176"},{"key":"ref29","article-title":"Rtmdet: An empirical study of designing real-time object detectors","author":"Lyu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32672"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"ref34","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"proceedings of the IEEE conference on computer vision and pattern recognition","author":"Ross","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3283137"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref37","article-title":"Spacenet: A remote sensing dataset and challenge series","author":"Van Etten","year":"2018","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref39","first-page":"2","article-title":"Ov-dino: Unified open-vocabulary detection with language-aware selective fusion","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"ref41","article-title":"Ova-detr: Open vocabulary aerial object detection using image-text alignment and fusion","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01648"},{"key":"ref45","article-title":"The kfiou loss for rotated object detection","author":"Yang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02586"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28518"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3104230"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548541"}],"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\/11444760.pdf?arnumber=11444760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:42Z","timestamp":1777612182000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00785","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}