{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:00:05Z","timestamp":1784131205574,"version":"3.55.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Yunlong Lake Laboratory of Deep Underground Science and Engineering Project","award":["104024005"],"award-info":[{"award-number":["104024005"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52204177"],"award-info":[{"award-number":["52204177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Funded by the Graduate Innovation Program of China University of Mining and Technology","award":["2024WLKXJ080"],"award-info":[{"award-number":["2024WLKXJ080"]}]},{"name":"Jiangsu Funding Program for Excellent Postdoctoral Talent","award":["2024ZB423"],"award-info":[{"award-number":["2024ZB423"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M763543"],"award-info":[{"award-number":["2024M763543"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcsvt.2026.3662475","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:09:48Z","timestamp":1770671388000},"page":"7846-7859","source":"Crossref","is-referenced-by-count":4,"title":["TGCADNet: Text-Guided Context-Aware Detection via CLIP for Small Objects in UAV Scenes"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4821-1985","authenticated-orcid":false,"given":"Fengqian","family":"Sun","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8831-1994","authenticated-orcid":false,"given":"Deqiang","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9088-1774","authenticated-orcid":false,"given":"Ping","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3592-0651","authenticated-orcid":false,"given":"Tianshu","family":"Song","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9097-0657","authenticated-orcid":false,"given":"Liangliang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2873-2636","authenticated-orcid":false,"given":"Qiqi","family":"Kou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology and the School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3121987"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3077880"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3533019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224580"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3335157"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3038156"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3550726"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3560637"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC51459.2021.9415217"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICNLP58431.2023.00010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118665"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3042065"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647349"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3392794"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3363057"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01291"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3141826"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3516760"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3373033"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3396489"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3549953"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1988"},{"key":"ref26","article-title":"Mind the modality gap: Towards a remote sensing vision-language model via cross-modal alignment","author":"Zavras","year":"2024","journal-title":"arXiv:2402.09816"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02394"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3429"},{"key":"ref29","article-title":"YOLOv12: Attention-centric real-time object detectors","author":"Tian","year":"2025","journal-title":"arXiv:2502.12524"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i15.38217"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref32","article-title":"RT-DETRv2: Improved baseline with bag-of-freebies for real-time detection transformer","author":"Lv","year":"2024","journal-title":"arXiv:2407.17140"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.109966"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-9901-8_4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref36","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","author":"Zhao","year":"2023","journal-title":"arXiv:2305.18010"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3413013"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27939"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3523505"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28518"},{"key":"ref44","article-title":"SegEarth-OV: Towards training-free open-vocabulary segmentation for remote sensing images","author":"Li","year":"2024","journal-title":"arXiv:2410.01768"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32672"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.193"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01266-1"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.002"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3387572"},{"key":"ref51","article-title":"YOLOv13: Real-time object detection with hypergraph-enhanced adaptive visual perception","author":"Lei","year":"2025","journal-title":"arXiv:2506.17733"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3298852"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3228497"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210207"},{"key":"ref56","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","author":"Liu","year":"2022","journal-title":"arXiv:2201.12329"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02280"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32937"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3273314"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19986"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3386928"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3968"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3205052"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284161"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_31"},{"key":"ref66","first-page":"1","article-title":"Context augmentation and feature refinement network for tiny object detection","volume-title":"Proc. ICLR","author":"Xiao"},{"key":"ref67","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01049"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11552944\/11381905.pdf?arnumber=11381905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:28Z","timestamp":1780948468000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11381905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":69,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3662475","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}