{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:15:47Z","timestamp":1788930947067,"version":"build-2803163510"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62102205"],"award-info":[{"award-number":["62102205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576006"],"award-info":[{"award-number":["62576006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Anhui Provincial Natural Science Foundation-Outstanding Youth Project","doi-asserted-by":"publisher","award":["2408085Y032"],"award-info":[{"award-number":["2408085Y032"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3702419","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:46:01Z","timestamp":1781639161000},"page":"6517-6529","source":"Crossref","is-referenced-by-count":3,"title":["Large Language Model Guided Progressive Feature Alignment for Multimodal UAV Object Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0120-6472","authenticated-orcid":false,"given":"Wentao","family":"Wu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7233-2739","authenticated-orcid":false,"given":"Chenglong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5948-5055","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2887342"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3228497"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275538"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3326396"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103948"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3315544"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102246"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-025-00078-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612651"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2958030"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.06.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20351-1_19"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105143"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_30"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02534"},{"key":"ref16","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Song"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3148874"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.73"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.08.005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_46"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"ref27","article-title":"DPDETR: Decoupled position detection transformer for infrared-visible object detection","author":"Guo","year":"2024","journal-title":"arXiv:2408.06123"},{"key":"ref28","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref29","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref30","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Brown"},{"key":"ref31","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv:2303.08774"},{"key":"ref32","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","volume":"1","author":"Kenton"},{"key":"ref33","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"issue":"140","key":"ref34","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25225"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2688"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2026.3678244"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/rs13245128"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3376819"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3386309"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.015"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-15333-w"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108786"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3041316"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3258666"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11568942.pdf?arnumber=11568942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:52:31Z","timestamp":1782330751000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11568942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3702419","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}