{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:43:08Z","timestamp":1778251388488,"version":"3.51.4"},"reference-count":46,"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":[{"name":"Shenzhen Science and Technology Program","award":["JCYJ20240813105135047"],"award-info":[{"award-number":["JCYJ20240813105135047"]}]},{"name":"Taizhou Shenzhen Innovation Center Project","award":["TSC202501"],"award-info":[{"award-number":["TSC202501"]}]},{"name":"National Natural Science Funds for Distinguished Young Scholars","award":["62325307"],"award-info":[{"award-number":["62325307"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62527809"],"award-info":[{"award-number":["62527809"]}],"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.2026.3661868","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:57:46Z","timestamp":1770843466000},"page":"1870-1882","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive Fine-Grained Fusion Network for Multimodal UAV Object Detection"],"prefix":"10.1109","volume":"35","author":[{"given":"Zhanyan","family":"Tang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2704-0614","authenticated-orcid":false,"given":"Zhihao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7327-3304","authenticated-orcid":false,"given":"Mu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9554-2379","authenticated-orcid":false,"given":"Jie","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-9519","authenticated-orcid":false,"given":"Bob","family":"Zhang","sequence":"additional","affiliation":[{"name":"PAMI Research Group, Department of Computer and Information Science, University of Macau, Taipa, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-2123","authenticated-orcid":false,"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2208-962X","authenticated-orcid":false,"given":"Jianqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3045636"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3228497"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3501853"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3297408"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3198577"},{"key":"ref6","first-page":"17675","article-title":"MC-bench: A benchmark for multi-context visual grounding in the era of MLLMs","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Xu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3261752"},{"key":"ref8","article-title":"Multi-modal UAV detection, classification and tracking algorithm - technical report for CVPR 2024 UG2 challenge","volume-title":"arXiv:2405.16464","author":"Deng","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3373816"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3367934"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103918"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3183022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00472"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3077058"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00319"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968555"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3075747"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2021.3100986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s42401-022-00162-w"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-021-01111-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/1729881419842995"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-024-09188-y"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109913"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00914"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref34","volume-title":"YOLOv5","author":"Jocher et al","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00523"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3258666"},{"key":"ref40","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021","journal-title":"arXiv:2111.00273"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108786"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"ref45","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","year":"2019","journal-title":"arXiv:1907.07484"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3548704"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11393654.pdf?arnumber=11393654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T05:54:20Z","timestamp":1771307660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11393654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3661868","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}