{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T10:44:25Z","timestamp":1756896265605,"version":"3.37.3"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61903164","62276061"],"award-info":[{"award-number":["61903164","62276061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF of Jiangsu Province, China","award":["BK20191427"],"award-info":[{"award-number":["BK20191427"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3444900","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T17:23:55Z","timestamp":1723829035000},"page":"114212-114226","source":"Crossref","is-referenced-by-count":3,"title":["Learnable Cross-Scale Sparse Attention Guided Feature Fusion for UAV Object Detection"],"prefix":"10.1109","volume":"12","author":[{"given":"Xin","family":"Zuo","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang, China"}]},{"given":"Chenhui","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang, China"}]},{"given":"Yifei","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic and Informatics Engineering, Jiangsu University, Zhenjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4356-1831","authenticated-orcid":false,"given":"Jifeng","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Electronic and Informatics Engineering, Jiangsu University, Zhenjiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7033-3690","authenticated-orcid":false,"given":"Heng","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of North Texas, Denton, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6385-6776","authenticated-orcid":false,"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation, Southeast University, Nanjing, Jiangsu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759733"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2014.10.007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2491878"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00374"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3381272"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3341806"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref12","first-page":"16965","article-title":"Detrs beat YOLOs on real-time object detection","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zhao"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107917"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967274"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3095305"},{"key":"ref20","article-title":"A normalized Gaussian Wasserstein distance for tiny object detection","author":"Wang","year":"2021","journal-title":"arXiv:2110.13389"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref23","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7347926"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref28","first-page":"1","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/rs15112728"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.04.009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95892-3_31"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/drones8050186"},{"key":"ref36","first-page":"1","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Mnih"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6925"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref44","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref45","article-title":"Focal self-attention for local\u2013global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"arXiv:2107.00641"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.13141"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_5"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_32"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.619"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-11940-1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00090"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2022.1086140"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture13010124"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36868-w"},{"key":"ref61","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.011"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.002"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00103"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00840"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00018"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10638027.pdf?arnumber=10638027","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T04:08:04Z","timestamp":1725250084000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10638027\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3444900","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}