{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T04:45:50Z","timestamp":1781239550391,"version":"3.54.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2018AAA0101000"],"award-info":[{"award-number":["2018AAA0101000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076028"],"award-info":[{"award-number":["62076028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3572706","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T17:59:49Z","timestamp":1747936789000},"page":"1-14","source":"Crossref","is-referenced-by-count":49,"title":["Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7091-8159","authenticated-orcid":false,"given":"Zewen","family":"Du","sequence":"first","affiliation":[{"name":"National Key Laboratory of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenjiang","family":"Hu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guiyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Jin","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5734-3157","authenticated-orcid":false,"given":"Hongbin","family":"Ma","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Autonomous Intelligent Unmanned Systems, School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00030"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093394"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3045636"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3210207"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref7","article-title":"Feature pyramid grids","author":"Chen","year":"2020","journal-title":"arXiv:2004.03580"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53992.2023.10394415"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref13","first-page":"91","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref15","article-title":"YOLOv10: Real-time end-to-end object detection","author":"Wang","year":"2024","journal-title":"arXiv:2405.14458"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00840"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00103"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66823-5_39"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3348555"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3203476"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3256064"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680789"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","first-page":"68","article-title":"Stand-alone self-attention in vision models","volume-title":"Proc. Advances Neural Inf. Process. Syst.","volume":"32","author":"Ramachandran"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"ref32","article-title":"Axial attention in multidimensional transformers","author":"Ho","year":"2019","journal-title":"arXiv:1912.12180"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref35","article-title":"Dual refinement feature pyramid networks for object detection","author":"Ma","year":"2020","journal-title":"arXiv:2012.01733"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475708"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3103069"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01160"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00093"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref43","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Li"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref49","article-title":"CtxMIM: Context-enhanced masked image modeling for remote sensing image understanding","author":"Zhang","year":"2023","journal-title":"arXiv:2310.00022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref51","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.07155"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00509"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11010850.pdf?arnumber=11010850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:56:32Z","timestamp":1749059792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11010850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3572706","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}