{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T23:11:44Z","timestamp":1778109104251,"version":"3.51.4"},"reference-count":60,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376285"],"award-info":[{"award-number":["62376285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Digital Signal Processing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.dsp.2026.106089","type":"journal-article","created":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T23:37:28Z","timestamp":1774136248000},"page":"106089","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Aero-DETR: Adaptive transformer for high-precision object detection in UAV imagery"],"prefix":"10.1016","volume":"177","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9640-2904","authenticated-orcid":false,"given":"Zongquan","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuxuan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2701-0398","authenticated-orcid":false,"given":"Yun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"11","key":"10.1016\/j.dsp.2026.106089_bib0001","doi-asserted-by":"crossref","first-page":"6047","DOI":"10.1109\/TNNLS.2021.3080276","article-title":"Vehicle detection from UAV imagery with deep learning: a review","volume":"33","author":"Bouguettaya","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.dsp.2026.106089_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121495","article-title":"Application of raycast method for person geolocalization and distance determination using UAV images in real-World land search and rescue scenarios","volume":"237","author":"Paulin","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"9","key":"10.1016\/j.dsp.2026.106089_bib0003","doi-asserted-by":"crossref","first-page":"2283","DOI":"10.1109\/TIM.2017.2700198","article-title":"Medical image fusion and denoising with alternating sequential filter and adaptive fractional order total variation","volume":"66","author":"Zhao","year":"2017","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"6","key":"10.1016\/j.dsp.2026.106089_bib0004","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106089_bib0005","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6154","article-title":"Cascade r-cnn: delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.dsp.2026.106089_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7464","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"10.1016\/j.dsp.2026.106089_bib0007","unstructured":"G. Jocher, A. Chaurasia, J. Qiu, Ultralytics YOLOv8 8.0.0, 2023, ([EB\/OL] Available at: https:\/\/github.com\/ultralytics\/ultralytics). Accessed: 2026-01-24."},{"key":"10.1016\/j.dsp.2026.106089_bib0008","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Yolov9: learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"key":"10.1016\/j.dsp.2026.106089_bib0009","first-page":"107984","article-title":"Yolov10: real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.dsp.2026.106089_bib0010","unstructured":"R. Khanam, M. Hussain, Yolov11: An overview of the key architectural enhancements, (2024). arXiv preprint arXiv: 2410.17725."},{"key":"10.1016\/j.dsp.2026.106089_bib0011","unstructured":"Y. Tian, Q. Ye, D. Doermann, Yolov12: Attention-centric real-time object detectors, (2025). arXiv preprint arXiv: 2502.12524."},{"key":"10.1016\/j.dsp.2026.106089_bib0012","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.dsp.2026.106089_bib0013","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, Deformable detr: Deformable transformers for end-to-end object detection, (2020). arXiv preprint arXiv: 2010.04159."},{"key":"10.1016\/j.dsp.2026.106089_bib0014","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3621","article-title":"Fast convergence of detr with spatially modulated co-attention","author":"Gao","year":"2021"},{"key":"10.1016\/j.dsp.2026.106089_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.dsp.2026.106089_bib0016","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"15162","article-title":"Deim: detr with improved matching for fast convergence","author":"Huang","year":"2025"},{"key":"10.1016\/j.dsp.2026.106089_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13668","article-title":"Querydet: cascaded sparse query for accelerating high-resolution small object detection","author":"Yang","year":"2022"},{"key":"10.1016\/j.dsp.2026.106089_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13435","article-title":"Adaptive sparse convolutional networks with global context enhancement for faster object detection on drone images","author":"Du","year":"2023"},{"key":"10.1016\/j.dsp.2026.106089_bib0019","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8673","article-title":"FBRT-YOLO: Faster and better for real-Time aerial image detection","volume":"39","author":"Xiao","year":"2025"},{"key":"10.1016\/j.dsp.2026.106089_bib0020","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.isprsjprs.2025.06.009","article-title":"Teaching in adverse scenes: a statistically feedback-driven threshold and mask adjustment teacher-student framework for object detection in UAV images under adverse scenes","volume":"227","author":"Chen","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.dsp.2026.106089_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128459","article-title":"MFEL-YOLO For small object detection in UAV aerial images","author":"Hou","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.dsp.2026.106089_bib0022","first-page":"1","article-title":"DTSSNet: Dynamic training sample selection network for UAV object detection","volume":"62","author":"Chen","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.dsp.2026.106089_bib0023","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops","article-title":"Visdrone-DET2019: the vision meets drone object detection in image challenge results","author":"Du","year":"2019"},{"issue":"10","key":"10.1016\/j.dsp.2026.106089_bib0024","doi-asserted-by":"crossref","first-page":"13863","DOI":"10.1109\/TITS.2024.3386928","article-title":"Yolc: you only look clusters for tiny object detection in aerial images","volume":"25","author":"Liu","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.dsp.2026.106089_bib0025","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6569","article-title":"Centernet: keypoint triplets for object detection","author":"Duan","year":"2019"},{"key":"10.1016\/j.dsp.2026.106089_bib0026","first-page":"1","article-title":"Aodet: aerial object detection using transformers for foreground regions","volume":"62","author":"Wang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.dsp.2026.106089_bib0027","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2024.3481415","article-title":"No-Extra components density map cropping guided object detection in aerial images","author":"Guo","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.dsp.2026.106089_bib0028","first-page":"1","article-title":"Full-scale feature aggregation and grouping feature reconstruction-based UAV image target detection","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.dsp.2026.106089_bib0029","article-title":"Global-Local fusion with semantic information-Guidance for accurate small object detection in UAV aerial images","author":"Chen","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.dsp.2026.106089_bib0030","article-title":"OWRT-DETR: A novel real-Time transformer network for small object detection in open water search and rescue from UAV aerial imagery","author":"Ma","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.dsp.2026.106089_bib0031","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.dsp.2026.106089_bib0032","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: Transformers for image recognition at scale, (2020). arXiv preprint arXiv: 2010.11929."},{"key":"10.1016\/j.dsp.2026.106089_bib0033","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3651","article-title":"Conditional detr for fast training convergence","author":"Meng","year":"2021"},{"key":"10.1016\/j.dsp.2026.106089_bib0034","unstructured":"S. Liu, F. Li, H. Zhang, X. Yang, X. Qi, H. Su, J. Zhu, L. Zhang, Dab-detr: Dynamic anchor boxes are better queries for detr, (2022). arXiv preprint arXiv: 2201.12329."},{"key":"10.1016\/j.dsp.2026.106089_bib0035","unstructured":"W. Lv, Y. Zhao, Q. Chang, K. Huang, G. Wang, Y. Liu, Rt-detrv2: Improved baseline with bag-of-freebies for real-time detection transformer, (2024). arXiv preprint arXiv: 2407.17140."},{"key":"10.1016\/j.dsp.2026.106089_bib0036","series-title":"2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","first-page":"1628","article-title":"RT-DETRv3: Real-time end-to-end object detection with hierarchical dense positive supervision","author":"Wang","year":"2025"},{"key":"10.1016\/j.dsp.2026.106089_bib0037","unstructured":"Y. Peng, H. Li, P. Wu, Y. Zhang, X. Sun, F. Wu, D-FINE: Redefine regression task in DETRs as fine-grained distribution refinement, (2024). arXiv preprint arXiv: 2410.13842."},{"key":"10.1016\/j.dsp.2026.106089_bib0038","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"9933","article-title":"Mr. detr: instructive multi-route training for detection transformers","author":"Zhang","year":"2025"},{"key":"10.1016\/j.dsp.2026.106089_bib0039","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.dsp.2026.106089_bib0040","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"10.1016\/j.dsp.2026.106089_bib0041","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10781","article-title":"Efficientdet: scalable and efficient object detection","author":"Tan","year":"2020"},{"issue":"1","key":"10.1016\/j.dsp.2026.106089_bib0042","first-page":"223","article-title":"Drone detection method based on mobilevit and CA-PANet","volume":"12","author":"Cheng","year":"2023","journal-title":"Electronics (Basel)"},{"key":"10.1016\/j.dsp.2026.106089_bib0043","first-page":"1","article-title":"SSPNet: Scale selection pyramid network for tiny person detection from UAV images","volume":"19","author":"Hong","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"issue":"5","key":"10.1016\/j.dsp.2026.106089_bib0044","doi-asserted-by":"crossref","first-page":"907","DOI":"10.3390\/rs16050907","article-title":"Object detection in remote sensing images based on adaptive multi-scale feature fusion method","volume":"16","author":"Liu","year":"2024","journal-title":"Remote Sens. (Basel)"},{"issue":"1","key":"10.1016\/j.dsp.2026.106089_bib0045","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1007\/s00371-024-03355-w","article-title":"E-FPN: An enhanced feature pyramid network for UAV scenarios detection","volume":"41","author":"Li","year":"2025","journal-title":"Vis. Comput."},{"key":"10.1016\/j.dsp.2026.106089_bib0046","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"390","article-title":"CSPNet: A new backbone that can enhance learning capability of CNN","author":"Wang","year":"2020"},{"key":"10.1016\/j.dsp.2026.106089_bib0047","unstructured":"X. Yuan, Z. Zheng, Y. Li, X. Liu, L. Liu, X. Li, Q. Hou, M.-M. Cheng, Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection, 2025, https:\/\/arxiv.org\/abs\/2501.03775."},{"key":"10.1016\/j.dsp.2026.106089_bib0048","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6027","article-title":"Learning to upsample by learning to sample","author":"Liu","year":"2023"},{"key":"10.1016\/j.dsp.2026.106089_bib0049","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"370","article-title":"The unmanned aerial vehicle benchmark: object detection and tracking","author":"Du","year":"2018"},{"key":"10.1016\/j.dsp.2026.106089_bib0050","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"3490","article-title":"Tood: task-aligned one-stage object detection","author":"Feng","year":"2021"},{"key":"10.1016\/j.dsp.2026.106089_bib0051","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"8311","article-title":"Clustered object detection in aerial images","author":"Yang","year":"2019"},{"key":"10.1016\/j.dsp.2026.106089_bib0052","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"190","article-title":"Density map guided object detection in aerial images","author":"Li","year":"2020"},{"key":"10.1016\/j.dsp.2026.106089_bib0053","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2789","article-title":"Coarse-grained density map guided object detection in aerial images","author":"Duan","year":"2021"},{"key":"10.1016\/j.dsp.2026.106089_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111978","article-title":"Dynamic selection of gaussian samples for object detection on drone images via shape sensing","volume":"170","author":"Li","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.dsp.2026.106089_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113253","article-title":"A lightweight object detection method based on fine-grained information extraction and exchange in UAV aerial images","volume":"315","author":"Zhou","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.dsp.2026.106089_bib0056","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.dsp.2026.106089_bib0057","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"issue":"3","key":"10.1016\/j.dsp.2026.106089_bib0058","doi-asserted-by":"crossref","first-page":"1410","DOI":"10.1007\/s11263-024-02247-9","article-title":"LSKNet: A foundation lightweight backbone for remote sensing: y. li et al","volume":"133","author":"Li","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.dsp.2026.106089_bib0059","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12021","article-title":"Run, don\u2019t walk: chasing higher FLOPS for faster neural networks","author":"Chen","year":"2023"},{"key":"10.1016\/j.dsp.2026.106089_bib0060","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14420","article-title":"Efficientvit: memory efficient vision transformer with cascaded group attention","author":"Liu","year":"2023"}],"container-title":["Digital Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1051200426002083?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1051200426002083?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T22:25:41Z","timestamp":1778106341000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1051200426002083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":60,"alternative-id":["S1051200426002083"],"URL":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106089","relation":{},"ISSN":["1051-2004"],"issn-type":[{"value":"1051-2004","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Aero-DETR: Adaptive transformer for high-precision object detection in UAV imagery","name":"articletitle","label":"Article Title"},{"value":"Digital Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106089","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106089"}}