{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T12:10:23Z","timestamp":1779451823137,"version":"3.53.1"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62071474"],"award-info":[{"award-number":["62071474"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.knosys.2026.115788","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T09:32:48Z","timestamp":1773826368000},"page":"115788","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["D2-DETR:DETR With Dual-Domain frequency-spatial modeling for unmanned aerial vehicle imagery object detection"],"prefix":"10.1016","volume":"341","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3646-6645","authenticated-orcid":false,"given":"Xuanming","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6182-4877","authenticated-orcid":false,"given":"Huanxin","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyuan","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shitian","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangshan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115788_bib0001","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1440","article-title":"Fast r-cnn","author":"Girshick","year":"2015"},{"key":"10.1016\/j.knosys.2026.115788_bib0002","series-title":"European Conference on Computer Vision","first-page":"21","article-title":"Ssd: single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.knosys.2026.115788_bib0003","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.knosys.2026.115788_bib0004","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.knosys.2026.115788_bib0005","series-title":"9Th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","article-title":"Deformable DETR: deformable transformers for end-to-End object detection","author":"Zhu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115788_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13619","article-title":"Dn-detr: accelerate detr training by introducing query denoising","author":"Li","year":"2022"},{"key":"10.1016\/j.knosys.2026.115788_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2022.103620","article-title":"Improving small objects detection using transformer","volume":"89","author":"Dubey","year":"2022","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.knosys.2026.115788_bib0008","series-title":"European Conference on Computer Vision","first-page":"290","article-title":"Dq-detr: detr with dynamic query for tiny object detection","author":"Huang","year":"2024"},{"key":"10.1016\/j.knosys.2026.115788_bib0009","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2988","article-title":"Dynamic detr: end-to-end object detection with dynamic attention","author":"Dai","year":"2021"},{"key":"10.1016\/j.knosys.2026.115788_bib0010","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"},{"issue":"6","key":"10.1016\/j.knosys.2026.115788_bib0011","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.knosys.2026.115788_bib0012","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9627","article-title":"Fcos: fully convolutional one-stage object detection","author":"Tian","year":"2019"},{"key":"10.1016\/j.knosys.2026.115788_bib0013","first-page":"4479","article-title":"Fast fourier convolution","volume":"33","author":"Chi","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115788_bib0014","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"12504","article-title":"Retinexformer: one-stage retinex-based transformer for low-light image enhancement","author":"Cai","year":"2023"},{"key":"10.1016\/j.knosys.2026.115788_bib0015","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5896","article-title":"Learning a sparse transformer network for effective image deraining","author":"Chen","year":"2023"},{"key":"10.1016\/j.knosys.2026.115788_bib0016","series-title":"European Conference on Computer Vision","first-page":"146","article-title":"Stripformer: strip transformer for fast image deblurring","author":"Tsai","year":"2022"},{"key":"10.1016\/j.knosys.2026.115788_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"17683","article-title":"Uformer: a general u-shaped transformer for image restoration","author":"Wang","year":"2022"},{"key":"10.1016\/j.knosys.2026.115788_bib0018","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"2149","article-title":"Resolution-robust large mask inpainting with fourier convolutions","author":"Suvorov","year":"2022"},{"key":"10.1016\/j.knosys.2026.115788_bib0019","series-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023","article-title":"Selective frequency network for image restoration","author":"Cui","year":"2023"},{"key":"10.1016\/j.knosys.2026.115788_bib0020","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.knosys.2026.115788_bib0021","unstructured":"J. Ma, B. Chen, Dual Refinement Feature Pyramid Networks for Object Detection, CoRR abs\/2012.01733(2020). https:\/\/arxiv.org\/abs\/2012.01733. 2012.01733."},{"key":"10.1016\/j.knosys.2026.115788_bib0022","doi-asserted-by":"crossref","first-page":"2678","DOI":"10.1109\/TIP.2023.3272826","article-title":"Tripartite feature enhanced pyramid network for dense prediction","volume":"32","author":"Liu","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.knosys.2026.115788_bib0023","first-page":"1","article-title":"FSANet: Feature-and-spatial-aligned network for tiny object detection in remote sensing images","volume":"60","author":"Wu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.knosys.2026.115788_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2020.103910","article-title":"Recent advances in small object detection based on deep learning: a review","volume":"97","author":"Tong","year":"2020","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.knosys.2026.115788_bib0025","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.knosys.2026.115788_bib0026","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"},{"issue":"5","key":"10.1016\/j.knosys.2026.115788_bib0027","doi-asserted-by":"crossref","first-page":"108","DOI":"10.3390\/drones6050108","article-title":"Lightweight detection network for arbitrary-oriented vehicles in UAV imagery via global attentive relation and multi-path fusion","volume":"6","author":"Feng","year":"2022","journal-title":"Drones"},{"key":"10.1016\/j.knosys.2026.115788_bib0028","series-title":"2024IEEE International Conference on Robotics and Automation (ICRA)","first-page":"6614","article-title":"HIC-YOLOv5: Improved YOLOv5 for small object detection","author":"Tang","year":"2024"},{"key":"10.1016\/j.knosys.2026.115788_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2020.104046","article-title":"Deep learning-based object detection in low-altitude UAV datasets: a survey","volume":"104","author":"Mittal","year":"2020","journal-title":"Image Vis. Comput."},{"issue":"3","key":"10.1016\/j.knosys.2026.115788_bib0030","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.3390\/s23031261","article-title":"Multiple attention mechanism enhanced YOLOX for remote sensing object detection","volume":"23","author":"Shen","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.knosys.2026.115788_bib0031","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114602","article-title":"A survey and performance evaluation of deep learning methods for small object detection","volume":"172","author":"Liu","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115788_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"467","article-title":"Nl-ffc: non-local fast fourier convolution for image super resolution","author":"Sinha","year":"2022"},{"key":"10.1016\/j.knosys.2026.115788_bib0033","series-title":"European Conference on Computer Vision","first-page":"257","article-title":"Learning spatiotemporal frequency-transformer for compressed video super-resolution","author":"Qiu","year":"2022"},{"key":"10.1016\/j.knosys.2026.115788_bib0034","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5886","article-title":"Efficient frequency domain-based transformers for high-quality image deblurring","author":"Kong","year":"2023"},{"key":"10.1016\/j.knosys.2026.115788_bib0035","series-title":"International Conference on Machine Learning","first-page":"42589","article-title":"Fourmer: an efficient global modeling paradigm for image restoration","author":"Zhou","year":"2023"},{"key":"10.1016\/j.knosys.2026.115788_bib0036","article-title":"SAFF-DETR: An end-to-end object detection network for remote sensing images with targets of varying sizes based on scale adaptation and frequency fusion","author":"Zhi","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.knosys.2026.115788_bib0037","unstructured":"H. Zhang, K. Liu, Z. Gan, G. Zhu, UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery, CoRR abs\/2501.01855(2025). 2501.0185510.48550\/ARXIV.2501.01855."},{"key":"10.1016\/j.knosys.2026.115788_bib0038","unstructured":"B. Gao, J. Tong, X. Chen, H. Yu, Z. Li, DFIR-DETR: Frequency Domain Enhancement and Dynamic Feature Aggregation for Cross-Scene Small Object Detection, arXiv preprint arXiv: 2512.07078(2025)."},{"issue":"10","key":"10.1016\/j.knosys.2026.115788_bib0039","doi-asserted-by":"crossref","first-page":"523","DOI":"10.3390\/drones8100523","article-title":"Amfef-detr: an end-to-end adaptive multi-scale feature extraction and fusion object detection network based on uav aerial images","volume":"8","author":"Wang","year":"2024","journal-title":"Drones"},{"key":"10.1016\/j.knosys.2026.115788_bib0040","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1160","article-title":"Effective fusion factor in FPN for tiny object detection","author":"Gong","year":"2021"},{"key":"10.1016\/j.knosys.2026.115788_bib0041","article-title":"Local to global: a sparse transformer-based small object detector for remote sensing images","author":"Li","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"4","key":"10.1016\/j.knosys.2026.115788_bib0042","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1109\/TAI.2022.3178062","article-title":"Towards disturbance rejection in feature pyramid network","volume":"4","author":"Hu","year":"2022","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.115788_bib0043","first-page":"4137","article-title":"Spatial-frequency channels, shape bias, and adversarial robustness","volume":"36","author":"Subramanian","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115788_bib0044","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"658","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"10.1016\/j.knosys.2026.115788_bib0045","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.knosys.2026.115788_bib0046","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25\u201329, 2022","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","author":"Liu","year":"2022"},{"issue":"11","key":"10.1016\/j.knosys.2026.115788_bib0047","doi-asserted-by":"crossref","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","article-title":"Detection and tracking meet drones challenge","volume":"44","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115788_bib0048","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.knosys.2026.115788_bib0049","series-title":"2021IEEE\/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.knosys.2026.115788_bib0050","unstructured":"C. Lyu, W. Zhang, H. Huang, Y. Zhou, Y. Wang, Y. Liu, S. Zhang, K. Chen, RTMDet: An Empirical Study of Designing Real-Time Object Detectors, CoRR abs\/2212.07784(2022). 2212.0778410.48550\/ARXIV.2212.07784."},{"key":"10.1016\/j.knosys.2026.115788_bib0051","unstructured":"Z. Yao, J. Ai, B. Li, C. Zhang, Efficient DETR: Improving End-to-End Object Detector with Dense Prior, CoRR abs\/2104.01318(2021). https:\/\/arxiv.org\/abs\/2104.01318. 2104.01318."},{"key":"10.1016\/j.knosys.2026.115788_bib0052","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"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005149?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005149?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T11:43:44Z","timestamp":1779450224000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126005149"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":52,"alternative-id":["S0950705126005149"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115788","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"D2-DETR:DETR With Dual-Domain frequency-spatial modeling for unmanned aerial vehicle imagery object detection","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115788","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115788"}}