{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:24:40Z","timestamp":1778048680213,"version":"3.51.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T00:00:00Z","timestamp":1771459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T00:00:00Z","timestamp":1771459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Natural ScienceFoundation of China","award":["62376114"],"award-info":[{"award-number":["62376114"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-026-08308-9","type":"journal-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T17:47:52Z","timestamp":1771523272000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ERS-DETR: a lightweight real-time transformer for remote sensing small target detection with enhanced feature fusion and dual-frequency encoding"],"prefix":"10.1007","volume":"82","author":[{"given":"Zongmin","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youlin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huakun","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhui","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,19]]},"reference":[{"key":"8308_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3249247","volume":"72","author":"S Li","year":"2023","unstructured":"Li S, Yu J, Wang H (2023) Damages detection of aeroengine blades via deep learning algorithms. IEEE Trans Instrum Meas 72:1\u201311. https:\/\/doi.org\/10.1109\/TIM.2023.3249247","journal-title":"IEEE Trans Instrum Meas"},{"key":"8308_CR2","doi-asserted-by":"publisher","unstructured":"Jocher G et al. (2020) ultralytics\/yolov5: v3.1-bug fixes and performance improvements. Zenodo.https:\/\/doi.org\/10.5281\/zenodo.4154370","DOI":"10.5281\/zenodo.4154370"},{"key":"8308_CR3","unstructured":"Li C et al. (2022) YOLOv6: a single-stage object detection framework for industrial applications. https:\/\/arxiv.org\/abs\/2209.02976"},{"key":"8308_CR4","doi-asserted-by":"publisher","unstructured":"Reis D, Kupec J, Hong J, Daoudi A (2023) Real-time flying object detection with YOLOv8. https:\/\/doi.org\/10.48550\/arXiv.2305.09972","DOI":"10.48550\/arXiv.2305.09972"},{"key":"8308_CR5","first-page":"107984","volume":"37","author":"A Wang","year":"2024","unstructured":"Wang A, Chen H, Liu L, Chen K, Lin Z, Han J (2024) Yolov10: real-time end-to-end object detection. Neural Inf Process Syst 37:107984\u2013108011","journal-title":"Neural Inf Process Syst"},{"key":"8308_CR6","unstructured":"Vaswani A et al. (2017) Attention is all you need. Neural Inf Process Syst 30"},{"key":"8308_CR7","doi-asserted-by":"publisher","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European Conference on Computer Vision, pp 213\u2013229. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"8308_CR8","doi-asserted-by":"crossref","unstructured":"Zhao Y et al. (2024). DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 16965\u201316974","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"8308_CR9","doi-asserted-by":"publisher","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable DETR: deformable transformers for end-to-end object detection. https:\/\/doi.org\/10.48550\/arXiv.2010.04159","DOI":"10.48550\/arXiv.2010.04159"},{"key":"8308_CR10","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. Neural Inf Process Syst 28"},{"key":"8308_CR11","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017). Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"8308_CR12","doi-asserted-by":"crossref","unstructured":"Paz D, Zhang H, Christensen HI (2021) TridentNet: a conditional generative model for dynamic trajectory generation. In: International Conference on Intelligent Autonomous Systems, pp 403\u2013416","DOI":"10.1007\/978-3-030-95892-3_31"},{"key":"8308_CR13","doi-asserted-by":"publisher","unstructured":"Liu W et al (2016) SSD: single shot MultiBox detector. In: European Conference on Computer Vision, pp 21\u201337. https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"8308_CR14","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"8308_CR15","doi-asserted-by":"publisher","unstructured":"Zhang H, Li F, Liu S, Zhang L, Su H, Zhu J, et al. (2022) DINO: DETR with improved denoising anchor boxes for end-to-end object detection. https:\/\/doi.org\/10.48550\/arXiv.2203.03605","DOI":"10.48550\/arXiv.2203.03605"},{"issue":"3","key":"8308_CR16","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1007\/s00371-023-02886-y","volume":"40","author":"S Zeng","year":"2024","unstructured":"Zeng S, Yang W, Jiao Y, Geng L, Chen X (2024) SCA-YOLO: A new small object detection model for UAV images. Vis Comput 40(3):1787\u2013803. https:\/\/doi.org\/10.1007\/s00371-023-02886-y","journal-title":"Vis Comput"},{"key":"8308_CR17","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/s12145-025-01808-x","volume":"18","author":"H Luo","year":"2025","unstructured":"Luo H, Yuqi W, Youlin C, Xi L, Jianhui Z, Deng Z (2025) EBC-YOLO: a remote sensing target recognition model adapted for complex environments. Earth Sci Inf 18:282. https:\/\/doi.org\/10.1007\/s12145-025-01808-x","journal-title":"Earth Sci Inf"},{"key":"8308_CR18","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1609\/aaai.v36i1.19986","volume":"36","author":"Y Huang","year":"2022","unstructured":"Huang Y, Chen J, Huang D (2022) UFPMP-Det: toward accurate and efficient object detection on drone imagery. Proc AAAI Conf Artif Intell 36:1026\u20131033. https:\/\/doi.org\/10.1609\/aaai.v36i1.19986","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"8308_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2025.3617006","volume":"63","author":"Q Zhu","year":"2025","unstructured":"Zhu Q, Li K, Zhang G, Wang X, Huang J, Li X (2025) GDSR: global-detail integration through dual-branch network with wavelet losses for remote sensing image super-resolution. IEEE Trans Geosci Remote Sens 63:1\u201316. https:\/\/doi.org\/10.1109\/TGRS.2025.3617006","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"17","key":"8308_CR20","doi-asserted-by":"publisher","first-page":"5496","DOI":"10.3390\/s24175496","volume":"24","author":"Y Kong","year":"2024","unstructured":"Kong Y, Shang X, Jia S (2024) Drone-DETR: efficient small object detection for remote sensing image using enhanced RT-DETR model. Sensors 24(17):5496. https:\/\/doi.org\/10.3390\/s24175496","journal-title":"Sensors"},{"key":"8308_CR21","doi-asserted-by":"publisher","first-page":"523","DOI":"10.3390\/drones8100523","volume":"8","author":"S Wang","year":"2024","unstructured":"Wang S, Jiang H, Yang J, Ma X, Chen J (2024) AMFEF-DETR: an end-to-end adaptive multi-scale feature extraction and fusion object detection network based on UAV aerial images. Drones 8:523. https:\/\/doi.org\/10.3390\/drones8100523","journal-title":"Drones"},{"key":"8308_CR22","doi-asserted-by":"publisher","first-page":"3404","DOI":"10.3390\/electronics13173404","volume":"13","author":"X Cao","year":"2024","unstructured":"Cao X, Wang H, Wang X, Hu B (2024) DFS-DETR: detailed-feature-sensitive detector for small object detection in aerial images using transformer. Electronics 13:3404. https:\/\/doi.org\/10.3390\/electronics13173404","journal-title":"Electronics"},{"key":"8308_CR23","first-page":"14541","volume":"35","author":"Z Pan","year":"2022","unstructured":"Pan Z, Cai J, Zhuang B (2022) Fast vision transformers with HiLo attention. Neural Inf Process Syst 35:14541\u201314554","journal-title":"Neural Inf Process Syst"},{"key":"8308_CR24","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.3390\/agronomy14122887","volume":"14","author":"S Wang","year":"2024","unstructured":"Wang S, Chen D, Xiang J, Zhang C (2024) A deep-learning-based detection method for small target tomato pests in insect traps. Agronomy 14:2887. https:\/\/doi.org\/10.3390\/agronomy14122887","journal-title":"Agronomy"},{"key":"8308_CR25","doi-asserted-by":"publisher","first-page":"4628","DOI":"10.3390\/s24144628","volume":"24","author":"Z Liu","year":"2024","unstructured":"Liu Z, Sun C, Wang X (2024) DST-DETR: image dehazing RT-DETR for safety helmet detection in foggy weather. Sensors 24:4628. https:\/\/doi.org\/10.3390\/s24144628","journal-title":"Sensors"},{"key":"8308_CR26","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 658\u2013666","DOI":"10.1109\/CVPR.2019.00075"},{"key":"8308_CR27","doi-asserted-by":"publisher","first-page":"12993","DOI":"10.1609\/aaai.v34i07.6999","volume":"34","author":"Z Zheng","year":"2020","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2020) Distance-IoU loss: faster and better learning for bounding box regression. Proc AAAI Conf Artif Intell 34:12993\u201313000. https:\/\/doi.org\/10.1609\/aaai.v34i07.6999","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"8308_CR28","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1016\/j.neunet.2023.11.041","volume":"170","author":"L Can","year":"2024","unstructured":"Can L, Kaige W, Qing L, Fazhan Z, Kun Z, Hongtu M (2024) Powerful-IoU: more straightforward and faster bounding box regression loss with a nonmonotonic focusing mechanism. Neural Netw 170:276\u2013284. https:\/\/doi.org\/10.1016\/j.neunet.2023.11.041","journal-title":"Neural Netw"},{"key":"8308_CR29","doi-asserted-by":"publisher","unstructured":"Ma S, Xu Y (2023) MPDIoU: a loss for efficient and accurate bounding box regression. arXiv preprint.https:\/\/doi.org\/10.48550\/arXiv.2307.07662","DOI":"10.48550\/arXiv.2307.07662"},{"key":"8308_CR30","doi-asserted-by":"publisher","unstructured":"Zhang H, Zhang S (2024) Focaler-IoU: more focused intersection over union loss. arXiv preprint.https:\/\/doi.org\/10.48550\/arXiv.2401.10525","DOI":"10.48550\/arXiv.2401.10525"},{"key":"8308_CR31","doi-asserted-by":"publisher","unstructured":"Zhang, H, Zhang S Shape-IoU: more accurate metric considering bounding box shape and scale. https:\/\/doi.org\/10.48550\/arXiv.2312.17663","DOI":"10.48550\/arXiv.2312.17663"},{"key":"8308_CR32","doi-asserted-by":"publisher","unstructured":"Zheng M, Sun L, Dong J, Pan J (2024) SMFANet: a lightweight self-modulation feature aggregation network for efficient image super-resolution. In: European Conference on Computer Vision, pp 359\u2013375. https:\/\/doi.org\/10.1007\/978-3-031-72973-7_21","DOI":"10.1007\/978-3-031-72973-7_21"},{"key":"8308_CR33","doi-asserted-by":"publisher","unstructured":"Cai X, Lai Q, Wang Y, Wang W, Sun Z, Yao Y (2024) Poly kernel inception network for remote sensing detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 27706\u201327716. https:\/\/doi.org\/10.1109\/CVPR52733.2024.02617","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"8308_CR34","doi-asserted-by":"publisher","first-page":"9528","DOI":"10.1109\/TNNLS.2022.3151138","volume":"34","author":"J Zhong","year":"2022","unstructured":"Zhong J, Chen J, Mian A (2022) DualConv: dual convolutional kernels for lightweight deep neural networks. IEEE Trans Neural Netw Learn Syst 34:9528\u20139535. https:\/\/doi.org\/10.1109\/TNNLS.2022.3151138","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"8308_CR35","doi-asserted-by":"publisher","unstructured":"Jiang X, Zhang X, Gao N, Deng Y (2024) When fast Fourier transform meets transformer for image restoration. In: European Conference on Computer Vision, pp 381\u2013402. https:\/\/doi.org\/10.1007\/978-3-031-72995-9_22","DOI":"10.1007\/978-3-031-72995-9_22"},{"key":"8308_CR36","doi-asserted-by":"publisher","unstructured":"Zhang J et al. (2023) Rethinking mobile block for efficient attention-based models. In: International Conference on Computer Vision, pp 1389\u20131400. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00134","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"8308_CR37","doi-asserted-by":"publisher","unstructured":"Adarsh P, Rathi P, Kumar M (2020) YOLO v3-Tiny: object detection and recognition using one stage improved model. In: 2020 6th International Conference on Advanced Computing and Communication Systems, pp 687\u2013694. https:\/\/doi.org\/10.1109\/10.1109\/ICACCS48705.2020.9074315","DOI":"10.1109\/10.1109\/ICACCS48705.2020.9074315"},{"key":"8308_CR38","doi-asserted-by":"publisher","unstructured":"Wang C-Y, Yeh I-H, Mark Liao H-Y (2024) Yolov9: learning what you want to learn using programmable gradient information. In: European Conference on Computer Vision, pp 1\u201321. https:\/\/doi.org\/10.1007\/978-3-031-72751-1_1","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"8308_CR39","doi-asserted-by":"publisher","unstructured":"Yao Z, Ai J, Li B, Zhang C (2021) Efficient DETR: improving end-to-end object detector with dense prior. https:\/\/doi.org\/10.48550\/arXiv.2104.01318","DOI":"10.48550\/arXiv.2104.01318"},{"key":"8308_CR40","doi-asserted-by":"publisher","first-page":"3057","DOI":"10.3390\/rs16163057","volume":"16","author":"Y Li","year":"2024","unstructured":"Li Y, Li Q, Pan J, Zhou Y, Zhu H, Wei H, Liu C (2024) SOD-YOLO: small-object-detection algorithm based on improved YOLOv8 for UAV images. Remote Sens 16:3057. https:\/\/doi.org\/10.3390\/rs16163057","journal-title":"Remote Sens"},{"issue":"5","key":"8308_CR41","doi-asserted-by":"publisher","first-page":"053048","DOI":"10.1117\/1.JEI.34.5.053048","volume":"34","author":"Y Han","year":"2025","unstructured":"Han Y, Sen Y, Zenghui W, Jigang T (2025) LES-DETR: lightweight enhanced detection transformer for UAV small targets. J Electron Imaging 34(5):053048. https:\/\/doi.org\/10.1117\/1.JEI.34.5.053048","journal-title":"J Electron Imaging"},{"key":"8308_CR42","doi-asserted-by":"publisher","unstructured":"Wang D, Xu R, Han Q, Ye F, Liang Q (2025) DPLR-DETR: small object detection model for UAV aerial imagery. In: 2025 5th International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA), pp 76\u201381. https:\/\/doi.org\/10.1109\/CAIBDA65784.2025.11183415","DOI":"10.1109\/CAIBDA65784.2025.11183415"},{"key":"8308_CR43","first-page":"51094","volume":"36","author":"C Wang","year":"2023","unstructured":"Wang C, He W, Nie Y, Guo J, Liu C, Wang Y et al (2023) Gold-YOLO: efficient object detector via gather-and-distribute mechanism. Adv Neural Inf Process Syst 36:51094\u2013112","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08308-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-026-08308-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08308-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T17:47:56Z","timestamp":1771523276000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-026-08308-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,19]]},"references-count":43,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["8308"],"URL":"https:\/\/doi.org\/10.1007\/s11227-026-08308-9","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,19]]},"assertion":[{"value":"29 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"183"}}