{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:03:00Z","timestamp":1784764980548,"version":"3.55.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":64,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Jiaxing Public Welfare Research Project","award":["2025CGW075"],"award-info":[{"award-number":["2025CGW075"]}]},{"name":"Jiaxing Team Science and Technology Commissioner Project","award":["K2024-1-1-06"],"award-info":[{"award-number":["K2024-1-1-06"]}]},{"name":"General Scientific Research Project of Zhejiang Provincial Department of Education","award":["Y202456753"],"award-info":[{"award-number":["Y202456753"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-53405-7","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T14:45:35Z","timestamp":1779288335000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient UAV object detection using spectro-spatial synergistic learning and implicit recursive refinement"],"prefix":"10.1038","volume":"16","author":[{"given":"Xiaoji","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongbin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bilu","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JunHao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"key":"53405_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_23","author":"D Du","year":"2018","unstructured":"Du, D. et al. The unmanned aerial vehicle benchmark: Object detection and tracking. ECCV https:\/\/doi.org\/10.1007\/978-3-030-01249-6_23 (2018).","journal-title":"ECCV"},{"key":"53405_CR2","unstructured":"Zhu, P. et al. Vision meets drones: A challenge. https:\/\/arXiv.org\/abs\/1804.07437 (2018)."},{"key":"53405_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169","author":"R Girshick","year":"2015","unstructured":"Girshick, R. Fast r-cnn. ICCV https:\/\/doi.org\/10.1109\/ICCV.2015.169 (2015).","journal-title":"ICCV"},{"key":"53405_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106","author":"T-Y Lin","year":"2017","unstructured":"Lin, T.-Y. et al. Feature pyramid networks for object detection. CVPR https:\/\/doi.org\/10.1109\/CVPR.2017.106 (2017).","journal-title":"CVPR"},{"key":"53405_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324","author":"T-Y Lin","year":"2017","unstructured":"Lin, T.-Y. et al. Focal loss for dense object detection. ICCV https:\/\/doi.org\/10.1109\/ICCV.2017.324 (2017).","journal-title":"ICCV"},{"key":"53405_CR6","unstructured":"Redmon, J. & Farhadi, A. Yolov3: An incremental improvement. https:\/\/arXiv.org\/abs\/1804.02767 (2018)."},{"key":"53405_CR7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079","author":"M Tan","year":"2020","unstructured":"Tan, M. et al. Efficientdet: Scalable and efficient object detection. CVPR https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079 (2020).","journal-title":"CVPR"},{"key":"53405_CR8","unstructured":"Ge, Z. et al. Yolox: Exceeding yolo series in 2021. https:\/\/arXiv.org\/abs\/2107.08430 (2021)."},{"key":"53405_CR9","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y. et al. Yolov9: Learning what you want to learn using programmable gradient information. https:\/\/arXiv.org\/abs\/2402.13616 (2024).","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"53405_CR10","doi-asserted-by":"crossref","unstructured":"Wang, A. et al. Yolov10: Real-time end-to-end object detection. https:\/\/arXiv.org\/abs\/2405.14458 (2024).","DOI":"10.52202\/079017-3429"},{"key":"53405_CR11","volume-title":"International Conference on Machine Learning, 5301\u20135310","author":"N Rahaman","year":"2019","unstructured":"Rahaman, N. et al. On the spectral bias of neural networks. In International Conference on Machine Learning, 5301\u20135310 (ed. Rahaman, N.) (PMLR, 2019)."},{"key":"53405_CR12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140","author":"A Howard","year":"2019","unstructured":"Howard, A. et al. Searching for MobileNetV3. ICCV https:\/\/doi.org\/10.1109\/ICCV.2019.00140 (2019).","journal-title":"ICCV"},{"key":"53405_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8","author":"N Ma","year":"2018","unstructured":"Ma, N. et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design. ECCV https:\/\/doi.org\/10.1007\/978-3-030-01264-9_8 (2018).","journal-title":"ECCV"},{"key":"53405_CR14","doi-asserted-by":"publisher","first-page":"111518","DOI":"10.1016\/j.engappai.2025.111518","volume":"158","author":"M Li","year":"2025","unstructured":"Li, M., Liang, X., Hu, Q., Lin, Y. E. & Xia, C. Multi-scale feature fusion with knowledge distillation for object detection in aerial imagery. Eng. Appl. Artif. Intell. 158, 111518 (2025).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"53405_CR15","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1007\/s10586-025-05452-4","volume":"28","author":"H Zhou","year":"2025","unstructured":"Zhou, H., Sun, Z. & Sun, K. A UAV image small object detection approach with enhanced feature pyramid and receptive field. Clust. Comput. 28, 714 (2025).","journal-title":"Clust. Comput."},{"key":"53405_CR16","unstructured":"Tseng, G. et al. Galileo: Learning global & local features of many remote sensing modalities. https:\/\/arXiv.org\/abs\/2502.09356 (2025)."},{"key":"53405_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121366","author":"Q Fan","year":"2025","unstructured":"Fan, Q. et al. Lud-yolo: A novel lightweight object detection network for unmanned aerial vehicle. Inf. Sci. https:\/\/doi.org\/10.1016\/j.ins.2024.121366 (2025).","journal-title":"Inf. Sci."},{"key":"53405_CR18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00203","author":"C-Y Wang","year":"2020","unstructured":"Wang, C.-Y. et al. Cspnet: A new backbone that can enhance learning capability of cnn. CVPR Work https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00203 (2020).","journal-title":"CVPR Work"},{"key":"53405_CR19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352","author":"X Ding","year":"2021","unstructured":"Ding, X. et al. Repvgg: Making vgg-style convnets great again. CVPR https:\/\/doi.org\/10.1109\/CVPR46437.2021.01352 (2021).","journal-title":"CVPR"},{"key":"53405_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_27","author":"P Zhu","year":"2018","unstructured":"Zhu, P. et al. Visdrone-det2018: The vision meets drone object detection in image challenge results. ECCV Work https:\/\/doi.org\/10.1007\/978-3-030-11021-5_27 (2018).","journal-title":"ECCV Work"},{"key":"53405_CR21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296","author":"J Ding","year":"2019","unstructured":"Ding, J. et al. Learning ROI transformer for oriented object detection in aerial images. CVPR https:\/\/doi.org\/10.1109\/CVPR.2019.00296 (2019).","journal-title":"CVPR"},{"key":"53405_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00832","author":"X Yang","year":"2019","unstructured":"Yang, X. et al. Scrdet: Towards more robust detection for small, cluttered and rotated objects. ICCV https:\/\/doi.org\/10.1109\/ICCV.2019.00832 (2019).","journal-title":"ICCV"},{"key":"53405_CR23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048","author":"J Han","year":"2021","unstructured":"Han, J. et al. Align deep features for oriented object detection. IEEE Trans Geosci Remote. Sens. https:\/\/doi.org\/10.1109\/TGRS.2021.3062048 (2021).","journal-title":"IEEE Trans Geosci Remote. Sens."},{"key":"53405_CR24","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.300","author":"Y Li","year":"2024","unstructured":"Li, Y. et al. Lightweight object detection networks for UAV aerial images based on YOLO. Chin. J. Electron. https:\/\/doi.org\/10.23919\/cje.2022.00.300 (2024).","journal-title":"Chin. J. Electron."},{"key":"53405_CR25","doi-asserted-by":"publisher","DOI":"10.1080\/21642583.2023.2246777","author":"J Zhang","year":"2023","unstructured":"Zhang, J. et al. Small object detection in uav image based on improved yolov5. Syst. Sci. Control Eng. https:\/\/doi.org\/10.1080\/21642583.2023.2246777 (2023).","journal-title":"Syst. Sci. Control Eng."},{"key":"53405_CR26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00312","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z. et al. Vit-YOLO: Transformer-based YOLO for object detection. ICCV https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00312 (2021).","journal-title":"ICCV"},{"key":"53405_CR27","doi-asserted-by":"publisher","DOI":"10.3390\/s24175496","author":"Y Kong","year":"2024","unstructured":"Kong, Y. et al. Drone-DETR: Efficient small object detection for remote sensing image using enhanced RT-DETR model. Sensors https:\/\/doi.org\/10.3390\/s24175496 (2024).","journal-title":"Sensors"},{"key":"53405_CR28","doi-asserted-by":"publisher","unstructured":"Zhang, H. et al. Uav-detr: Efficient end-to-end object detection for unmanned aerial vehicle imagery. https:\/\/doi.org\/10.4855\/arXiv.2501.01855 (2025).","DOI":"10.4855\/arXiv.2501.01855"},{"key":"53405_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-64232-z","author":"W Hua","year":"2024","unstructured":"Hua, W. et al. A new lightweight network for efficient UAV object detection. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-024-64232-z (2024).","journal-title":"Sci. Rep."},{"key":"53405_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06611-x","author":"Y Lyu","year":"2025","unstructured":"Lyu, Y. et al. LightUAV-YOLO: A lightweight object detection model for unmanned aerial vehicle image. J. Supercomput. https:\/\/doi.org\/10.1007\/s11227-024-06611-x (2025).","journal-title":"J. Supercomput."},{"key":"53405_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-024-01622-3","author":"J Qu","year":"2025","unstructured":"Qu, J. et al. SS-YOLOv8: Small-size object detection algorithm based on improved YOLOv8 for UAV imagery. Multim. Syst. https:\/\/doi.org\/10.1007\/s00530-024-01622-3 (2025).","journal-title":"Multim. Syst."},{"key":"53405_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104489","author":"Y Zheng","year":"2025","unstructured":"Zheng, Y. et al. LAM-YOLO: Drones-based small object detection on lighting-occlusion attention mechanism YOLO. Comput. Vis. Image Underst. https:\/\/doi.org\/10.1016\/j.cviu.2025.104489 (2025).","journal-title":"Comput. Vis. Image Underst."},{"key":"53405_CR33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32490","author":"C Li","year":"2025","unstructured":"Li, C. et al. RemDet: Rethinking efficient model design for UAV object detection. Proc. AAAI Conf. Artif. Intell. https:\/\/doi.org\/10.1609\/aaai.v39i5.32490 (2025).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"53405_CR34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474","author":"M Sandler","year":"2018","unstructured":"Sandler, M. et al. MobileNetV2: Inverted residuals and linear bottlenecks. CVPR https:\/\/doi.org\/10.1109\/CVPR.2018.00474 (2018).","journal-title":"CVPR"},{"key":"53405_CR35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293","author":"M Tan","year":"2019","unstructured":"Tan, M. et al. MnasNet: Platform-aware neural architecture search for mobile. CVPR https:\/\/doi.org\/10.1109\/CVPR.2019.00293 (2019).","journal-title":"CVPR"},{"key":"53405_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165","author":"K Han","year":"2020","unstructured":"Han, K. et al. Ghostnet: More features from cheap operations. CVPR https:\/\/doi.org\/10.1109\/CVPR42600.2020.00165 (2020).","journal-title":"CVPR"},{"key":"53405_CR37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01509","author":"A Wang","year":"2024","unstructured":"Wang, A. et al. RepVit: Revisiting mobile CNN from Vit perspective. CVPR https:\/\/doi.org\/10.1109\/CVPR52733.2024.01506 (2024).","journal-title":"CVPR"},{"key":"53405_CR38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_5","author":"K Wu","year":"2022","unstructured":"Wu, K. et al. TinyVit: Fast pretraining distillation for small vision transformers. ECCV https:\/\/doi.org\/10.1007\/978-3-031-20044-1_5 (2022).","journal-title":"ECCV"},{"key":"53405_CR39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_1","author":"M Maaz","year":"2022","unstructured":"Maaz, M. et al. Edgenext: Efficiently amalgamated cnn-transformer architecture for mobile vision applications. ECCV https:\/\/doi.org\/10.1007\/978-3-031-19803-8_1 (2022).","journal-title":"ECCV"},{"key":"53405_CR40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2206.01191","author":"Y Li","year":"2022","unstructured":"Li, Y. et al. Efficientformer: Vision transformers at mobilenet speed. Adv. Neural Inf. Process Syst. https:\/\/doi.org\/10.48550\/arXiv.2206.01191 (2022).","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"53405_CR41","doi-asserted-by":"publisher","unstructured":"Li, Y. et al. Rethinking vision transformers for MobileNet size and speed.\u00a0arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2212.08059 (2023).","DOI":"10.48550\/arXiv.2212.08059"},{"key":"53405_CR42","doi-asserted-by":"publisher","unstructured":"He, H. et al. Mobilemamba: Lightweight multi-receptive visual mamba network. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2411.15941 (2025).","DOI":"10.48550\/arXiv.2411.15941"},{"key":"53405_CR43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.08083","author":"A Hatamizadeh","year":"2025","unstructured":"Hatamizadeh, A. & Kautz, J. Mambavision: A hybrid mamba-transformer vision backbone. CVPR. https:\/\/doi.org\/10.48550\/arXiv.2407.08083 (2025).","journal-title":"CVPR."},{"key":"53405_CR44","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-024-03127-y","author":"Y Chen","year":"2024","unstructured":"Chen, Y. et al. Frr-net: A fast reparameterized residual network for low-light image enhancement. Signal Image Video Process. https:\/\/doi.org\/10.1007\/s11760-024-03127-y (2024).","journal-title":"Signal Image Video Process."},{"key":"53405_CR45","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-023-01252-1","author":"Y Chen","year":"2024","unstructured":"Chen, Y. et al. Fmr-net: A fast multi-scale residual network for low-light image enhancement. Multim. Syst. https:\/\/doi.org\/10.1007\/s00530-023-01252-1 (2024).","journal-title":"Multim. Syst."},{"key":"53405_CR46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3206399","author":"K Liu","year":"2022","unstructured":"Liu, K. et al. Yolov5-tassel: Detecting tassels in rgb uav imagery. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. https:\/\/doi.org\/10.1109\/JSTARS.2022.3206399 (2022).","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"53405_CR47","doi-asserted-by":"publisher","DOI":"10.3390\/s23167190","author":"Y Wang","year":"2023","unstructured":"Wang, Y. et al. Uav-yolov8: A small-object-detection model based on improved yolov8. Sensors https:\/\/doi.org\/10.3390\/s23167190 (2023).","journal-title":"Sensors"},{"key":"53405_CR48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.12524","author":"Y Tian","year":"2025","unstructured":"Tian, Y. et al. Yolov12: Attention-centric real-time object detectors. Adv. Neural Inf. Process. Syst. https:\/\/doi.org\/10.48550\/arXiv.2502.12524 (2025).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"53405_CR49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32937","author":"Y Xiao","year":"2025","unstructured":"Xiao, Y. et al. Fbrt-yolo: Faster and better for real-time aerial image detection. AAAI https:\/\/doi.org\/10.1609\/aaai.v39i8.32937 (2025).","journal-title":"AAAI"},{"key":"53405_CR50","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-024-03404-w","author":"N Rani","year":"2024","unstructured":"Rani, N. et al. Lv-yolo: Logistic vehicle speed detection and counting. Sig. Image Video Process https:\/\/doi.org\/10.1007\/s11760-024-03404-w (2024).","journal-title":"Sig. Image Video Process"},{"key":"53405_CR51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00314","author":"X Zhu","year":"2021","unstructured":"Zhu, X. et al. Tph-yolov5: Improved yolov5 based on transformer prediction head. ICCV https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00314 (2021).","journal-title":"ICCV"},{"key":"53405_CR52","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2024.2329528","author":"Q Wu","year":"2024","unstructured":"Wu, Q. et al. C3tb-yolov5: Integrated yolov5 with transformer. Int. J. Remote Sens. https:\/\/doi.org\/10.1080\/01431161.2024.2329528 (2024).","journal-title":"Int. J. Remote Sens."},{"key":"53405_CR53","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3348555","author":"L Chen","year":"2024","unstructured":"Chen, L. et al. Dtssnet: Dynamic training sample selection network for UAV object detection. IEEE Trans. Geosci. Remote Sens. https:\/\/doi.org\/10.1109\/TGRS.2023.3348555 (2024).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"53405_CR54","doi-asserted-by":"publisher","unstructured":"Kunyang, W. et al. DIFNet: Dual-Information Fusion Network for depth completion Information Fusion 125103424. (2026). https:\/\/doi.org\/10.1016\/j.inffus.2025.103424","DOI":"10.1016\/j.inffus.2025.103424"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53405-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53405-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53405-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T23:27:47Z","timestamp":1784762867000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53405-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":54,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["53405"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-53405-7","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-8816494\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"assertion":[{"value":"7 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"23040"}}