{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T23:13:51Z","timestamp":1784070831865,"version":"3.55.0"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07836-0","type":"journal-article","created":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T19:10:47Z","timestamp":1757704247000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["REA-YOLO for small object detection in UAV aerial images"],"prefix":"10.1007","volume":"81","author":[{"given":"Jinhang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liqiang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haitao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zetian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglin","family":"Rong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"issue":"7","key":"7836_CR1","doi-asserted-by":"publisher","first-page":"7963","DOI":"10.1007\/s13369-022-06738-0","volume":"47","author":"F Ahmed","year":"2022","unstructured":"Ahmed F et al (2022) Recent advances in unmanned aerial vehicles: a review. Arab J Sci Eng 47(7):7963\u20137984","journal-title":"Arab J Sci Eng"},{"issue":"6","key":"7836_CR2","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7836_CR3","doi-asserted-by":"crossref","unstructured":"Redmon J et al (2016) You only look once: unified, real-time object detection. In: 2016 ieee conference on computer vision and pattern recognition (CVPR). pp 779\u201388","DOI":"10.1109\/CVPR.2016.91"},{"key":"7836_CR4","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu W et al (2016) SSD: Single Shot MultiBox Detector. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision \u2013 ECCV 2016. Springer International Publishing, Cham, pp 21\u201337"},{"key":"#cr-split#-7836_CR5.1","doi-asserted-by":"crossref","unstructured":"Lin TY et al (2018) Focal loss for dense object detection [Internet]. arXiv","DOI":"10.1109\/ICCV.2017.324"},{"key":"#cr-split#-7836_CR5.2","unstructured":"[cited 2024 Dec 24]. Available from: http:\/\/arxiv.org\/abs\/1708.02002"},{"key":"7836_CR6","unstructured":"Dosovitskiy A et al (2020) An image is worth 16 \u00d7 16 words: transformers for image recognition at scale. CoRR [Internet]. abs\/2010.11929. Available from: https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"7836_CR7","unstructured":"Vaswani A et al (2017) Attention is all you need. In: Proceedings of the 31st international conference on neural information processing systems. Red Hook, NY, USA: Curran Associates Inc. pp 6000\u201310. (NIPS\u201917)."},{"key":"7836_CR8","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer vision\u2014ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion N et al (2020) End-to-end object detection with transformers. In: Vedaldi A, Bischof H, Brox T, Frahm JM (eds) Computer vision\u2014ECCV 2020. Springer International Publishing, Cham, pp 213\u2013229"},{"key":"7836_CR9","unstructured":"Zhang H et al (2022) DINO: DETR with improved denoising anchor boxes for end-to-end object detection. ArXiv [Internet]. abs\/2203.03605. Available from: https:\/\/api.semanticscholar.org\/CorpusID:247292561"},{"key":"7836_CR10","doi-asserted-by":"crossref","unstructured":"Zhao Y et al (2024) DETRs Beat YOLOs on real-time object detection [Internet]. Available from: https:\/\/arxiv.org\/abs\/2304.08069","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"7836_CR11","unstructured":"Liu Y et al (2024) VMamba: visual state space model [Internet]. arXiv. [cited 2025 Mar 17]. Available from: http:\/\/arxiv.org\/abs\/2401.10166"},{"key":"7836_CR12","unstructured":"Wang Z et al (2024) Mamba YOLO: a simple baseline for object detection with state space model [Internet]. arXiv. [cited 2025 Mar 17]. Available from: http:\/\/arxiv.org\/abs\/2406.05835"},{"key":"7836_CR13","first-page":"11966","volume":"2022","author":"Z Liu","year":"2022","unstructured":"Liu Z et al (2022) A ConvNet for the 2020s. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022:11966\u201311976","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"7836_CR14","unstructured":"Zhang J, et al. Rethinking Mobile Block for Efficient Attention-based Models [Internet]. arXiv; 2023 [cited 2025 Mar 17]. Available from: http:\/\/arxiv.org\/abs\/2301.01146"},{"key":"7836_CR15","doi-asserted-by":"crossref","unstructured":"Wang A, et al.: Rep ViT: Revisiting Mobile CNN From ViT Perspective. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024. p. 15909\u201320.","DOI":"10.1109\/CVPR52733.2024.01506"},{"key":"7836_CR16","unstructured":"Mehta S, et al.: MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer. ArXiv [Internet]. 2021;abs\/2110.02178. Available from: https:\/\/api.semanticscholar.org\/CorpusID:238354201"},{"key":"7836_CR17","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/978-3-031-19211-1_33","volume-title":"Wireless Algorithms, Systems, and Applications","author":"Z Chen","year":"2022","unstructured":"Chen Z et al (2022) EdgeViT: Efficient Visual Modeling for Edge Computing. In: Wang L, Segal M, Chen J, Qiu T (eds) Wireless Algorithms, Systems, and Applications. Springer Nature Switzerland, Cham, pp 393\u2013405"},{"key":"7836_CR18","doi-asserted-by":"crossref","unstructured":"Li Y, et al. Rethinking Vision Transformers for MobileNet Size and Speed. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 2023. p. 16843\u201354.","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"7836_CR19","doi-asserted-by":"crossref","unstructured":"Zhang Z et al (2021) ViT-YOLO: Transformer-based YOLO for object detection. In: 2021 IEEE\/CVF international conference on computer vision workshops (ICCVW). pp 2799\u2013808","DOI":"10.1109\/ICCVW54120.2021.00314"},{"key":"7836_CR20","unstructured":"Wang C et al (2023) Gold-YOLO: efficient object detector via gather-and-distribute mechanism [Internet]. Available from: https:\/\/arxiv.org\/abs\/2309.11331"},{"key":"7836_CR21","doi-asserted-by":"crossref","unstructured":"Redmon J, et al.: YOLO9000: Better, Faster, Stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. p. 6517\u201325","DOI":"10.1109\/CVPR.2017.690"},{"key":"7836_CR22","unstructured":"Bochkovskiy A et al (2020) YOLOv4: optimal speed and accuracy of object detection. ArXiv [Internet]. abs\/2004.10934. Available from: https:\/\/api.semanticscholar.org\/CorpusID:216080778"},{"key":"7836_CR23","unstructured":"Ge Z, Liu S et al (2021) YOLOX: exceeding YOLO series in 2021 [Internet]. Available from: https:\/\/arxiv.org\/abs\/2107.08430"},{"key":"7836_CR24","doi-asserted-by":"crossref","unstructured":"Khokhlov I et al (2020) Tiny-YOLO object detection supplemented with geometrical data. In: 2020 IEEE 91st vehicular technology conference (VTC2020-Spring). pp 1\u20135","DOI":"10.1109\/VTC2020-Spring48590.2020.9128749"},{"key":"7836_CR25","unstructured":"Redmon J, et al.: YOLOv3: An Incremental Improvement [Internet]. 2018. Available from: https:\/\/arxiv.org\/abs\/1804.02767"},{"key":"7836_CR26","doi-asserted-by":"crossref","unstructured":"Wei Y et al (2023) YOLOv7-UAV: improved YOLOv7 algorithm for small object detection in UAV image scenarios. In: 2023 international conference on artificial intelligence of things and systems (AIoTSys). pp 64\u201370","DOI":"10.1109\/AIoTSys58602.2023.00031"},{"key":"7836_CR27","doi-asserted-by":"crossref","unstructured":"Wang G et al (2023) UAV-YOLOv8: A small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios. Sensors [Internet]. 23(16). Available from: https:\/\/www.mdpi.com\/1424-8220\/23\/16\/7190.","DOI":"10.3390\/s23167190"},{"key":"7836_CR28","first-page":"1","volume-title":"Computer vision\u2014ECCV 2024","author":"CY Wang","year":"2025","unstructured":"Wang CY et al (2025) YOLOv9: learning what you want to learn using programmable gradient information. In: Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G (eds) Computer vision\u2014ECCV 2024. Springer Nature Switzerland, Cham, pp 1\u201321"},{"key":"7836_CR29","unstructured":"Wang A et al (2024) YOLOv10: real-time end-to-end object detection [Internet]. Available from: https:\/\/arxiv.org\/abs\/2405.14458"},{"key":"7836_CR30","doi-asserted-by":"crossref","unstructured":"Rasheed AF et al (2024) YOLOv11 Optimization for efficient resource utilization [Internet]. Available from: https:\/\/arxiv.org\/abs\/2412.14790","DOI":"10.1007\/s11227-025-07520-3"},{"key":"7836_CR31","unstructured":"Tian Y et al (2025) YOLOv12: attention-centric real-time object detectors [Internet]. arXiv. [cited 2025 Mar 17]. Available from: http:\/\/arxiv.org\/abs\/2502.12524"},{"key":"7836_CR32","doi-asserted-by":"crossref","unstructured":"Ding J et al (2019) Learning RoI transformer for oriented object detection in aerial images. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp 2844\u201353","DOI":"10.1109\/CVPR.2019.00296"},{"key":"7836_CR33","doi-asserted-by":"crossref","unstructured":"Chen C et al (2019) RRNet: a hybrid detector for object detection in drone-captured images. In: 2019 IEEE\/CVF international conference on computer vision workshop (ICCVW). pp 100\u20138","DOI":"10.1109\/ICCVW.2019.00018"},{"key":"7836_CR34","doi-asserted-by":"crossref","unstructured":"Wang X et al (2021) SPB-YOLO: An efficient real-time detector for unmanned aerial vehicle images. In: 2021 international conference on artificial intelligence in information and communication (ICAIIC). pp 099\u2013104","DOI":"10.1109\/ICAIIC51459.2021.9415214"},{"key":"7836_CR35","doi-asserted-by":"crossref","unstructured":"Liu Z et al (2021) HRDNet: high-resolution detection network for small objects. In: 2021 IEEE international conference on multimedia and expo (ICME). pp 1\u20136","DOI":"10.1109\/ICME51207.2021.9428241"},{"key":"7836_CR36","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.neucom.2021.03.016","volume":"443","author":"G Tian","year":"2021","unstructured":"Tian G et al (2021) A dual neural network for object detection in UAV images. Neurocomputing 443:292\u2013301","journal-title":"Neurocomputing"},{"key":"7836_CR37","unstructured":"Simonyan K et al (2014) Very deep convolutional networks for large-scale image recognition. CoRR [Internet]. abs\/1409.1556. Available from: https:\/\/api.semanticscholar.org\/CorpusID:14124313"},{"key":"7836_CR38","doi-asserted-by":"publisher","first-page":"10011","DOI":"10.1109\/TCSVT.2024.3402097","volume":"34","author":"Z Zhu","year":"2024","unstructured":"Zhu Z, Zheng R, Qi G, Li S, Li Y, Gao X (2024) Small object detection method based on global multi-level perception and dynamic region aggregation. IEEE Trans Circ Syst Video Technol 34:10011\u201310022. https:\/\/doi.org\/10.1109\/TCSVT.2024.3402097","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"7836_CR39","doi-asserted-by":"publisher","DOI":"10.3390\/rs16040644","author":"Y Li","year":"2024","unstructured":"Li Y, Zhou Z, Qi G, Hu G, Zhu Z, Huang X (2024) Remote sensing micro-object detection under global and local attention mechanism. Remote Sens. https:\/\/doi.org\/10.3390\/rs16040644","journal-title":"Remote Sens"},{"key":"7836_CR40","doi-asserted-by":"publisher","DOI":"10.3390\/rs14020420","author":"G Qi","year":"2022","unstructured":"Qi G, Zhang Y, Wang K, Mazur N, Liu Y, Malaviya D (2022) Small object detection method based on adaptive spatial parallel convolution and fast multi-scale fusion. Remote Sens. https:\/\/doi.org\/10.3390\/rs14020420","journal-title":"Remote Sens"},{"key":"7836_CR41","doi-asserted-by":"crossref","unstructured":"Xi Y et al (2022) FiFoNet: Fine-grained target focusing network for object detection in UAV images. remote sensing [Internet]. 14(16). Available from: https:\/\/www.mdpi.com\/2072-4292\/14\/16\/3919","DOI":"10.3390\/rs14163919"},{"issue":"1","key":"7836_CR42","doi-asserted-by":"publisher","first-page":"7817","DOI":"10.1038\/s41598-023-34892-4","volume":"13","author":"L Deng","year":"2023","unstructured":"Deng L et al (2023) Lightweight aerial image object detection algorithm based on improved YOLOv5s. Sci Rep 13(1):7817","journal-title":"Sci Rep"},{"key":"7836_CR43","doi-asserted-by":"crossref","unstructured":"Lee Y et al (2019) An energy and GPU-computation efficient backbone network for real-time object detection. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW). pp 752\u201360","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"7836_CR44","doi-asserted-by":"publisher","unstructured":"Ma N et al (2018) ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds.) Computer vision \u2013 ECCV 2018 [Internet]. Cham: Springer International Publishing. [cited 2025 Mar 17]. p. 122\u201338.(Lecture Notes in Computer Science; vol.11218). Available from: https:\/\/link.springer.com\/https:\/\/doi.org\/10.1007\/978-3-030-01264-9_8","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"7836_CR45","doi-asserted-by":"crossref","unstructured":"Tang Z et al (2020) PENet: object detection using points estimation in high definition aerial images. In: 2020 19th IEEE international conference on machine learning and applications (ICMLA). pp 392\u20138","DOI":"10.1109\/ICMLA51294.2020.00069"},{"key":"7836_CR46","unstructured":"Huang Y et al (2021) UFPMP-Det: Toward accurate and efficient object detection on drone imagery. ArXiv [Internet]. abs\/2112.10415. Available from: https:\/\/api.semanticscholar.org\/CorpusID:245334316"},{"key":"7836_CR47","doi-asserted-by":"publisher","first-page":"1807","DOI":"10.1109\/JSEN.2021.3139124","volume":"22","author":"AN Wilson","year":"2022","unstructured":"Wilson AN, Kumar A, Jha A, Cenkeramaddi LR (2022) Embedded sensors, communication technologies, computing platforms and machine learning for UAVs: a review. IEEE Sens J 22:1807\u20131826. https:\/\/doi.org\/10.1109\/JSEN.2021.3139124","journal-title":"IEEE Sens J"},{"key":"7836_CR48","doi-asserted-by":"publisher","first-page":"11815","DOI":"10.1109\/JSEN.2023.3265659","volume":"23","author":"M Li","year":"2023","unstructured":"Li M, Zhai D, Yang D, Xu L (2023) Bvtracker: multivehicle tracking based on behavioral-visual features. IEEE Sens J 23:11815\u201311824. https:\/\/doi.org\/10.1109\/JSEN.2023.3265659","journal-title":"IEEE Sens J"},{"key":"7836_CR49","doi-asserted-by":"publisher","first-page":"16092","DOI":"10.1109\/TVT.2024.3425755","volume":"73","author":"C Wang","year":"2024","unstructured":"Wang C, Wang J, Ma Z, Xu M, Qi K, Ji Z, Wei C (2024) Integrated learning-based framework for autonomous quadrotor UAV landing on a collaborative moving UGV. IEEE Trans Veh Technol 73:16092\u201316107. https:\/\/doi.org\/10.1109\/TVT.2024.3425755","journal-title":"IEEE Trans Veh Technol"},{"key":"7836_CR50","doi-asserted-by":"publisher","unstructured":"Zhang Z et al (2018) ExFuse: enhancing feature fusion for semantic segmentation. In: computer vision\u2014ECCV 2018: 15th European conference, Munich, Germany, September 8\u201314, 2018, Proceedings, Part X [Internet]. Berlin, Heidelberg: Springer-Verlag; 2018. p. 273\u201388. Available from: https:\/\/doi.org\/10.1007\/978-3-030-01249-6_17","DOI":"10.1007\/978-3-030-01249-6_17"},{"key":"7836_CR51","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/978-3-030-58520-4_26","volume-title":"Computer vision\u2014ECCV 2020","author":"X Li","year":"2020","unstructured":"Li X et al (2020) Improving semantic segmentation via decoupled body and edge supervision. In: Vedaldi A, Bischof H, Brox T, Frahm JM (eds) Computer vision\u2014ECCV 2020. Springer International Publishing, Cham, pp 435\u2013452"},{"key":"7836_CR52","unstructured":"Luo W et al (2016) Understanding the effective receptive field in deep convolutional neural networks. In: Proceedings of the 30th international conference on neural information processing systems. Red Hook, NY, USA: Curran Associates Inc. pp 4905\u201313. (NIPS\u201916)"},{"key":"7836_CR53","doi-asserted-by":"crossref","unstructured":"Dai X et al (2021) Dynamic head: unifying object detection heads with attentions. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). pp 7369\u201378","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"7836_CR54","unstructured":"Lee J et al (2021) Layer-adaptive sparsity for the magnitude-based pruning [Internet]. arXiv. [cited 2025 Mar 17]. Available from: http:\/\/arxiv.org\/abs\/2010.07611"},{"key":"7836_CR55","doi-asserted-by":"crossref","unstructured":"Du D et al (2019) VisDrone-DET2019: the vision meets drone object detection in image challenge results. In: 2019 IEEE\/cvf international conference on computer vision workshop (ICCVW). pp 213\u201326","DOI":"10.1109\/ICCVW.2019.00030"},{"issue":"4","key":"7836_CR56","doi-asserted-by":"publisher","first-page":"2388","DOI":"10.1109\/TPAMI.2024.3524377","volume":"47","author":"Y Feng","year":"2025","unstructured":"Feng Y et al (2025) Hyper-YOLO: when visual object detection meets hypergraph computation. IEEE Trans Pattern Anal Mach Intell 47(4):2388\u20132401","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7836_CR57","unstructured":"Xu X et al (2022) DAMO-YOLO\u202f: a report on real-time object detection design. ArXiv [Internet]. abs\/2211.15444. Available from: https:\/\/api.semanticscholar.org\/CorpusID:254043744"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07836-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07836-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07836-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T19:10:57Z","timestamp":1757704257000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07836-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"references-count":58,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["7836"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07836-0","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"24 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2025","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"1332"}}