{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:53:17Z","timestamp":1782395597351,"version":"3.54.5"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Postgraduate Research & Practice Innovation Program of NUAA","award":["xcxjh20251504"],"award-info":[{"award-number":["xcxjh20251504"]}]},{"name":"he Natural Science Foundation of Jiangsu Province","award":["BK20241395"],"award-info":[{"award-number":["BK20241395"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11554-026-01902-3","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T15:16:30Z","timestamp":1780758990000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Csf-yolo: clean features and stable fusion for UAV small-object detection"],"prefix":"10.1007","volume":"23","author":[{"given":"Lixiao","family":"Deng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinbao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"issue":"1","key":"1902_CR1","doi-asserted-by":"publisher","first-page":"149","DOI":"10.3390\/rs16010149","volume":"16","author":"G Tang","year":"2024","unstructured":"Tang, G., Ni, J., Zhao, Y., Gu, Y., Cao, W.: A survey of object detection for UAVs based on deep learning. Remote Sens. 16(1), 149 (2024). https:\/\/doi.org\/10.3390\/rs16010149","journal-title":"Remote Sens."},{"key":"1902_CR2","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.cogr.2024.07.002","volume":"4","author":"AA Laghari","year":"2024","unstructured":"Laghari, A.A., Jumani, A.K., Laghari, R.A., Li, H., Karim, S., Khan, A.A.: Unmanned aerial vehicles advances in object detection and communication security review. Cogn Robot 4, 128\u2013141 (2024). https:\/\/doi.org\/10.1016\/j.cogr.2024.07.002","journal-title":"Cogn Robot"},{"key":"1902_CR3","doi-asserted-by":"publisher","unstructured":"Du, D., Qi, Y., Yu, H., Yang, Y., Duan, K., Li, G., Zhang, W., Huang, Q., Tian, Q.:The Unmanned Aerial Vehicle Benchmark: object detection and tracking. In: Computer Vision \u2013 ECCV 2018, pp. 375\u2013391 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_23.","DOI":"10.1007\/978-3-030-01249-6_23."},{"key":"1902_CR4","unstructured":"Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., Ling, H.: Detection and tracking meet drones challenge (2020). arXiv:2001.06303 arXiv preprint"},{"key":"1902_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Y., He, Z., Wang, L., Wang, W., Yuan, Y., Zhang, D., Zhang, J., Zhu, P., Van Gool, L., Han, J., Hoi, S., Hu, Q., Liu, M.: VisDrone-DET2021: the vision meets drone object detection challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 2847\u20132854 (2021)","DOI":"10.1109\/ICCVW54120.2021.00319"},{"issue":"19","key":"1902_CR6","doi-asserted-by":"publisher","first-page":"5063","DOI":"10.3390\/rs14195063","volume":"14","author":"X Luo","year":"2022","unstructured":"Luo, X., Wu, Y., Wang, F.: Target detection method of UAV aerial imagery based on improved YOLOv5. Remote Sens. 14(19), 5063 (2022). https:\/\/doi.org\/10.3390\/rs14195063","journal-title":"Remote Sens."},{"issue":"18","key":"1902_CR7","doi-asserted-by":"publisher","first-page":"3942","DOI":"10.3390\/electronics12183942","volume":"12","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Xie, J., Zhang, S., Yu, Z., Ma, J.: SMFF-YOLO: a small target detection method for unmanned aerial vehicles based on multi-level feature fusion. Electronics 12(18), 3942 (2023). https:\/\/doi.org\/10.3390\/electronics12183942","journal-title":"Electronics"},{"issue":"22","key":"1902_CR8","doi-asserted-by":"publisher","first-page":"5405","DOI":"10.3390\/rs15225405","volume":"15","author":"Y Min","year":"2023","unstructured":"Min, Y., Li, X., Wen, H., Qu, H., Zheng, Z., Zhang, L., Lan, R., Wang, S.: YOLO-DCTI: a small object detection method in aerial images based on a double-ended contextual transformer feature enhancement module. Remote Sens. 15(22), 5405 (2023). https:\/\/doi.org\/10.3390\/rs15225405","journal-title":"Remote Sens."},{"issue":"2","key":"1902_CR9","doi-asserted-by":"publisher","first-page":"384","DOI":"10.3390\/rs16020384","volume":"16","author":"Z Hui","year":"2024","unstructured":"Hui, Z., Liu, T., Yang, J., Xu, Y., Zhang, X.: SEB-YOLO: an improved YOLOv5 model for remote sensing small target detection. Remote Sens. 16(2), 384 (2024). https:\/\/doi.org\/10.3390\/rs16020384","journal-title":"Remote Sens."},{"issue":"14","key":"1902_CR10","doi-asserted-by":"publisher","first-page":"2441","DOI":"10.3390\/rs17142441","volume":"17","author":"S Zhao","year":"2025","unstructured":"Zhao, S., Chen, H., Zhang, D., Tao, Y., Feng, X., Zhang, D.: SR-YOLO: spatial-to-depth enhanced multi-scale attention network for small target detection in UAV aerial imagery. Remote Sens. 17(14), 2441 (2025). https:\/\/doi.org\/10.3390\/rs17142441","journal-title":"Remote Sens."},{"issue":"24","key":"1902_CR11","doi-asserted-by":"publisher","first-page":"3936","DOI":"10.3390\/rs17243936","volume":"17","author":"Z Zhuo","year":"2025","unstructured":"Zhuo, Z., Lu, R., Yao, Y., Wang, S., Zheng, Z.: TAF-YOLO: a small-object detection network for UAV aerial imagery via visible and infrared adaptive fusion. Remote Sens. 17(24), 3936 (2025). https:\/\/doi.org\/10.3390\/rs17243936","journal-title":"Remote Sens."},{"key":"1902_CR12","doi-asserted-by":"publisher","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117\u20132125 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106.","DOI":"10.1109\/CVPR.2017.106."},{"key":"1902_CR13","doi-asserted-by":"publisher","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8759\u20138768 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00913.","DOI":"10.1109\/CVPR.2018.00913."},{"key":"1902_CR14","doi-asserted-by":"publisher","unstructured":"Li, J., Wen, Y., He, L.: SCConv: Spatial and channel reconstruction convolution for feature redundancy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6153\u20136162 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00596.","DOI":"10.1109\/CVPR52729.2023.00596."},{"key":"1902_CR15","doi-asserted-by":"publisher","unstructured":"Li, H.: Rethinking features-fused-pyramid-neck for object detection. In: Computer Vision \u2013 ECCV 2024, pp. 74\u201390 (2024). https:\/\/doi.org\/10.1007\/978-3-031-72855-6_5.","DOI":"10.1007\/978-3-031-72855-6_5."},{"key":"1902_CR16","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/s10462-025-11150-9","volume":"58","author":"W Hua","year":"2025","unstructured":"Hua, W., Chen, Q.: A survey of small object detection based on deep learning in aerial images. Artif. Intell. Rev. 58, 162 (2025). https:\/\/doi.org\/10.1007\/s10462-025-11150-9","journal-title":"Artif. Intell. Rev."},{"key":"1902_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2025.200561","volume":"27","author":"M Nikouei","year":"2025","unstructured":"Nikouei, M., Baroutian, B., Nabavi, S., Taraghi, F., Aghaei, A., Sajedi, A., Moghaddam, M.E.: Small object detection: a comprehensive survey on challenges, techniques and real-world applications. Intell. Syst. Appl. 27, 200561 (2025). https:\/\/doi.org\/10.1016\/j.iswa.2025.200561","journal-title":"Intell. Syst. Appl."},{"key":"1902_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107455","volume":"128","author":"G Song","year":"2024","unstructured":"Song, G., Du, H., Zhang, X., Bao, F., Zhang, Y.: Small object detection in unmanned aerial vehicle images using multi-scale hybrid attention. Eng. Appl. Artif. Intell. 128, 107455 (2024). https:\/\/doi.org\/10.1016\/j.engappai.2023.107455","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1902_CR19","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s44196-024-00632-3","volume":"17","author":"L Xu","year":"2024","unstructured":"Xu, L., Zhao, Y., Zhai, Y., et al.: Small object detection in UAV images based on YOLOv8n. Int. J. Comput. Intell. Syst. 17, 223 (2024). https:\/\/doi.org\/10.1007\/s44196-024-00632-3","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"1902_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128459","volume":"291","author":"T Hou","year":"2025","unstructured":"Hou, T., Leng, C., Wang, J., Pei, Z., Peng, J., Cheng, I., Basu, A.: MFEL-YOLO for small object detection in UAV aerial images. Expert Syst. Appl. 291, 128459 (2025). https:\/\/doi.org\/10.1016\/j.eswa.2025.128459","journal-title":"Expert Syst. Appl."},{"issue":"12","key":"1902_CR21","doi-asserted-by":"publisher","first-page":"24330","DOI":"10.1109\/TITS.2022.3203715","volume":"23","author":"J Shen","year":"2022","unstructured":"Shen, J., Zhou, W., Liu, N., Sun, H., Li, D., Zhang, Y.: An anchor-rree lightweight deep convolutional network for vehicle detection in aerial images. IEEE Trans. Intell. Transp. Syst. 23(12), 24330\u201324342 (2022). https:\/\/doi.org\/10.1109\/TITS.2022.3203715","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1902_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2025.3642410","author":"J Shen","year":"2025","unstructured":"Shen, J., Liu, N., Sun, H., Wu, S., Liang, Z., Han, L.: Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection. IEEE Trans. Intell. Transp. Syst. (2025). https:\/\/doi.org\/10.1109\/TITS.2025.3642410","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"1902_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3132332","volume":"71","author":"J Shen","year":"2022","unstructured":"Shen, J., Liu, N., Xu, C., Sun, H., Xiao, Y., Li, D., Zhang, Y.: Finger vein recognition algorithm based on lightweight deep convolutional neural network. IEEE Trans. Instrum. Meas. 71, 1\u201313 (2022). https:\/\/doi.org\/10.1109\/TIM.2021.3132332","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"1902_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2025.122760","volume":"726","author":"D Li","year":"2026","unstructured":"Li, D., Jin, Z., Guan, C., Ji, L., Zhang, Y., Xu, Z., Zhang, J.: KACNet: enhancing CNN feature representation with Kolmogorov-Arnold networks for medical image segmentation and classification. Inf. Sci. 726, 122760 (2026). https:\/\/doi.org\/10.1016\/j.ins.2025.122760","journal-title":"Inf. Sci."},{"key":"1902_CR25","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., Berg, A. C.: SSD: Single shot multiBox detector. In: Computer Vision \u2013 ECCV 2016, pp. 21\u201337 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2.","DOI":"10.1007\/978-3-319-46448-0_2."},{"key":"1902_CR26","doi-asserted-by":"publisher","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: DetNet: design backbone for object detection. In: Computer Vision \u2013 ECCV 2018, pp. 334\u2013350 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_20.","DOI":"10.1007\/978-3-030-01264-9_20."},{"key":"1902_CR27","doi-asserted-by":"publisher","unstructured":"Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S. Z.: Single-shot refinement neural network for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4203\u20134212 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00442.","DOI":"10.1109\/CVPR.2018.00442."},{"key":"1902_CR28","doi-asserted-by":"publisher","unstructured":"Tan, M., Pang, R., Le, Q. V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10781\u201310790 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01080.","DOI":"10.1109\/CVPR42600.2020.01080."},{"key":"1902_CR29","doi-asserted-by":"publisher","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324.","DOI":"10.1109\/ICCV.2017.324."},{"key":"1902_CR30","doi-asserted-by":"publisher","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: CenterNet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6569\u20136578 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00667.","DOI":"10.1109\/ICCV.2019.00667."},{"key":"1902_CR31","doi-asserted-by":"publisher","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: Computer Vision \u2013 ECCV 2018, pp. 734\u2013750 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_45.","DOI":"10.1007\/978-3-030-01231-1_45."},{"key":"1902_CR32","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6154\u20136162 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00644.","DOI":"10.1109\/CVPR.2018.00644."},{"key":"1902_CR33","doi-asserted-by":"publisher","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M. R., Huang, W.: TOOD: task-aligned one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3490\u20133499 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00349.","DOI":"10.1109\/ICCV48922.2021.00349."},{"key":"1902_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S. Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9759\u20139768 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00978.","DOI":"10.1109\/CVPR42600.2020.00978."},{"key":"1902_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"1902_CR36","doi-asserted-by":"publisher","unstructured":"Wu, Y., Chen, Y., Yuan, L., Liu, Z., Wang, L., Li, H., Fu,Y.: Rethinking classification and localization for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10186\u201310195 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01020.","DOI":"10.1109\/CVPR42600.2020.01020."},{"issue":"1","key":"1902_CR37","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/s11760-023-02912-z","volume":"18","author":"A Mu","year":"2024","unstructured":"Mu, A., Wang, X., Zhang, Z., Ma, X., Wang, J., Jiang, S.: Small target detection in drone aerial images based on feature fusion. SIViP 18(1), 585\u2013598 (2024). https:\/\/doi.org\/10.1007\/s11760-023-02912-z","journal-title":"SIViP"},{"key":"1902_CR38","doi-asserted-by":"publisher","unstructured":"Zhu, X., Lyu, Y., Wang, X., Zhao, Q.: TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 2778\u20132788 (2021). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00312.","DOI":"10.1109\/ICCVW54120.2021.00312."},{"key":"1902_CR39","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021, (2021). arXiv:2107.08430 arXiv preprint"},{"key":"1902_CR40","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91.","DOI":"10.1109\/CVPR.2016.91."},{"key":"1902_CR41","doi-asserted-by":"publisher","unstructured":"Ultralytics, YOLOv5: V6.0-YOLOv5n \u201cNano\u201d models. Roboflow Integration, TensorFlow Export, OpenCV DNN Support, Zenodo (2021). https:\/\/doi.org\/10.5281\/zenodo.5563715.","DOI":"10.5281\/zenodo.5563715."},{"key":"1902_CR42","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, X., Hao, Q., Liang, B., Zhang, L., Jin, X., Chu, W., Wei, X.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint, arXiv:2209.02976 (2022)"},{"key":"1902_CR43","doi-asserted-by":"publisher","unstructured":"Sohan, M., Singh, T. J., Chanu, C., Singh, K. M.: A review on YOLOv8 and its advancements. In: International Conference on Data Intelligence and Cognitive Informatics, pp. 529\u2013545 (2024). https:\/\/doi.org\/10.1007\/978-981-97-7315-6_40.","DOI":"10.1007\/978-981-97-7315-6_40."},{"key":"1902_CR44","doi-asserted-by":"publisher","unstructured":"Wang, C. Y., Yeh, I. H., Liao, H. Y. M.: YOLOv9: learning what you want to learn using programmable gradient information. In: Computer Vision \u2013 ECCV 2024, pp. 1\u201321 (2024). https:\/\/doi.org\/10.1007\/978-3-031-72970-6_1.","DOI":"10.1007\/978-3-031-72970-6_1."},{"key":"1902_CR45","doi-asserted-by":"publisher","first-page":"107984","DOI":"10.52202\/079017-3429","volume":"37","author":"A Wang","year":"2024","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: YOLOv10: real-time end-to-end object detection. Adv. Neural. Inf. Process. Syst. 37, 107984\u2013108011 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1902_CR46","unstructured":"Khanam, R., Hussain, M.: YOLOv11: an overview of the key architectural enhancements. (2024). arXiv:2410.17725 arXiv preprint"},{"key":"1902_CR47","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90."},{"key":"1902_CR48","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. (2014). arXiv:1409.1556 arXiv preprint"},{"key":"1902_CR49","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: objects as points. (2019). arXiv:1904.07850 arXiv preprint"},{"key":"1902_CR50","doi-asserted-by":"publisher","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Computer Vision \u2013 ECCV 2016, pp. 483\u2013499 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29.","DOI":"10.1007\/978-3-319-46484-8_29."},{"key":"1902_CR51","doi-asserted-by":"publisher","unstructured":"Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., Zhang, Z.: Dynamic head: unifying object detection heads with attentions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7373\u20137382 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00729.","DOI":"10.1109\/CVPR46437.2021.00729."},{"key":"1902_CR52","unstructured":"Bochkovskiy, A., Wang, C. Y., Liao, H. Y.M.: YOLOv4: optimal speed and accuracy of object detection. (2020). arXiv:2004.10934 arXiv preprint"},{"key":"1902_CR53","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1492\u20131500 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.161.","DOI":"10.1109\/CVPR.2017.161."},{"key":"1902_CR54","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/s11554-025-01770-3","volume":"22","author":"H Yan","year":"2025","unstructured":"Yan, H., Kong, X., Shimada, T., Tomiyama, H.: TOE-YOLO: accurate and efficient detection of tiny objects in UAV imagery. J. Real-Time Image Proc. 22, 194 (2025). https:\/\/doi.org\/10.1007\/s11554-025-01770-3","journal-title":"J. Real-Time Image Proc."},{"issue":"7","key":"1902_CR55","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.3390\/electronics13071190","volume":"13","author":"W Shao","year":"2024","unstructured":"Shao, W., Li, Q., Xu, Y., Lv, Z., Qin, L.: Aero-YOLO: an efficient vehicle and pedestrian detection algorithm based on unmanned aerial imagery. Electronics 13(7), 1190 (2024). https:\/\/doi.org\/10.3390\/electronics13071190","journal-title":"Electronics"},{"key":"1902_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3363057","volume":"62","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Ye, M., Zhu, G., Liu, Y., Guo, P., Yan, J.: FFCA-YOLO for small object detection in remote sensing images. IEEE Trans. Geosci. Remote Sens. 62, 1\u201315 (2024). https:\/\/doi.org\/10.1109\/TGRS.2024.3363057","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1902_CR57","doi-asserted-by":"publisher","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16965\u201316974 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01605.","DOI":"10.1109\/CVPR52733.2024.01605."},{"key":"1902_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3095186","volume":"60","author":"Q Ming","year":"2021","unstructured":"Ming, Q., Miao, Z., Zhou, Z., Dong, H.: CFC-Net: a critical feature capturing network for arbitrary-oriented object detection in remote-sensing images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201314 (2021)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1902_CR59","unstructured":"Tian, Y., Ye, Y., Sun, X., Li, S., Du, J., Guo, X., Hao, X., Liu, J.: YOLOv12: attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524 (2025)"},{"key":"1902_CR60","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1016\/j.neucom.2022.06.049","volume":"501","author":"J Zhou","year":"2022","unstructured":"Zhou, J., Feng, K., Li, W., Han, J., Pan, F.: TS4Net: two-stage sample selective strategy for rotating object detection. Neurocomputing 501, 753\u2013764 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2022.06.049","journal-title":"Neurocomputing"},{"key":"1902_CR61","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.jvcir.2015.11.002","volume":"34","author":"S Razakarivony","year":"2016","unstructured":"Razakarivony, S., Jurie, F.: Vehicle detection in aerial imagery: a small target detection benchmark. J. Vis. Commun. Image Represent. 34, 187\u2013203 (2016). https:\/\/doi.org\/10.1016\/j.jvcir.2015.11.002","journal-title":"J. Vis. Commun. Image Represent."}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-026-01902-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-026-01902-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-026-01902-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:38:36Z","timestamp":1782394716000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-026-01902-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":61,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1902"],"URL":"https:\/\/doi.org\/10.1007\/s11554-026-01902-3","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"8 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 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":"109"}}