{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T02:27:50Z","timestamp":1773714470309,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819544448","type":"print"},{"value":"9789819544455","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-4445-5_27","type":"book-chapter","created":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T03:43:57Z","timestamp":1768103037000},"page":"393-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learnable Bilateral Downsampling and\u00a0Triple-Augmented Feature Fusion in\u00a0YOLOv8 for\u00a0Small Object Detection of\u00a0UAV Aerial Images"],"prefix":"10.1007","author":[{"given":"Ruojun","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Gui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengling","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Nguyen, L.D., Nguyen, K.K., Kortun, A., et al.: Real-time deployment and resource allocation for distributed UAV systems in disaster relief. In: 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), pp. 1\u20135. IEEE (2019)","DOI":"10.1109\/SPAWC.2019.8815522"},{"issue":"6","key":"27_CR2","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.3390\/rs13061221","volume":"13","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Wang, L., Tian, T., et al.: A review of unmanned aerial vehicle low-altitude remote sensing (UAV-LARS) use in agricultural monitoring in China. Remote Sens. 13(6), 1221 (2021)","journal-title":"Remote Sens."},{"key":"27_CR3","doi-asserted-by":"publisher","first-page":"8982","DOI":"10.1109\/JSTARS.2023.3317500","volume":"16","author":"H Xu","year":"2023","unstructured":"Xu, H., Wang, L., Han, W., et al.: A survey on UAV applications in smart city management: challenges, advances, and opportunities. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 16, 8982\u20139010 (2023)","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"issue":"21","key":"27_CR4","doi-asserted-by":"publisher","first-page":"14473","DOI":"10.3390\/su142114473","volume":"14","author":"Y Li","year":"2022","unstructured":"Li, Y., Liu, M., Jiang, D.: Application of unmanned aerial vehicles in logistics: a literature review. Sustainability 14(21), 14473 (2022)","journal-title":"Sustainability"},{"key":"27_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103808","volume":"143","author":"A Li","year":"2022","unstructured":"Li, A., Hansen, M., Zou, B.: Traffic management and resource allocation for UAV-based parcel delivery in low-altitude urban space. Transp. Res. Part C Emerging Technol. 143, 103808 (2022)","journal-title":"Transp. Res. Part C Emerging Technol."},{"key":"27_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ohx.2023.e00479","volume":"16","author":"T Rathod","year":"2023","unstructured":"Rathod, T., Patil, V., Harikrishnan, R., et al.: Multipurpose deep learning-powered UAV for forest fire prevention and emergency response. HardwareX 16, e00479 (2023)","journal-title":"HardwareX"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Alexan, W., Aly, L., Korayem, Y., et al.: Secure communication of military reconnaissance images over UAV-assisted relay networks. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3407838"},{"key":"27_CR8","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real time object detection with region proposal networks. In: Proceedings of the 29th Advances in Neural Information Processing Systems, pp. 91\u201399. MIT, Cambridge, MA (2015)"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et al.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463. IEEE, Piscataway, NJ (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., et al.: You only look once: unified, real time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788. IEEE, Piscataway, NJ (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"27_CR12","unstructured":"Qiang, C., Yingming, W., Tong, Y., et al.: You only look one-level feature. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13039\u201313048. IEEE, Piscataway, NJ (2021)"},{"key":"27_CR13","unstructured":"Long, X., Deng, K., Wang, G., et al.: PP-YOLO: an effective and efficient implementation of object detector. arXiv preprint arXiv:2007.12099 (2020)"},{"key":"27_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., et al.: Less is more: focus attention for efficient DETR. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6674\u20136683 (2023)","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Li, F., Zeng, A., Liu, S., et al.: Lite DETR: an interleaved multi-scale encoder for efficient DETR. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18558\u201318567 (2023)","DOI":"10.1109\/CVPR52729.2023.01780"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Tang, S., Zhang, S., Fang, Y.: HIC-YOLOv5: improved YOLOv5 for small object detection. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 6614\u20136619. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610273"},{"issue":"3","key":"27_CR18","doi-asserted-by":"publisher","first-page":"84","DOI":"10.3390\/drones8030084","volume":"8","author":"NUA Tahir","year":"2024","unstructured":"Tahir, N.U.A., Long, Z., Zhang, Z., et al.: PVswin-YOLOv8s: UAV-based pedestrian and vehicle detection for traffic management in smart cities using improved YOLOv8. Drones 8(3), 84 (2024)","journal-title":"Drones"},{"issue":"16","key":"27_CR19","doi-asserted-by":"publisher","first-page":"3269","DOI":"10.3390\/electronics13163269","volume":"13","author":"XY Qiu","year":"2024","unstructured":"Qiu, X.Y., Chen, Y.J., Cai, W.H., et al.: LD-YOLOv10: a lightweight target detection algorithm for drone scenarios based on YOLOv10. Electronics 13(16), 3269 (2024)","journal-title":"Electronics"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, H., Shao, F.M., HE, X.H., et al.: Research on object detection and recognition method for UAV aerial images based on improved YOLOv5. Drones 7(6), 402\u2013431 (2023)","DOI":"10.3390\/drones7060402"},{"key":"27_CR21","unstructured":"Wang, C., He, W., Nie, Y., et al.: Gold-YOLO: efficient object detector via gather-and-distribute mechanism. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Patel, H., Shah, H., Patel, G., et al.: Hematologic cancer diagnosis and classification using machine and deep learning: state-of-the-art techniques and emerging research directives. Artif. Intell. Med., 102883 (2024)","DOI":"10.1016\/j.artmed.2024.102883"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Cao, Y., He, Z., Wang, L., et al.: VisDrone-DET2021: the vision meets drone object detection challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2847\u20132854 (2021)","DOI":"10.1109\/ICCVW54120.2021.00319"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Du, D., Qi, Y., Yu, H., et al.: The unmanned aerial vehicle benchmark: object detection and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 370\u2013386 (2018)","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"27_CR26","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"27_CR27","unstructured":"Li, C., Li, L., Jiang, H., et al.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., Mark Liao, H.Y.: YOLOv9: learning what you want to learn using programmable gradient information. In: European Conference on Computer Vision, pp. 1\u201321. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Liu, L., et al.: YOLOv10: real-time end-to-end object detection. In: Advances in Neural Information Processing Systems, vol. 37, pp. 107984\u2013108011 (2024)","DOI":"10.52202\/079017-3429"},{"key":"27_CR30","unstructured":"Khanam, R., Hussain, M.: YOLOv11: an overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725 (2024)"},{"key":"27_CR31","unstructured":"Tian, Y., Ye, Q., Doermann, D.: YOLOv12: attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524 (2025)"},{"key":"27_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105057","volume":"147","author":"M Kang","year":"2024","unstructured":"Kang, M., Ting, C.M., Ting, F.F., et al.: ASF-YOLO: a novel YOLO model with attentional scale sequence fusion for cell instance segmentation. Image Vis. Comput. 147, 105057 (2024)","journal-title":"Image Vis. Comput."},{"key":"27_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126440","volume":"269","author":"H Wang","year":"2025","unstructured":"Wang, H., Liu, J., Zhao, J., et al.: Precision and speed: LSOD-YOLO for lightweight small object detection. Expert Syst. Appl. 269, 126440 (2025)","journal-title":"Expert Syst. Appl."},{"key":"27_CR34","unstructured":"Zhu, X., Su, W., Lu, L., et al.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., et al.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"27_CR36","doi-asserted-by":"crossref","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, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Yang, G., Lei, J., Zhu, Z., et al.: AFPN: asymptotic feature pyramid network for object detectioni. In: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 2184\u20132189. IEEE (2023)","DOI":"10.1109\/SMC53992.2023.10394415"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4445-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T03:44:03Z","timestamp":1768103043000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4445-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819544448","9789819544455"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4445-5_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"12 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okinawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2025.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}