{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T13:07:51Z","timestamp":1784725671203,"version":"3.55.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["No. 2019YFB2103003"],"award-info":[{"award-number":["No. 2019YFB2103003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00530-026-02429-0","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T09:15:31Z","timestamp":1780737331000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BiSD-YOLO: a compact YOLO framework for small object detection in aerial images via bidirectional fusion and sparse dynamic enhancement"],"prefix":"10.1007","volume":"32","author":[{"given":"Junhao","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeping","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siwei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"issue":"6","key":"2429_CR1","doi-asserted-by":"publisher","first-page":"9689","DOI":"10.1109\/JIOT.2019.2930656","volume":"6","author":"M Wan","year":"2019","unstructured":"Wan, M., Gu, G., Qian, W., Ren, K., Maldague, X., Chen, Q.: Unmanned aerial vehicle video-based target tracking algorithm using sparse representation. IEEE Internet Things J. 6(6), 9689\u20139706 (2019). https:\/\/doi.org\/10.1109\/JIOT.2019.2930656","journal-title":"IEEE Internet Things J."},{"issue":"5","key":"2429_CR2","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1016\/S1003-6326(23)66202-8","volume":"33","author":"J xin LIU","year":"2023","unstructured":"xin LIU, J., peng LIU, H., LIU, R., qiang XUE, J., hua LI, Y., WANG, F.: Application of aeromagnetic survey to mineral exploration of jinping, yunnan, china by using multirotor uav. Trans. Nonferrous Met. Soc. China 33(5), 1550\u20131558 (2023). https:\/\/doi.org\/10.1016\/S1003-6326(23)66202-8","journal-title":"Trans. Nonferrous Met. Soc. China"},{"key":"2429_CR3","doi-asserted-by":"publisher","unstructured":"Zhang, L., Zhang, J., Wang, B., Shen, C., Deng, C., Zhao, X.: Yolo-mslite: Lightweight multispectral object detection algorithm with feature channel-wise knowledge distillation for autonomous vehicles. IEEE Trans. Veh. Technol. , 1\u201314 (2025). https:\/\/doi.org\/10.1109\/TVT.2025.3620594","DOI":"10.1109\/TVT.2025.3620594"},{"key":"2429_CR4","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., Doll\u00e1r, P.: Microsoft coco: Common objects in context (2015), arXiv:1405.0312","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2429_CR5","unstructured":"Wang, J., Xu, C., Yang, W., Yu, L.: A normalized gaussian wasserstein distance for tiny object detection (2022), arXiv:2110.13389"},{"key":"2429_CR6","doi-asserted-by":"publisher","unstructured":"Ruan, H., Qian, W., Zheng, Z., Peng, Y.: A decoupled semantic\u2013detail learning network for remote sensing object detection in complex backgrounds. Electronics 12(14),(2023). https:\/\/doi.org\/10.3390\/electronics12143201","DOI":"10.3390\/electronics12143201"},{"issue":"2","key":"2429_CR7","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TSMC.2020.3005231","volume":"52","author":"G Chen","year":"2022","unstructured":"Chen, G., Wang, H., Chen, K., Li, Z., Song, Z., Liu, Y., Chen, W., Knoll, A.: A survey of the four pillars for small object detection: Multiscale representation, contextual information, super-resolution, and region proposal. IEEE Transactions on Systems, Man, and Cybernetics: Systems 52(2), 936\u2013953 (2022). https:\/\/doi.org\/10.1109\/TSMC.2020.3005231","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics: Systems"},{"issue":"12","key":"2429_CR8","doi-asserted-by":"publisher","first-page":"6283","DOI":"10.1007\/s00521-024-09422-6","volume":"36","author":"W Wei","year":"2024","unstructured":"Wei, W., Cheng, Y., He, J., Zhu, X.: A review of small object detection based on deep learning. Neural Comput. Appl. 36(12), 6283\u20136303 (2024). https:\/\/doi.org\/10.1007\/s00521-024-09422-6","journal-title":"Neural Comput. Appl."},{"key":"2429_CR9","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast r-cnn. In: 2015 IEEE International Conference on Computer Vision (ICCV). , 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"2429_CR10","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2429_CR11","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). , 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"2429_CR12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision - ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: Single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision - ECCV 2016, pp. 21\u201337. Springer International Publishing, Cham (2016)"},{"key":"2429_CR13","doi-asserted-by":"publisher","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., Tian, Q.: Centernet: Keypoint triplets for object detection. In : 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). pp 6568\u20136577 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00667","DOI":"10.1109\/ICCV.2019.00667"},{"key":"2429_CR14","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision - 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.) Computer Vision - ECCV 2020, pp. 213\u2013229. Springer International Publishing, Cham (2020)"},{"issue":"1","key":"2429_CR15","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/s44196-023-00302-w","volume":"16","author":"U Sirisha","year":"2023","unstructured":"Sirisha, U., Praveen, S.P., Srinivasu, P.N., Barsocchi, P., Bhoi, A.K.: Statistical Analysis of Design Aspects of Various YOLO-Based Deep Learning Models for Object Detection. Int. J. Comput. Intell. Syst. 16(1), 126 (2023). https:\/\/doi.org\/10.1007\/s44196-023-00302-w","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"2429_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, Q., Huang, H., Han, Z., Gu, Q.: (2023) A modified yolov8 detection network for uav aerial image recognition. Drones 7(5). https:\/\/doi.org\/","DOI":"10.3390\/drones7050304"},{"issue":"28","key":"2429_CR17","doi-asserted-by":"publisher","first-page":"20939","DOI":"10.1007\/s00521-023-08809-1","volume":"35","author":"FM Talaat","year":"2023","unstructured":"Talaat, F.M., ZainEldin, H.: An improved fire detection approach based on YOLO-v8 for smart cities. Neural Comput. Appl. 35(28), 20939\u201320954 (2023). https:\/\/doi.org\/10.1007\/s00521-023-08809-1","journal-title":"Neural Comput. Appl."},{"key":"2429_CR18","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":"2429_CR19","doi-asserted-by":"crossref","unstructured":"Fan, Q., Li, Y., Deveci, M., Zhong, K., Kadry, S.: Lud-yolo: A novel lightweight object detection network for unmanned aerial vehicle. Inf. Sci. 686, 121366 (2025)","DOI":"10.1016\/j.ins.2024.121366"},{"key":"2429_CR20","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, J., Zhao, J., Zhang, J., Zhao, D.: Precision and speed: Lsod-yolo for lightweight small object detection. Expert Syst. Appl. 269, 126440 (2025)","DOI":"10.1016\/j.eswa.2025.126440"},{"issue":"2","key":"2429_CR21","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/s00530-025-01702-y","volume":"31","author":"Y Xuan","year":"2025","unstructured":"Xuan, Y., Zhang, X.Y., Li, C., Wang, H., Mu, C.: Lam-yolov11 for UAV transmission line inspection: Overcoming environmental challenges with enhanced detection efficiency. Multimedia Syst. 31(2), 110 (2025). https:\/\/doi.org\/10.1007\/s00530-025-01702-y","journal-title":"Multimedia Syst."},{"key":"2429_CR22","unstructured":"Yang, B., Bender, G., Le, Q.V., Ngiam, J.: Condconv: Conditionally parameterized convolutions for efficient inference (2020), https:\/\/arxiv.org\/abs\/1904.04971"},{"key":"2429_CR23","doi-asserted-by":"publisher","unstructured":"Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: Attention over convolution kernels. In : 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp 11027\u201311036 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01104","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"2429_CR24","unstructured":"Li, C., Zhou, A., Yao, A.: Omni-dimensional dynamic convolution. In : International Conference on Learning Representations (2022), https:\/\/openreview.net\/forum?id=DmpCfq6Mg39"},{"key":"2429_CR25","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 : 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp 936\u2013944 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"2429_CR26","doi-asserted-by":"publisher","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In : 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 8759\u20138768 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2429_CR27","doi-asserted-by":"publisher","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In : 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp 10778\u201310787 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2429_CR28","unstructured":"Liu, S., Huang, D., Wang, Y.: Learning spatial fusion for single-shot object detection (2019). https:\/\/arxiv.org\/abs\/1911.09516"},{"key":"2429_CR29","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/978-3-031-72949-2_21","volume-title":"Computer Vision - ECCV 2024","author":"SE Finder","year":"2025","unstructured":"Finder, S.E., Amoyal, R., Treister, E., Freifeld, O.: Wavelet convolutions for large receptive fields. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision - ECCV 2024, pp. 363\u2013380. Springer Nature Switzerland, Cham (2025)"},{"key":"2429_CR30","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., Li, Y., Zhang, B., Liang, Y., Zhou, L., Xu, X., Chu, X., Wei, X., Wei, X.: Yolov6: A single-stage object detection framework for industrial applications. ArXiv abs\/2209.02976 (2022), https:\/\/api.semanticscholar.org\/CorpusID:252110986"},{"key":"2429_CR31","doi-asserted-by":"publisher","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In : 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp 7464\u20137475 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00721","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"2429_CR32","first-page":"1","volume-title":"Computer Vision - ECCV 2024","author":"CY Wang","year":"2025","unstructured":"Wang, C.Y., Yeh, I.H., Mark Liao, H.Y.: 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 - ECCV 2024, pp. 1\u201321. Springer Nature Switzerland, Cham (2025)"},{"key":"2429_CR33","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: Yolov10: Real-time end-to-end object detection. ArXiv abs\/2405.14458 (2024), https:\/\/api.semanticscholar.org\/CorpusID:269983404","DOI":"10.52202\/079017-3429"},{"key":"2429_CR34","unstructured":"Khanam, R., Hussain, M.: Yolov11: An overview of the key architectural enhancements (2024), arXiv: 2410.17725"},{"key":"2429_CR35","unstructured":"Tian, Y., Ye, Q., Doermann, D.: Yolov12: Attention-centric real-time object detectors (2025), https:\/\/arxiv.org\/abs\/2502.12524"},{"key":"2429_CR36","unstructured":"Lei, M., Li, S., Wu, Y., et\u00a0al.: Yolov13: Real-time object detection with hypergraph-enhanced adaptive visual perception. arXiv preprint (2025). arXiv:2506.17733"},{"key":"2429_CR37","unstructured":"Chakrabarty, S.: Yolo26: An analysis of nms-free end to end framework for real-time object detection (2026).https:\/\/arxiv.org\/abs\/2601.12882"},{"key":"2429_CR38","doi-asserted-by":"crossref","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 (2023)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"2429_CR39","doi-asserted-by":"publisher","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., et\u00a0al.: 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\u2013226 (2019). https:\/\/doi.org\/10.1109\/ICCVW.2019.00030","DOI":"10.1109\/ICCVW.2019.00030"},{"issue":"11","key":"2429_CR40","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2022","unstructured":"Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., Ling, H.: Detection and tracking meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7380\u20137399 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3119563","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2429_CR41","doi-asserted-by":"publisher","unstructured":"Yu, X., Gong, Y., Jiang, N., Ye, Q., Han, Z.: Scale match for tiny person detection. In : 2020 IEEE Winter Conference on Applications of Computer Vision (WACV). pp 1246\u20131254 (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093394","DOI":"10.1109\/WACV45572.2020.9093394"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02429-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02429-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02429-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T12:55:33Z","timestamp":1784724933000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02429-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":41,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["2429"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02429-0","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]},"assertion":[{"value":"27 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 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"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"333"}}