{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T23:08:12Z","timestamp":1783465692972,"version":"3.55.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":26,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100010822","name":"Chengdu Science and Technology Bureau","doi-asserted-by":"publisher","award":["2025-YF11-00077-HZ"],"award-info":[{"award-number":["2025-YF11-00077-HZ"]}],"id":[{"id":"10.13039\/501100010822","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s00371-026-04404-2","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:35:05Z","timestamp":1774589705000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing UAV aerial small target detection with bidirectional dynamic multi-scale attention YOLO"],"prefix":"10.1007","volume":"42","author":[{"given":"Zhenzhu","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinzhao","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"issue":"S1","key":"4404_CR1","first-page":"185","volume":"52","author":"P Yang","year":"2021","unstructured":"Yang, P., Zhao, Y.Y., Li, Y.M., Wu, Y.F., Li, W.R., Li, Z.B.: Review of research on integration of agricultural air-ground integration based on multi-source information fusion. Trans. Chin. Soc. Agric. Mach. 52(S1), 185\u2013196 (2021)","journal-title":"Trans. Chin. Soc. Agric. Mach."},{"key":"4404_CR2","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/JMASS.2021.3083659","volume":"2","author":"J Dong","year":"2021","unstructured":"Dong, J., Ota, K., Dong, M.: UAV-based real-time survivor detection system in post-disaster search and rescue operations. IEEE J. Miniat. Air Space Syst. 2, 209\u2013219 (2021)","journal-title":"IEEE J. Miniat. Air Space Syst."},{"key":"4404_CR3","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics (2023)"},{"key":"4404_CR4","doi-asserted-by":"crossref","unstructured":"Domozi, Z., Stojcsics, D., Benhamida, A., Kozlovszky, M., Molnar, A.: Real time object detection for aerial search and rescue missions for missing persons. In: Proceedings of the 2020 IEEE 15th International Conference of System of Systems Engineering (SoSE), Budapest, Hungary, 2\u20134 June 2020, pp. 519\u2013524 (2020)","DOI":"10.1109\/SoSE50414.2020.9130475"},{"key":"4404_CR5","doi-asserted-by":"publisher","first-page":"3032","DOI":"10.1109\/JSTARS.2020.3000317","volume":"13","author":"M Haroon","year":"2020","unstructured":"Haroon, M., Shahzad, M., Fraz, M.M.: Multisized object detection using spaceborne optical imagery. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 13, 3032\u20133046 (2020)","journal-title":"IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens."},{"key":"4404_CR6","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"4404_CR7","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: single shot multibox detector. In: Proceedings of the European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"4404_CR8","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"4404_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"4404_CR10","doi-asserted-by":"crossref","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), (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"4404_CR11","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4404_CR12","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Pang, R., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"4404_CR13","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"4404_CR14","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"4404_CR15","unstructured":"Ouyang, D., He, S., Zhan, J., Guo, H., Huang, Z., Luo, M., Zhang, G.: Efficient multi-scale attention module with cross-spatial learning. arXiv preprint arXiv:2305.13563 (2021)"},{"key":"4404_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, X., Li, J., Liu, L., Xue, Z., Zhang, B., Jiang, Z., Huang, T., Wang, Y., Wang, C.: Rethinking mobile block for efficient attention-based models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1389\u20131400 (2023)","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"4404_CR17","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"4404_CR18","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems 30 (NIPS), (2017)"},{"key":"4404_CR19","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., Chua, T.S.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"4404_CR20","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: ShuffleNet V2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"4404_CR21","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"},{"key":"4404_CR22","unstructured":"Li, X., Ding, H., Zhang, W., Yuan, H., Cheng, G., Jiangmiao, P., Chen, K., Liu, Z., Loy, C.C.: Transformer-based visual segmentation: a survey. arXiv preprint arXiv:2304.09854 (2023)"},{"key":"4404_CR23","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: PVT v2: improved baselines with pyramid vision transformer. Comput. arXiv preprint arXiv:2106.13797"},{"key":"4404_CR24","unstructured":"Zhang, J., Li, X., Wang, Y., Wang, C., Yang, Y., Liu, Y., Tao, D.: EATFormer: improving vision transformer inspired by evolutionary algorithm. arXiv preprint arXiv:2206.09325 (2022)"},{"key":"4404_CR25","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. arXiv preprint arXiv:2304.08069 (2023).","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"4404_CR26","doi-asserted-by":"publisher","first-page":"48572","DOI":"10.1109\/ACCESS.2019.2909530","volume":"7","author":"H Shakhatreh","year":"2019","unstructured":"Shakhatreh, H., Sawalmeh, A.H., Al-Fuqaha, A., Dou, Z., Almaita, E., Khalil, I., Othman, N.S., Khreishah, A., Guizani, M.: Unmanned aerial vehicles (UAVs): A survey on civil applications and key research challenges. IEEE Access 7, 48572\u201348634 (2019)","journal-title":"IEEE Access"},{"issue":"1","key":"4404_CR27","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s11370-022-00452-4","volume":"16","author":"SAH Mohsan","year":"2023","unstructured":"Mohsan, S.A.H., Khan, M.A., Noor, F., Ullah, I., Alsharif, M.H.: Unmanned aerial vehicles (UAVs): practical aspects, applications, open challenges, security issues, and future trends. Intell. Serv. Robot. 16(1), 109\u2013137 (2023)","journal-title":"Intell. Serv. Robot."},{"key":"4404_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103615","volume":"91","author":"B Bosquet","year":"2020","unstructured":"Bosquet, B., Mucientes, M., Brea, V.M.: STDnet: Exploiting high resolution feature maps for small object detection. Eng. Appl. Artif. Intell. 91, 103615 (2020)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"4404_CR29","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.isprsjprs.2014.10.002","volume":"98","author":"G Cheng","year":"2014","unstructured":"Cheng, G., Han, J., Zhou, P., Guo, L.: Multi-class geospatial object detection and geographic image classification based on collection of part detectors. ISPRS J. Photogramm. Remote Sens. 98, 119\u2013132 (2014)","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"4404_CR30","unstructured":"Ramachandran, P., Zoph, B., Le, Q.V.: Searching for Activation Functions. arXiv preprint arXiv:1710.05941 (2017)"},{"key":"4404_CR31","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: Convolutional Block Attention Module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"4404_CR32","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 (CVPR), pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"4404_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"4404_CR34","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"4404_CR35","doi-asserted-by":"publisher","first-page":"8927","DOI":"10.1007\/s00371-024-03284-8","volume":"40","author":"K Tong","year":"2024","unstructured":"Tong, K., Wu, Y.: I-YOLO: a novel single-stage framework for small object detection. Vis. Comput. 40, 8927\u20138944 (2024)","journal-title":"Vis. Comput."},{"key":"4404_CR36","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., Liao, H.Y.M.: YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. arXiv preprint arXiv:2402.13616 (2024)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"4404_CR37","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: YOLOv10: Real-Time End-to-End Object Detection. arXiv preprint arXiv:2405.14458 (2024)"},{"key":"4404_CR38","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., Zhang, L.: DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR. In: Proceedings of the International Conference on Learning Representations (ICLR) (2022)"},{"key":"4404_CR39","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.Y.: DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"4404_CR40","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: Deformable Transformers for End-to-End Object Detection. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"},{"key":"4404_CR41","doi-asserted-by":"crossref","unstructured":"Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., Ouyang, W., Loy, C.C., Lin, D.: Hybrid Task Cascade for Instance Segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4974\u20134983 (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"4404_CR42","doi-asserted-by":"crossref","unstructured":"Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-Aware Trident Networks for Object Detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 6054\u20136063 (2019)","DOI":"10.1109\/ICCV.2019.00615"},{"key":"4404_CR43","unstructured":"Wei, H., Liu, X., Xu, S., Dai, Z., Dai, Y., Xu, X.: DWRSeg: Rethinking efficient acquisition of multi-scale contextual information for real-time semantic segmentation. In: Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1234\u20131245 (2023)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04404-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-026-04404-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-026-04404-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T13:40:08Z","timestamp":1775742008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-026-04404-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["4404"],"URL":"https:\/\/doi.org\/10.1007\/s00371-026-04404-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"10 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 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 no conflict of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"227"}}