{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T14:08:55Z","timestamp":1792159735134,"version":"4.4.0"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.12101289"],"award-info":[{"award-number":["No.12101289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["No.2020J01821"],"award-info":[{"award-number":["No.2020J01821"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["No.2022J01891"],"award-info":[{"award-number":["No.2022J01891"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00371-024-03355-w","type":"journal-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T01:01:48Z","timestamp":1713747708000},"page":"675-693","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["E-FPN: an enhanced feature pyramid network for UAV scenarios detection"],"prefix":"10.1007","volume":"41","author":[{"given":"Zhongxu","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8372-7314","authenticated-orcid":false,"given":"Wenyuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,22]]},"reference":[{"issue":"3","key":"3355_CR1","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. Proc. IEEE 111(3), 257\u2013276 (2023)","journal-title":"Proc. IEEE"},{"key":"3355_CR2","doi-asserted-by":"crossref","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis. Comput. 38, 2939\u20132970 (2022)","DOI":"10.1007\/s00371-021-02166-7"},{"key":"3355_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, G., Chen, X., Tan, X., Zhang, J., Lan, X.: U-YOLO: improved YOLOv5 for small object detection on UAV-captured images. In: Cognitive Computation and Systems: First International Conference, pp. 3\u201315 (2023)","DOI":"10.1007\/978-981-99-2789-0_1"},{"key":"3355_CR4","doi-asserted-by":"crossref","unstructured":"Xu, B., Wang, C., Liu, Y., Zhou, Y.: An anchor-based convolutional network for the near-surface camouflaged personnel detection of UAVs. Vis. Comput. 40, 1659\u20131671 (2024)","DOI":"10.1007\/s00371-023-02877-z"},{"key":"3355_CR5","doi-asserted-by":"crossref","unstructured":"Li, Y.l., Feng, Y., Zhou, M.l., Xiong, X.C., Wang, Y.H., Qiang, B.H.: DMA-YOLO: multi-scale object detection method with attention mechanism for aerial images. Vis. Comput. 1\u201314 (2023). https:\/\/doi.org\/10.1007\/s00371-023-03095-3","DOI":"10.1007\/s00371-023-03095-3"},{"issue":"3","key":"3355_CR6","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng, D., Haase Sch\u00fctz, C., Rosenbaum, L., Hertlein, H., Glaeser, C., Timm, F., Wiesbeck, W., Dietmayer, K.: Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans. Intell. Transp. Syst. 22(3), 1341\u20131360 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"6","key":"3355_CR7","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"BR Kiran","year":"2022","unstructured":"Kiran, B.R., Sobh, I., Talpaert, V., Mannion, P., Sallab, A.A.A., Yogamani, S., P\u00e9rez, P.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. 23(6), 4909\u20134926 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3355_CR8","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1007\/s00371-020-01831-7","volume":"37","author":"W Chen","year":"2021","unstructured":"Chen, W., Huang, H., Peng, S., Zhou, C., Zhang, C.: YOLO-face: a real-time face detector. Vis. Comput. 37, 805\u2013813 (2021)","journal-title":"Vis. Comput."},{"key":"3355_CR9","unstructured":"Yu, Z., Huang, H., Chen, W., Su, Y., Liu, Y., Wang, X.: YOLO-FACEV2: a scale and occlusion aware face detector. arXiv preprint arXiv:2208.02019 (2022)"},{"key":"3355_CR10","doi-asserted-by":"crossref","unstructured":"Yuan, W., Fu, C., Liu, R., Fan, X.: SSoB: searching a scene-oriented architecture for underwater object detection. Vis Comput 39, 5199\u20135208 (2023)","DOI":"10.1007\/s00371-022-02654-4"},{"key":"3355_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"9","key":"3355_CR12","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3355_CR13","first-page":"1","volume":"39","author":"S Ren","year":"2015","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, 1\u201314 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3355_CR14","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, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3355_CR15","doi-asserted-by":"crossref","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, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3355_CR16","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"3355_CR17","unstructured":"Redmon, J., Farhadi, A.: YOLOV3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"3355_CR18","unstructured":"Bochkovskiy, A., Wang, C., Liao, H.M.: YOLOV4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"3355_CR19","unstructured":"Jocher, G.: YOLOv5 by Ultralytics (2020)"},{"key":"3355_CR20","unstructured":"Li, C., Li, L., Geng, Y., Jiang, H., Cheng, M., Zhang, B., Ke, Z., Xu, X., Chu, X.: YOLOV6 v3.0: a full-scale reloading. arXiv preprint arXiv:2301.05586 (2023)"},{"key":"3355_CR21","doi-asserted-by":"crossref","unstructured":"Wang, C., Bochkovskiy, A., Liao, H.M.: YOLOV7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"3355_CR22","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"3355_CR23","unstructured":"Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., Wang, G., Dang, Q., Wei, S., Du, Y., et al.: PP-YOLOE: An evolved version of YOLO. arXiv preprint arXiv:2203.16250 (2022)"},{"key":"3355_CR24","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: YOLO by Ultralytics (2023)"},{"key":"3355_CR25","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.rse.2018.06.028","volume":"216","author":"B Kellenberger","year":"2018","unstructured":"Kellenberger, B., Marcos, D., Tuia, D.: Detecting mammals in UAV images: best practices to address a substantially imbalanced dataset with deep learning. Remote Sens. Environ. 216, 139\u2013153 (2018)","journal-title":"Remote Sens. Environ."},{"issue":"4","key":"3355_CR26","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MCOM.2018.1700422","volume":"56","author":"J Gu","year":"2018","unstructured":"Gu, J., Su, T., Wang, Q., Du, X., Guizani, M.: Multiple moving targets surveillance based on a cooperative network for multi-UAV. IEEE Commun. Mag. 56(4), 82\u201389 (2018)","journal-title":"IEEE Commun. Mag."},{"key":"3355_CR27","doi-asserted-by":"crossref","unstructured":"Huang, J., Jiang, X., Jin, G.: Detection of river floating debris in UAV images based on improved YOLOV5. In: 2022 International Joint Conference on Neural Networks, pp. 1\u20138 (2022)","DOI":"10.1109\/IJCNN55064.2022.9892392"},{"key":"3355_CR28","doi-asserted-by":"publisher","first-page":"8085","DOI":"10.1109\/JSTARS.2022.3206399","volume":"15","author":"W Liu","year":"2022","unstructured":"Liu, W., Quijano, K., Crawford, M.M.: YOLOv5-Tassel: Detecting tassels in RGB UAV imagery with improved YOLOv5 based on transfer learning. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 15, 8085\u20138094 (2022)","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"issue":"1","key":"3355_CR29","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s00371-021-02331-y","volume":"39","author":"J Fan","year":"2023","unstructured":"Fan, J., Yang, X., Lu, R., Li, W., Huang, Y.: Long-term visual tracking algorithm for UAVs based on kernel correlation filtering and surf features. Vis Comput 39(1), 319\u2013333 (2023)","journal-title":"Vis Comput"},{"issue":"6","key":"3355_CR30","first-page":"84","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 60(6), 84\u201390 (2017)","journal-title":"Adv Neural Inf Process Syst"},{"key":"3355_CR31","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"3355_CR32","doi-asserted-by":"crossref","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3355_CR33","doi-asserted-by":"crossref","unstructured":"Wang, C., Liao, H.M., Wu, Y.H., Chen, P., Hsieh, J.W., Yeh, I.H.: CSPNet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"3355_CR34","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"3355_CR35","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"3355_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3355_CR37","unstructured":"Mehta, S., Rastegari, M.: MobileVit: light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178 (2021)"},{"key":"3355_CR38","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"3355_CR39","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, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"3355_CR40","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V.: Searching for MobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"3355_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"3355_CR42","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, pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"3355_CR43","unstructured":"Xu, X., Jiang, Y., Chen, W., Huang, Y., Zhang, Y., Sun, X.: DAMO-YOLO: a report on real-time object detection design. arXiv preprint arXiv:2211.15444 (2022)"},{"key":"3355_CR44","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: Computer Vision\u2013ECCV 2016: 14th European Conference, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3355_CR45","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: PaNet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9197\u20139206 (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"3355_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Sheng, T., Wang, Y., Tang, Z., Chen, Y., Cai, L., Ling, H.: M2Det: A single-shot object detector based on multi-level feature pyramid network. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 9259\u20139266 (2019)","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"3355_CR47","doi-asserted-by":"crossref","unstructured":"Ghaisi, G., Lin, T.Y., Pang, R., NAS-FPN, Q.V.L.: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE Computer Vision and Pattern Recognition, pp. 7029\u20137038 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"3355_CR48","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":"3355_CR49","unstructured":"Jiang, Y., Tan, Z., Wang, J., Sun, X., Lin, M., Li, H.: GiraffeDet: a heavy-neck paradigm for object detection. arXiv preprint arXiv:2202.04256 (2022)"},{"key":"3355_CR50","doi-asserted-by":"crossref","unstructured":"Wang, G., Li, J., Wu, Z., Xu, J., Shen, J., Yang, W.: EfficientFace: an efficient deep network with feature enhancement for accurate face detection. arXiv preprint arXiv:2302.11816 (2023)","DOI":"10.1007\/s00530-023-01134-6"},{"key":"3355_CR51","doi-asserted-by":"crossref","unstructured":"Yang, G., Lei, J., Zhu, Z., Cheng, S., Feng, Z., Liang, R.: AFPN: asymptotic feature pyramid network for object detection. arXiv preprint arXiv:2306.15988 (2023)","DOI":"10.1109\/SMC53992.2023.10394415"},{"key":"3355_CR52","doi-asserted-by":"crossref","unstructured":"Chen, C., Zhang, Y., Lv, Q., Wei, S., Wang, X., Sun, X., Dong, J.: RRNet: a hybrid detector for object detection in drone-captured images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 100\u2013108 (2019)","DOI":"10.1109\/ICCVW.2019.00018"},{"issue":"19","key":"3355_CR53","doi-asserted-by":"publisher","first-page":"3140","DOI":"10.3390\/rs12193140","volume":"12","author":"R Zhang","year":"2020","unstructured":"Zhang, R., Shao, Z., Huang, X., Wang, J., Li, D.: Object detection in UAV images via global density fused convolutional network. Remote Sens. 12(19), 3140\u20133143 (2020)","journal-title":"Remote Sens."},{"key":"3355_CR54","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., Liu, J., Yang, W.: A dual neural network for object detection in UAV images. Neurocomputing 443, 292\u2013301 (2021)","journal-title":"Neurocomputing"},{"key":"3355_CR55","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.neucom.2022.03.033","volume":"489","author":"R Zhang","year":"2022","unstructured":"Zhang, R., Shao, Z., Huang, X., Wang, J., Wang, Y., Li, D.: Adaptive dense pyramid network for object detection in UAV imagery. Neurocomputing 489, 377\u2013389 (2022)","journal-title":"Neurocomputing"},{"key":"3355_CR56","doi-asserted-by":"crossref","unstructured":"Zeng, S., Yang, W., Jiao, Y., Geng, L., Chen, X.: SCA-YOLO:: a new small object detection model for UAV images. Vis. Comput. 40, 1787\u20131803 (2024)","DOI":"10.1007\/s00371-023-02886-y"},{"key":"3355_CR57","doi-asserted-by":"publisher","first-page":"126384","DOI":"10.1016\/j.neucom.2023.126384","volume":"547","author":"T Wang","year":"2023","unstructured":"Wang, T., Ma, Z., Yang, T., Zou, S.: PETNet: a YOLO-based prior enhanced transformer network for aerial image detection. Neurocomputing 547, 126384\u2013126390 (2023)","journal-title":"Neurocomputing"},{"key":"3355_CR58","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"3355_CR59","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural Inf. Process. Syst. 33, 21002\u201321012 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"11","key":"3355_CR60","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2021","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 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3355_CR61","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3355_CR62","doi-asserted-by":"crossref","unstructured":"Chen, Z., Huang, S., Lv, H., Luo, Z., Liu, J.: Defect detection in automotive glass based on modified YOLOv5 with multi-scale feature fusion and dual lightweight strategy. Vis. Comput. 1432\u20132315 (2024). https:\/\/doi.org\/10.1007\/s00371-023-03225-x","DOI":"10.1007\/s00371-023-03225-x"},{"key":"3355_CR63","doi-asserted-by":"crossref","unstructured":"Yu, W., Yang, T., Chen, C.: Towards resolving the challenge of long-tail distribution in D images for object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3258\u20133267 (2021)","DOI":"10.1109\/WACV48630.2021.00330"},{"key":"3355_CR64","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, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"3355_CR65","doi-asserted-by":"crossref","unstructured":"Albaba, B.M., Ozer, S.: SyNet: an ensemble network for object detection in UAV images. In: 2020 25th International Conference on Pattern Recognition, pp. 10227\u201310234 (2021)","DOI":"10.1109\/ICPR48806.2021.9412847"},{"key":"3355_CR66","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., Peng, T., Zheng, J., : VisDrone-DET2019: the vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 213\u2013226 (2019)"},{"issue":"7","key":"3355_CR67","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.3390\/s20071861","volume":"20","author":"H Zhao","year":"2020","unstructured":"Zhao, H., Zhou, Y., Zhang, L., Peng, Y., Hu, X., Peng, H., Cai, X.: Mixed YOLOv3-LITE: a lightweight real-time object detection method. Sensors 20(7), 1861\u20131873 (2020)","journal-title":"Sensors"},{"key":"3355_CR68","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1109\/JSTARS.2023.3234161","volume":"16","author":"W Lu","year":"2023","unstructured":"Lu, W., Lan, C., Niu, C., Liu, W., Lyu, L., Shi, Q., Wang, S.: A CNN-transformer hybrid model based on CSWin transformer for UAV imageobject detection. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 16, 1211\u20131231 (2023)","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"3355_CR69","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: Tood: task-aligned one-stage object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision, pp. 3490\u20133499 (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"3355_CR70","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114 (2019)"},{"key":"3355_CR71","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"3355_CR72","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, S.H., He, H., Zhuo, W., Wen, S., Lee, C.H., Chan, S.H.G.: Run, don\u2019t walk: chasing higher flops for faster neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12021\u201312031 (2023)","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"3355_CR73","first-page":"9969","volume":"35","author":"Y Tang","year":"2022","unstructured":"Tang, Y., Han, K., Guo, J., Xu, C., Xu, C., Wang, Y.: GhostNetv2: enhance cheap operation with long-range attention. Adv Neural Inf Process Syst 35, 9969\u20139982 (2022)","journal-title":"Adv Neural Inf Process Syst"},{"key":"3355_CR74","unstructured":"Chen, H., Wang, Y., Guo, J., Tao, D.: VanillaNet: the power of minimalism in deep learning. arXiv preprint arXiv:2305.12972 (2023)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03355-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03355-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03355-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T17:55:02Z","timestamp":1737741302000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03355-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,22]]},"references-count":74,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["3355"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03355-w","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,22]]},"assertion":[{"value":"28 February 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}