{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T01:36:20Z","timestamp":1773452180352,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"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":["SIViP"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s11760-024-03003-9","type":"journal-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T10:02:25Z","timestamp":1711101745000},"page":"3983-3992","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["SES-YOLOv8n: automatic driving object detection algorithm based on improved YOLOv8"],"prefix":"10.1007","volume":"18","author":[{"given":"Yang","family":"Sun","sequence":"first","affiliation":[]},{"given":"Yuhang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Haiyang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Jiushuai","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Haonan","family":"Ning","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,22]]},"reference":[{"key":"3003_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3074063","author":"F Wang","year":"2021","unstructured":"Wang, F., Wang, P., Zhang, X., Li, H., Himed, B.J.I.A.: An overview of parametric modeling and methods for radar target detection with limited data. IEEE Access (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3074063","journal-title":"IEEE Access"},{"issue":"1","key":"3003_CR2","doi-asserted-by":"publisher","first-page":"30","DOI":"10.2174\/2212797610666170215144809","volume":"10","author":"Y Zhang","year":"2017","unstructured":"Zhang, Y., Zhang, W., Bi, J.: Recent advances in driverless car. Recent Pat. Mech. Eng. 10(1), 30\u201338 (2017)","journal-title":"Recent Pat. Mech. Eng."},{"key":"3003_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/MPOT.2019.2939376","author":"M Milford","year":"2019","unstructured":"Milford, M., Anthony, S., Scheirer, W.: Self-driving vehicles: key technical challenges and progress off the road. IEEE Potentials (2019). https:\/\/doi.org\/10.1109\/MPOT.2019.2939376","journal-title":"IEEE Potentials"},{"key":"3003_CR4","doi-asserted-by":"publisher","unstructured":"O'Shea, K., & Nash, R.: An introduction to convolutional neural networks. (2015). https:\/\/doi.org\/10.48550\/arXiv.1511.08458","DOI":"10.48550\/arXiv.1511.08458"},{"issue":"1","key":"3003_CR5","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2015","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Region-based convolutional networks for accurate object detection and segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 142\u2013158 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2015.2437384","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3003_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"3003_CR7","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"3003_CR8","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017). https:\/\/doi.org\/10.48550\/arXiv.1703.06870","DOI":"10.48550\/arXiv.1703.06870"},{"key":"3003_CR9","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. (2018). https:\/\/doi.org\/10.48550\/arXiv.1804.02767","DOI":"10.48550\/arXiv.1804.02767"},{"key":"3003_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.135","author":"P Jiang","year":"2022","unstructured":"Jiang, P., Ergu, D., Liu, F., Cai, Y., Ma, B.: A review of Yolo algorithm developments. Procedia Comput Sci (2022). https:\/\/doi.org\/10.1016\/j.procs.2022.01.135","journal-title":"Procedia Comput Sci"},{"key":"3003_CR11","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":"3003_CR12","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, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3003_CR13","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, 2017, pp. 2980\u20132988. https:\/\/doi.org\/10.48550\/arXiv.1708.02002","DOI":"10.48550\/arXiv.1708.02002"},{"key":"3003_CR14","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recog-nition (2014). https:\/\/doi.org\/10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"3003_CR15","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":"3003_CR16","doi-asserted-by":"publisher","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019). https:\/\/doi.org\/10.48550\/arXiv.1905.11946","DOI":"10.48550\/arXiv.1905.11946"},{"key":"3003_CR17","unstructured":"Tan, M., Le, Q.: Efficientnetv2: smaller models and faster training. In: International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)"},{"key":"3003_CR18","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.48550\/arXiv.1905.02244","DOI":"10.48550\/arXiv.1905.02244"},{"key":"3003_CR19","doi-asserted-by":"publisher","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7132\u20137141. https:\/\/doi.org\/10.48550\/arXiv.1709.01507","DOI":"10.48550\/arXiv.1709.01507"},{"key":"3003_CR20","doi-asserted-by":"publisher","unstructured":"Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H.: Internimage: exploring large-scale vision foundation models with deformable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14408\u201314419 (2023). https:\/\/doi.org\/10.48550\/arXiv.2211.05778","DOI":"10.48550\/arXiv.2211.05778"},{"key":"3003_CR21","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 0\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"3003_CR22","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.48550\/arXiv.2103.14030","DOI":"10.48550\/arXiv.2103.14030"},{"key":"3003_CR23","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":"3003_CR24","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.48550\/arXiv.1807.06521","DOI":"10.48550\/arXiv.1807.06521"},{"key":"3003_CR25","doi-asserted-by":"publisher","unstructured":"Zhu, Y., Newsam, S.: Densenet for dense flow. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 790\u2013794. IEEE (2017).https:\/\/doi.org\/10.1109\/ICIP.2017.8296389","DOI":"10.1109\/ICIP.2017.8296389"},{"key":"3003_CR26","doi-asserted-by":"publisher","unstructured":"Zhang, H., Zu, K., Lu, J., Zou, Y., Meng, D.: EPSANet: an efficient pyramid squeeze attention block on convolutional neural network. In: Proceedings of the Asian conference on computer vision, pp. 1161\u20131177 (2022). https:\/\/doi.org\/10.48550\/arXiv.2105.14447","DOI":"10.48550\/arXiv.2105.14447"},{"key":"3003_CR27","doi-asserted-by":"publisher","unstructured":"Pan, X., Ge, C., Lu, R., Song, S., Chen, G., Huang, Z., Huang, G.: On the integration of self-attention and convolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 815\u2013825 (2022). https:\/\/doi.org\/10.48550\/arXiv.2111.14556","DOI":"10.48550\/arXiv.2111.14556"},{"key":"3003_CR28","doi-asserted-by":"publisher","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.W.: BiFormer: vision transformer with bi-level routing attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10323\u201310333 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.08810","DOI":"10.48550\/arXiv.2303.08810"},{"key":"3003_CR29","doi-asserted-by":"crossref","unstructured":"Liu, J.-J., Hou, Q., Cheng, M.-M., Feng, J., Jiang, J: A simple pooling-based design for real-time salient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3917\u20133926 (2019)","DOI":"10.1109\/CVPR.2019.00404"},{"key":"3003_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, Y., Wang, S., Liang, T., Zhao, Q., Tang, Z., Ling, H.: Cbnet: a novel composite backbone network architecture for object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11653\u201311660 (2020)","DOI":"10.1609\/aaai.v34i07.6834"},{"key":"3003_CR31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2900709","author":"JU Kim","year":"2019","unstructured":"Kim, J.U., Kwon, J., Kim, H.G., Ro, Y.M.: BBC net: bounding-box critic network for occlusion-robust object detection. IEEE Trans. Circuits Syst. Video Technol. (2019). https:\/\/doi.org\/10.1109\/TCSVT.2019.2900709","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3003_CR32","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11142154","author":"X Xi","year":"2022","unstructured":"Xi, X., Wang, J., Li, F., Li, D.J.E.: IRSDet: Infrared small-object detection network based on sparse-skip connection and guide maps. Electronics (2022). https:\/\/doi.org\/10.3390\/electronics11142154","journal-title":"Electronics"},{"key":"3003_CR33","doi-asserted-by":"publisher","DOI":"10.3390\/s23041801","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Sun, Y., Wang, Z., Jiang, Y.J.S.: YOLOv7-RAR for Urban vehicle detection. Sensors (2023). https:\/\/doi.org\/10.3390\/s23041801","journal-title":"Sensors"},{"key":"3003_CR34","doi-asserted-by":"publisher","unstructured":"Ouyang, D., He, S., Zhang, G., Luo, M., Guo, H., Zhan, J., Huang, Z.: Efficient multi-scale attention module with cross-spatial learning. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096516","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"3003_CR35","doi-asserted-by":"publisher","unstructured":"Sunkara, R., Luo, T.: No more strided convolutions or pooling: A new CNN building block for low-resolution images and small objects. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 443\u2013459. Springer (2022). https:\/\/doi.org\/10.48550\/arXiv.2208.03641","DOI":"10.48550\/arXiv.2208.03641"},{"key":"3003_CR36","doi-asserted-by":"publisher","unstructured":"Cao, Y., Chen, K., Loy, C.C., Lin, D.: Prime sample attention in object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11583\u201311591 (2020). https:\/\/doi.org\/10.48550\/arXiv.1904.04821","DOI":"10.48550\/arXiv.1904.04821"},{"key":"3003_CR37","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u2013747 (2023). https:\/\/doi.org\/10.48550\/arXiv.2207.02696","DOI":"10.48550\/arXiv.2207.02696"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03003-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03003-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03003-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T13:15:14Z","timestamp":1716470114000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03003-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,22]]},"references-count":37,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["3003"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03003-9","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,22]]},"assertion":[{"value":"22 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2024","order":4,"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"}}]}}