{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T17:00:09Z","timestamp":1781974809720,"version":"3.54.5"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s11554-024-01585-8","type":"journal-article","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T09:16:57Z","timestamp":1732267017000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Improved real-time object detection method based on YOLOv8: a refined approach"],"prefix":"10.1007","volume":"22","author":[{"given":"Jiaqi","family":"Zhong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaming","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huilin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenna","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yipeng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"issue":"11","key":"1585_CR1","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao, Z.Q., Zheng, P., Xu, S., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212\u20133232 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1585_CR2","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neucom.2020.01.085","volume":"396","author":"X Wu","year":"2020","unstructured":"Wu, X., Sahoo, D., Hoi, S.C.: Recent advances in deep learning for object detection. Neurocomputing 396, 39\u201364 (2020)","journal-title":"Neurocomputing"},{"issue":"3","key":"1585_CR3","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"},{"issue":"14","key":"1585_CR4","doi-asserted-by":"publisher","first-page":"21353","DOI":"10.1007\/s11042-022-13801-3","volume":"82","author":"E Arkin","year":"2023","unstructured":"Arkin, E., Yadikar, N., Xu, X., Aysa, A., Ubul, K.: A survey: object detection methods from CNN to transformer. Multimed. Tools Appl. 82(14), 21353\u201321383 (2023)","journal-title":"Multimed. Tools Appl."},{"key":"1585_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An Image is Worth $$16\\times 16$$ Words: Transformers for Image Recognition at Scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1585_CR6","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 (ICCV), pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1585_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Chen, D., Liu, M., Dong, X., Yuan, L., Liu, Z.: Mobile-former: bridging mobilenet and transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5270\u20135279 (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"1585_CR8","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Lin, Z., Han, J., Ding, G.: Repvit: revisiting mobile cnn from vit perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15909\u201315920 (2024)","DOI":"10.1109\/CVPR52733.2024.01506"},{"key":"1585_CR9","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, Sh., 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":"1585_CR10","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"1585_CR11","unstructured":"Yang, L., Zhang, R.Y., Li, L., Xie, X.: Simam: a simple, parameter-free attention module for convolutional neural networks. In: International Conference on Machine Learning. PMLR, pp. 11863\u201311874 (2021)"},{"issue":"12","key":"1585_CR12","doi-asserted-by":"publisher","first-page":"12135","DOI":"10.1002\/int.23079","volume":"37","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Zhang, C., Wu, W., Zhang, B., Zhou, F.: Miniyolo: a lightweight object detection algorithm that realizes the trade-off between model size and detection accuracy. Int. J. Intell. Syst. 37(12), 12135\u201312151 (2022)","journal-title":"Int. J. Intell. Syst."},{"key":"1585_CR13","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":"1585_CR14","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":"1585_CR15","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An Incremental Improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"1585_CR16","doi-asserted-by":"crossref","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\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1585_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: 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":"1585_CR18","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., Polosukhin, I.: Attention is All You Need (nips), 2017. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"1585_CR19","unstructured":"Alexey, D.: An Image is Worth 16 $$\\times$$ 16 Words: Transformers for Image recognition at Scale. arXiv preprint arXiv: 2010.11929 (2020)"},{"key":"1585_CR20","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1585_CR21","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":"1585_CR22","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":"1585_CR23","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: Repvgg: Making vgg-style convnets great again. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13733\u201313742 (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"1585_CR24","unstructured":"Howard, AG., 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":"1585_CR25","doi-asserted-by":"crossref","unstructured":"Chu, X., Zhang, B., Xu, R.: Moga: searching beyond mobilenetv3. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4042\u20134046. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054428"},{"key":"1585_CR26","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":"1585_CR27","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1585_CR28","doi-asserted-by":"crossref","unstructured":"Peng, Z., Huang, W., Gu, S., Xie, L., Wang, Y., Jiao, J., Ye, Q.: Conformer: local features coupling global representations for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 367\u2013376 (2021)","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"1585_CR29","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Han, J., Ding, G.: Diverse branch block: building a convolution as an inception-like unit. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10886\u201310895 (2021)","DOI":"10.1109\/CVPR46437.2021.01074"},{"key":"1585_CR30","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":"1585_CR31","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1016\/j.neunet.2022.08.029","volume":"155","author":"K Min","year":"2022","unstructured":"Min, K., Lee, G.H., Lee, S.W.: Attentional feature pyramid network for small object detection. Neural Netw. 155, 439\u2013450 (2022)","journal-title":"Neural Netw."},{"key":"1585_CR32","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: Ghostnet: more features from cheap operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1580\u20131589 (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"1585_CR33","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":"1585_CR34","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":"1585_CR35","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"1585_CR36","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11534\u201311542 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"issue":"5","key":"1585_CR37","first-page":"995","volume":"32","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Ma, M., Wang, Z., Li, J., Sun, Y.: Podyolo object detection model based on bi-directional dynamic cross-level pyramid network. Eng. Lett. 32(5), 995\u20131003 (2024)","journal-title":"Eng. Lett."},{"issue":"2","key":"1585_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e24143","volume":"10","author":"S Wang","year":"2024","unstructured":"Wang, S., Hao, X.: YOLO-SK: a lightweight multiscale object detection algorithm. Heliyon 10(2), e24143 (2024)","journal-title":"Heliyon"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01585-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01585-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01585-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,3]],"date-time":"2025-02-03T17:16:19Z","timestamp":1738602979000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01585-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["1585"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01585-8","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"27 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2024","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 interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"4"}}