{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T12:01:03Z","timestamp":1758628863146,"version":"3.37.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T00:00:00Z","timestamp":1738022400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T00:00:00Z","timestamp":1738022400000},"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":[[2025,3]]},"DOI":"10.1007\/s11760-025-03831-3","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:47:37Z","timestamp":1738090057000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["LKStar-Yolov8n: an autonomous driving object detection algorithm based on large convolution kernel star structure of Yolov8n"],"prefix":"10.1007","volume":"19","author":[{"given":"Yang","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiushuai","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Ning","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"key":"3831_CR1","doi-asserted-by":"publisher","first-page":"18185","DOI":"10.1109\/TITS.2024.3417826","volume":"25","author":"Z Meng","year":"2024","unstructured":"Meng, Z., Song, Y., Zhang, Y., Nan, Y., Bai, Z.: Traffic object detection for autonomous driving fusing LiDAR and Pseudo 4D-radar under bird\u2019s-eye-view. IEEE Trans. Intell. Transp. Syst. 25, 18185\u201318195 (2024). https:\/\/doi.org\/10.1109\/TITS.2024.3417826","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3831_CR2","doi-asserted-by":"publisher","first-page":"17160","DOI":"10.1109\/TITS.2024.3432761","volume":"25","author":"N Hoanh","year":"2024","unstructured":"Hoanh, N., Vu Pham, T.: A multi-task framework for car detection from high-resolution UAV imagery focusing on road regions. IEEE Trans. Intell. Transp. Syst. 25, 17160\u201317173 (2024). https:\/\/doi.org\/10.1109\/TITS.2024.3432761","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3831_CR3","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition. pp. 580\u2013587. IEEE, Columbus, OH, USA (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"3831_CR4","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"3831_CR5","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., others: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929. (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"3831_CR6","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European conference on computer vision. pp. 213\u2013229. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3831_CR7","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, http:\/\/arxiv.org\/abs\/2103.14030, (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3831_CR8","doi-asserted-by":"publisher","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. (2021). https:\/\/doi.org\/10.48550\/arXiv.2010.04159","DOI":"10.48550\/arXiv.2010.04159"},{"key":"3831_CR9","doi-asserted-by":"publisher","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16965\u201316974 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01605","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"3831_CR10","doi-asserted-by":"publisher","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. arXiv preprint arXiv:2203.03605. (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.03605","DOI":"10.48550\/arXiv.2203.03605"},{"key":"3831_CR11","doi-asserted-by":"publisher","unstructured":"Lv, W., Zhao, Y., Chang, Q., Huang, K., Wang, G., Liu, Y.: RT-DETRv2: Improved baseline with bag-of-freebies for real-time detection transformer. arXiv preprint arXiv:2407.17140. (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.17140","DOI":"10.48550\/arXiv.2407.17140"},{"key":"3831_CR12","doi-asserted-by":"publisher","unstructured":"Ding, X., Zhang, X., Han, J., Ding, G.: Scaling up your kernels to 31x31: revisiting large kernel design in cnns. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 11963\u201311975 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01166","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"3831_CR13","doi-asserted-by":"publisher","unstructured":"Liu, S., Chen, T., Chen, X., Chen, X., Xiao, Q., Wu, B., K\u00e4rkk\u00e4inen, T., Pechenizkiy, M., Mocanu, D., Wang, Z.: More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity, http:\/\/arxiv.org\/abs\/2207.03620, (2023). https:\/\/doi.org\/10.48550\/arXiv.2207.03620","DOI":"10.48550\/arXiv.2207.03620"},{"key":"3831_CR14","doi-asserted-by":"publisher","unstructured":"Ding, X., Zhang, Y., Ge, Y., Zhao, S., Song, L., Yue, X., Shan, Y.: UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition, http:\/\/arxiv.org\/abs\/2311.15599, (2024). https:\/\/doi.org\/10.48550\/arXiv.2311.15599","DOI":"10.48550\/arXiv.2311.15599"},{"key":"3831_CR15","doi-asserted-by":"publisher","unstructured":"Ma, X., Dai, X., Bai, Y., Wang, Y., Fu, Y.: Rewrite the stars, http:\/\/arxiv.org\/abs\/2403.19967, (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.19967","DOI":"10.48550\/arXiv.2403.19967"},{"key":"3831_CR16","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: Single shot multibox detector. In: Computer 473 Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, 474 The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, 475 pp. 21\u201337. Springer (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3831_CR17","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. pp. 2980\u20132988 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.324","DOI":"10.1109\/ICCV.2017.324"},{"key":"3831_CR18","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.48550\/arXiv.1911.09070","DOI":"10.48550\/arXiv.1911.09070"},{"key":"3831_CR19","doi-asserted-by":"publisher","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850. (2019). https:\/\/doi.org\/10.48550\/arXiv.1904.07850","DOI":"10.48550\/arXiv.1904.07850"},{"key":"3831_CR20","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Con-ference on Computer Vision (ICCV), 2015, pp. 1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"3831_CR21","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, 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3831_CR22","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN, http:\/\/arxiv.org\/abs\/1703.06870, (2018). https:\/\/doi.org\/10.48550\/arXiv.1703.06870","DOI":"10.48550\/arXiv.1703.06870"},{"key":"3831_CR23","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: Better, faster, stronger, http:\/\/arxiv.org\/abs\/1612.08242, (2016). https:\/\/doi.org\/10.48550\/arXiv.1612.08242","DOI":"10.48550\/arXiv.1612.08242"},{"key":"3831_CR24","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: An incremental improvement, http:\/\/arxiv.org\/abs\/1804.02767, (2018). https:\/\/doi.org\/10.48550\/arXiv.1804.02767","DOI":"10.48550\/arXiv.1804.02767"},{"key":"3831_CR25","doi-asserted-by":"publisher","unstructured":"Bochkovskiy, A.: YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. (2020). https:\/\/doi.org\/10.48550\/arXiv.2004.10934","DOI":"10.48550\/arXiv.2004.10934"},{"key":"3831_CR26","doi-asserted-by":"publisher","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., others: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976. (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.02976","DOI":"10.48550\/arXiv.2209.02976"},{"key":"3831_CR27","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\u20137475 (2023). https:\/\/doi.org\/10.48550\/arXiv.2207.02696","DOI":"10.48550\/arXiv.2207.02696"},{"key":"3831_CR28","doi-asserted-by":"publisher","unstructured":"Varghese, R., Sambath, M.: YOLOv8: A novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS). pp. 1\u20136. IEEE (2024). https:\/\/doi.org\/10.1109\/ADICS58448.2024.10533619","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"3831_CR29","doi-asserted-by":"publisher","unstructured":"Wang, C.-Y., Yeh, I.-H., Liao, H.-Y.M.: YOLOv9: Learning what you want to learn using programmable gradient information, http:\/\/arxiv.org\/abs\/2402.13616, (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.13616","DOI":"10.48550\/arXiv.2402.13616"},{"key":"3831_CR30","doi-asserted-by":"publisher","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: YOLOv10: Real-Time End-to-End Object Detection, http:\/\/arxiv.org\/abs\/2405.14458, (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.14458","DOI":"10.48550\/arXiv.2405.14458"},{"key":"3831_CR31","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.48550\/arXiv.2201.03545","DOI":"10.48550\/arXiv.2201.03545"},{"key":"3831_CR32","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.48550\/arXiv.2209.08575","volume":"35","author":"M-H Guo","year":"2022","unstructured":"Guo, M.-H., Lu, C.-Z., Hou, Q., Liu, Z., Cheng, M.-M., Hu, S.-M.: Segnext: rethinking convolutional attention design for semantic segmentation. Adv. Neural Inf. Process. Syst. 35, 1140\u20131156 (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.08575","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3831_CR33","doi-asserted-by":"publisher","unstructured":"Li, Y., Hou, Q., Zheng, Z., Cheng, M.-M., Yang, J., Li, X.: Large selective kernel network for remote sensing object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16794\u201316805 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.09030","DOI":"10.48550\/arXiv.2303.09030"},{"key":"3831_CR34","doi-asserted-by":"publisher","unstructured":"Lin, W., Wu, Z., Chen, J., Huang, J., Jin, L.: Scale-aware modulation meet transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 6015\u20136026 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.09030","DOI":"10.48550\/arXiv.2303.09030"},{"key":"3831_CR35","doi-asserted-by":"publisher","unstructured":"Wasim, S.T., Khattak, M.U., Naseer, M., Khan, S., Shah, M., Khan, F.S.: Video-focalnets: Spatio-temporal focal modulation for video action recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 13778\u201313789 (2023). https:\/\/doi.org\/10.48550\/arXiv.2307.06947","DOI":"10.48550\/arXiv.2307.06947"},{"key":"3831_CR36","doi-asserted-by":"publisher","unstructured":"Li, S., Wang, Z., Liu, Z., Tan, C., Lin, H., Wu, D., Chen, Z., Zheng, J., Li, S.Z.: Efficient multi-order gated aggregation network. arXiv preprint arXiv:2211.03295. (2022). https:\/\/doi.org\/10.48550\/arXiv.2211.03295","DOI":"10.48550\/arXiv.2211.03295"},{"key":"3831_CR37","doi-asserted-by":"publisher","unstructured":"Yun, G., Yoo, J., Kim, K., Lee, J., Kim, D.H.: Spanet: frequency-balancing token mixer using spectral pooling aggregation modulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 6113\u20136124 (2023). https:\/\/doi.org\/10.48550\/arXiv.2308.11568","DOI":"10.48550\/arXiv.2308.11568"},{"key":"3831_CR38","doi-asserted-by":"publisher","first-page":"4203","DOI":"10.48550\/arXiv.2203.11926","volume":"35","author":"J Yang","year":"2022","unstructured":"Yang, J., Li, C., Dai, X., Gao, J.: Focal modulation networks. Adv. Neural Inf. Process. Syst. 35, 4203\u20134217 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.11926","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3831_CR39","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/s41095-023-0364-2","volume":"9","author":"M-H Guo","year":"2023","unstructured":"Guo, M.-H., Lu, C.-Z., Liu, Z.-N., Cheng, M.-M., Hu, S.-M.: Visual attention network. Comput. Visual Media 9, 733\u2013752 (2023). https:\/\/doi.org\/10.1007\/s41095-023-0364-2","journal-title":"Comput. Visual Media"},{"key":"3831_CR40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450","author":"Q Hou","year":"2024","unstructured":"Hou, Q., Lu, C.-Z., Cheng, M.-M., Feng, J.: Conv2former: a simple transformer-style convnet for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3401450","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3831_CR41","doi-asserted-by":"publisher","first-page":"10353","DOI":"10.48550\/arXiv.2207.14284","volume":"35","author":"Y Rao","year":"2022","unstructured":"Rao, Y., Zhao, W., Tang, Y., Zhou, J., Lim, S.N., Lu, J.: Hornet: efficient high-order spatial interactions with recursive gated convolutions. Adv. Neural Inf. Process. Syst. 35, 10353\u201310366 (2022). https:\/\/doi.org\/10.48550\/arXiv.2207.14284","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3831_CR42","doi-asserted-by":"publisher","unstructured":"Li, S., Wang, Z., Liu, Z., Tan, C., Lin, H., Wu, D., Chen, Z., Zheng, J., Li, S.Z.: Moganet: multi-order gated aggregation network. In: The Twelfth International Conference on Learning Representations (2023). https:\/\/doi.org\/10.48550\/arXiv.2211.03295","DOI":"10.48550\/arXiv.2211.03295"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03831-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03831-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03831-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T14:54:00Z","timestamp":1739458440000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03831-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,28]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["3831"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03831-3","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,1,28]]},"assertion":[{"value":"28 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2025","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"250"}}