{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:33:26Z","timestamp":1772120006753,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"S1","license":[{"start":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T00:00:00Z","timestamp":1714003200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T00:00:00Z","timestamp":1714003200000},"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":"crossref","award":["No. 52205088"],"award-info":[{"award-number":["No. 52205088"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100005230","name":"Chongqing Natural Science Foundation","doi-asserted-by":"crossref","award":["No. CSTB2022NSCQ-MSX0933"],"award-info":[{"award-number":["No. CSTB2022NSCQ-MSX0933"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Foundation of Chongqing Education Commission","award":["No. KJQN202201144"],"award-info":[{"award-number":["No. KJQN202201144"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11760-024-03193-2","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T09:02:36Z","timestamp":1714035756000},"page":"789-798","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving real-time small objects detection by fusion features of spatial coordinates"],"prefix":"10.1007","volume":"18","author":[{"given":"Qianjiang","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongyuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunze","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"3193_CR1","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik. J.: Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 580\u2013587. (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"3193_CR2","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast r-cnn. IEEE Int. Conf. Comput. Vis. (ICCV), pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"3193_CR3","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. Intel. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans Pattern Anal Mach. Intel."},{"key":"3193_CR4","doi-asserted-by":"publisher","unstructured":"Neubeck, A., Van Gool, L.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition. (ICPR'06), pp. 850\u2013855 (2006). https:\/\/doi.org\/10.1109\/ICPR.2006.479","DOI":"10.1109\/ICPR.2006.479"},{"key":"3193_CR5","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. IEEE Conf. Comput. Vis. Pattern Recog. (CVPR), pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2.16.91.","DOI":"10.1109\/CVPR.2.16.91"},{"key":"3193_CR6","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. IEEE Conf. Comput. Vis. Pattern Recogn. (CVPR), pp. 6517\u20136525 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.690.","DOI":"10.1109\/CVPR.2017.690"},{"key":"3193_CR7","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv:1804.02767. submitted: (2018)"},{"key":"3193_CR8","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H-Y. M.: Yolov4: Optimal speed and accuracy of object detection. IEEE Conf. Comput. Vis. Pattern Recog. (CVPR) (2020). https:\/\/arxiv.org\/abs\/2004.10934"},{"key":"3193_CR9","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. Eur. Conf. Comput. Vis. (ECCV), pp. 21\u201337 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3193_CR10","unstructured":"Fu, C.Y., Liu, W., Ranga, A., Tyagi, A. Berg, A.C.: (Preprint) arXiv:1701.06659. submitted: (2017)"},{"key":"3193_CR11","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Houlsby, N. (Preprint) arXiv:2010.11929. submitted: (2020)"},{"key":"3193_CR12","unstructured":"Krizhevsky, A., Hinton, G.E.: Learning multiple layers of features from tiny images, 7 (2009)"},{"issue":"6","key":"3193_CR13","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017)","journal-title":"Commun. ACM"},{"key":"3193_CR14","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","volume":"2009","author":"J Deng","year":"2009","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Li, F.: Imagenet: a large-scale hierarchical image database. IEEE Conf. Comput. Vis. Pattern Recogn.tion 2009, 248\u2013255 (2009). https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","journal-title":"IEEE Conf. Comput. Vis. Pattern Recogn.tion"},{"key":"3193_CR15","unstructured":"Graham, B.: (Preprint) arXiv:1412.6071. submitted (2014)"},{"key":"3193_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., Doll\u00e1r, v: Microsoft coco: common ob jects in context. In: European Conference on Computer Vision. Springer, Cham, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3193_CR17","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H-Y.M.: (Preprint) arXiv:2004.10934. submitted (2020)"},{"key":"3193_CR18","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":"3193_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3193_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan. S.: Perceptual generative adversarial networks for small object detectionIn: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1222\u20131230 (2017)","DOI":"10.1109\/CVPR.2017.211"},{"key":"3193_CR21","doi-asserted-by":"crossref","unstructured":"Bell, S., Zitnick, C.L., Bala, K., Girshick. R.: Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2874\u20132883 (2016)","DOI":"10.1109\/CVPR.2016.314"},{"key":"3193_CR22","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"3193_CR23","doi-asserted-by":"crossref","unstructured":"Kisantal, M., Wojna, Z., Murawski, J., et al. Augmentation for small object detection. arXiv preprint arXiv:1902.07296 (2019)","DOI":"10.5121\/csit.2019.91713"},{"key":"3193_CR24","unstructured":"Liu R, Lehman J, Molino P, Such F.P., Frank, E., Sergeev, A., Yosinski, J.: Advances in Neural Information Processing Systems, 31 (2018)"},{"key":"3193_CR25","doi-asserted-by":"publisher","unstructured":"Li, H., Li, J., Wei, H. et al. Slim-neck by GSConv: a lightweight-design for real-time detector architectures. J Real-Time Image Proc 21, 62 (2024). https:\/\/doi.org\/10.1007\/s11554-024-01436-6","DOI":"10.1007\/s11554-024-01436-6"},{"key":"3193_CR26","doi-asserted-by":"crossref","unstructured":"Wang, C., Mark Liao, H., Wu, Y., Chen, P., Hsieh, J., Yeh, I.: CSPNet: a new backbone that can enhance learning capability of CNN. IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"issue":"9","key":"3193_CR27","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":"3193_CR28","unstructured":". He, J, Shen, L., Sun, G.: Squeeze-and-excitation networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7132\u20137141 (2018)"},{"key":"3193_CR29","doi-asserted-by":"publisher","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13708\u201313717 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01350.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"3193_CR30","doi-asserted-by":"publisher","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z.: Huang, T.: Association for Computing Machinery, pp. 516\u2013520 (2016). https:\/\/doi.org\/10.1145\/2964284.2967274.","DOI":"10.1145\/2964284.2967274"},{"key":"3193_CR31","doi-asserted-by":"publisher","unstructured":"Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., Zuo, W.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybernet. pp. 1\u201313 (2021). https:\/\/doi.org\/10.1109\/TCYB.2021.3095305.","DOI":"10.1109\/TCYB.2021.3095305"},{"key":"3193_CR32","unstructured":"Zhang, Y., Ren, W., Zhang, Z., Jia, Z., Wang, L., Tan, T.: (Preprint) arXiv:2101.08158. submitted (2021)"},{"key":"3193_CR33","unstructured":"Du, D., Zhu, P., Wen, L. et al. VisDrone-DET2019: The vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)"},{"key":"3193_CR34","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Yuan, L., et al. Rethinking classification and localization for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10186\u201310195 (2020)","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"3193_CR35","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., Wang, W., Wu, L., et al.: 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."},{"key":"3193_CR36","unstructured":"Lv, W., Xu, S., Zhao, Y. et al.: Detrs beat yolos on real-time object detection. arXiv preprint arXiv:2304.08069, 2023."},{"key":"3193_CR37","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":"3193_CR38","unstructured":"Glenn, J.: YOLOv5 release v6.1. https:\/\/github.com\/-ultralytics\/yolov5\/releases\/tag\/v6.1, (2022)"},{"key":"3193_CR39","unstructured":"Li, C., Li, L., Jiang, H., et al.: YOLOv6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976, 2022."},{"key":"3193_CR40","unstructured":"Glenn, J: ultralytics. https:\/\/github.com\/ultralytics\/-ultralytics\/releases\/tag\/v8.1.0 (2023)"},{"key":"3193_CR41","unstructured":"Ge, Z., Liu, S., Wang, F., et al.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03193-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03193-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03193-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T08:29:26Z","timestamp":1719304166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03193-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,25]]},"references-count":41,"journal-issue":{"issue":"S1","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["3193"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03193-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2717722\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,25]]},"assertion":[{"value":"12 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}