{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:11:56Z","timestamp":1773155516431,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"7","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":["62172212"],"award-info":[{"award-number":["62172212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62172212"],"award-info":[{"award-number":["62172212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62172212"],"award-info":[{"award-number":["62172212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62172212"],"award-info":[{"award-number":["62172212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s10586-024-04474-8","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T03:37:06Z","timestamp":1714016226000},"page":"9663-9678","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["HCA-YOLO: a non-salient object detection method based on hierarchical attention mechanism"],"prefix":"10.1007","volume":"27","author":[{"given":"Chengang","family":"Dong","sequence":"first","affiliation":[]},{"given":"Yuhao","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Hanyue","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Liyan","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"4474_CR1","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., Kitani, K.M.: Rethinking transformer-based set prediction for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3611\u20133620 (2021)","DOI":"10.1109\/ICCV48922.2021.00359"},{"key":"4474_CR2","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1007\/s11554-022-01241-z","volume":"19","author":"H Wang","year":"2022","unstructured":"Wang, H., Jin, Y., Ke, H., Zhang, X.: DDH-YOLOv5: improved YOLOv5 based on Double IoU-aware decoupled head for object detection. J. Real-Time Image Proc. 19, 1023\u20131033 (2022)","journal-title":"J. Real-Time Image Proc."},{"key":"4474_CR3","doi-asserted-by":"crossref","unstructured":"Duan, K., Xie, L., Qi, H., Bai, S., Huang, Q., Tian, Q.: Corner proposal network for anchor-free, two-stage object detection. In: European Conference on Computer Vision, pp. 399\u2013416. Springer (2020)","DOI":"10.1007\/978-3-030-58580-8_24"},{"key":"4474_CR4","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and 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":"4474_CR5","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv:2107.08430 (2021)"},{"key":"4474_CR6","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L.: Swin transformer v2: scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"4474_CR7","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":"4474_CR8","unstructured":"Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., Wang, G., Dang, Q., Wei, S., Du, Y.: PP-YOLOE: An evolved version of YOLO. arXiv:2203.16250 (2022)"},{"key":"4474_CR9","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv: 2004.10934 (2020)"},{"key":"4474_CR10","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv: 1804.02767 (2018)"},{"key":"4474_CR11","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":"4474_CR12","doi-asserted-by":"publisher","first-page":"20939","DOI":"10.1007\/s00521-023-08809-1","volume":"35","author":"FM Talaat","year":"2023","unstructured":"Talaat, F.M., ZainEldin, H.: An improved fire detection approach based on YOLO-v8 for smart cities. Neural Comput. Appl.Comput. Appl. 35, 20939\u201320954 (2023)","journal-title":"Neural Comput. Appl.Comput. Appl."},{"key":"4474_CR13","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4474_CR14","doi-asserted-by":"crossref","unstructured":"Lu, C., Xia, Z., Przystupa, K., Kochan, O., Su, J.: DCELANM-Net: medical image segmentation based on dual channel efficient layer aggregation network with learner. arXiv: 2304.09620 (2023)","DOI":"10.1002\/ima.22960"},{"key":"4474_CR15","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 (ICCV), pp. 3490\u20133499. IEEE (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"4474_CR16","doi-asserted-by":"crossref","unstructured":"Chowdhury, P. N., Sain, A., Bhunia, A.K., Xiang, T., Gryaditskaya, Y., Song, Y.-Z.: Fs-coco: towards understanding of freehand sketches of common objects in context. In: European Conference on Computer Vision, pp. 253\u2013270. Springer (2022)","DOI":"10.1007\/978-3-031-20074-8_15"},{"key":"4474_CR17","unstructured":"Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., Sun, J.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv:1805.00123 (2018)"},{"key":"4474_CR18","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":"4474_CR19","doi-asserted-by":"crossref","unstructured":"Lu, X., Li, B., Yue, Y., Li, Q., Yan, J.: Grid r-cnn. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7363\u20137372 (2019)","DOI":"10.1109\/CVPR.2019.00754"},{"key":"4474_CR20","unstructured":"Liang, T., Chu, X., Liu, Y., Wang, Y., Tang, Z., Chu, W., Chen, J., Ling, H.: Cbnetv2: a composite backbone network architecture for object detection. arXiv: 2107.00420 (2021)"},{"key":"4474_CR21","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"4474_CR22","first-page":"1","volume":"70","author":"X Cheng","year":"2020","unstructured":"Cheng, X., Yu, J.: RetinaNet with difference channel attention and adaptively spatial feature fusion for steel surface defect detection. IEEE Trans. Instrum. Meas.Instrum. Meas. 70, 1\u201311 (2020)","journal-title":"IEEE Trans. Instrum. Meas.Instrum. Meas."},{"key":"4474_CR23","unstructured":"Wang, C.-Y., Yeh, I.-H., Liao, H.-Y. M.: You only learn one representation: unified network for multiple tasks. arXiv:2105.04206 (2021)"},{"key":"4474_CR24","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":"4474_CR25","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":"4474_CR26","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":"4474_CR27","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"},{"key":"4474_CR28","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":"4474_CR29","doi-asserted-by":"crossref","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 (2022). Springer","DOI":"10.1007\/978-3-031-26409-2_27"},{"key":"4474_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":"4474_CR31","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":"4474_CR32","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:1704.04861 (2017)"},{"key":"4474_CR33","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.neucom.2022.05.052","volume":"500","author":"Y Shen","year":"2022","unstructured":"Shen, Y., Zhang, F., Liu, D., Pu, W., Zhang, Q.: Manhattan-distance IOU loss for fast and accurate bounding box regression and object detection. Neurocomputing 500, 99\u2013114 (2022)","journal-title":"Neurocomputing"},{"key":"4474_CR34","unstructured":"Tong, Z., Chen, Y., Xu, Z., Yu, R.: Wise-IoU: bounding box regression loss with dynamic focusing mechanism. arXiv:2301.10051 (2023)"},{"key":"4474_CR35","doi-asserted-by":"publisher","first-page":"58774","DOI":"10.1109\/ACCESS.2018.2872698","volume":"6","author":"D Liang","year":"2018","unstructured":"Liang, D., Yang, F., Zhang, T., Yang, P.: Understanding mixup training methods. IEEE Access 6, 58774\u201358783 (2018)","journal-title":"IEEE Access"},{"key":"4474_CR36","doi-asserted-by":"crossref","unstructured":"Li, Q., Li, D., Zhao, K., Wang, L., Wang, K.: State of health estimation of lithium-ion battery based on improved ant lion optimization and support vector regression. J. Energy Storage 50, 104215 (2022)","DOI":"10.1016\/j.est.2022.104215"},{"key":"4474_CR37","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv:2209.02976 (2022)"},{"key":"4474_CR38","unstructured":"Lv, W., Xu, S., Zhao, Y., Wang, G., Wei, J., Cui, C., Du, Y., Dang, Q., Liu, Y.: Detrs beat yolos on real-time object detection. arXiv:2304.08069 (2023)"},{"issue":"6","key":"4474_CR39","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.Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell.Intell."},{"key":"4474_CR40","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"4474_CR41","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv:2010.04159 (2020)"},{"key":"4474_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Song, L., Li, Z., Sun, H., Sun, J., Zheng, N.: End-to-End Object Detection with Fully Convolutional Network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15849\u201315858 (2021)","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"4474_CR43","doi-asserted-by":"crossref","unstructured":"Gong, Y., Yu, X., Ding, Y., Peng, X., Zhao, J., Han, Z.: Effective fusion factor in FPN for tiny object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1160\u20131168 (2021)","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"4474_CR44","unstructured":"Gevorgyan, Z.: SIoU loss: More powerful learning for bounding box regression. arXiv:2205.12740 (2022)"},{"key":"4474_CR45","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"4474_CR46","doi-asserted-by":"crossref","unstructured":"He, C., Saha, P.: Investigating YOLO models towards outdoor obstacle detection for visually impaired people. arXiv:2312.07571 (2023)","DOI":"10.21203\/rs.3.rs-3733857\/v1"},{"key":"4474_CR47","unstructured":"Zhang, X., Song, Y., Song, T., Yang, D., Ye, Y., Zhou, J., Zhang, L.: AKConv: Convolutional Kernel with arbitrary sampled shapes and arbitrary number of parameters. arXiv:2311.11587 (2023)"},{"key":"4474_CR48","doi-asserted-by":"crossref","unstructured":"Ye, H., Zhang, B., Chen, T., Fan, J., Wang, B.: Performance-aware approximation of global channel pruning for multitask CNNs. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3260903"},{"key":"4474_CR49","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, pp. 5270\u20135279 (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"4474_CR50","doi-asserted-by":"crossref","unstructured":"Yi, H., Liu, B., Zhao, B., Liu, E.: Small object detection algorithm based on improved YOLOv8 for remote sensing. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. (2023)","DOI":"10.1109\/JSTARS.2023.3339235"},{"key":"4474_CR51","doi-asserted-by":"publisher","first-page":"7190","DOI":"10.3390\/s23167190","volume":"23","author":"G Wang","year":"2023","unstructured":"Wang, G., Chen, Y., An, P., Hong, H., Hu, J., Huang, T.: UAV-YOLOv8: a small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios. Sensors 23, 7190 (2023)","journal-title":"Sensors"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-024-04474-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-024-04474-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-024-04474-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T19:26:18Z","timestamp":1725909978000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-024-04474-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,25]]},"references-count":51,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["4474"],"URL":"https:\/\/doi.org\/10.1007\/s10586-024-04474-8","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,25]]},"assertion":[{"value":"19 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 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":"We have conducted a thorough assessment of both financial and non-financial affiliations that could potentially create a conflict of interest with the research presented. We unequivocally declare that no competing interests have been identified that could in any way introduce bias or influence the outcomes of our study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}