{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T13:52:18Z","timestamp":1776865938987,"version":"3.51.2"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Vietnam National University Ho Chi Minh City","award":["NCM2021-20-02"],"award-info":[{"award-number":["NCM2021-20-02"]}]},{"name":"Vietnam National University Ho Chi Minh City","award":["NCM2021-20-02"],"award-info":[{"award-number":["NCM2021-20-02"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s10586-025-05848-2","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T16:00:56Z","timestamp":1763568056000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A contrast-aware and uncertainty-optimized transformer model for small object detection in high-resolution images"],"prefix":"10.1007","volume":"29","author":[{"given":"Nguyen","family":"Hoanh","sequence":"first","affiliation":[]},{"given":"Tran Vu","family":"Pham","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"issue":"7","key":"5848_CR1","doi-asserted-by":"publisher","first-page":"9663","DOI":"10.1007\/s10586-024-04474-8","volume":"27","author":"C Dong","year":"2024","unstructured":"Dong, C., Tang, Y., Zhu, H., Zhang, L.: HCA-YOLO: A non-salient object detection method based on hierarchical attention mechanism. Cluster Comput. 27(7), 9663\u20139678 (2024)","journal-title":"Cluster Comput."},{"issue":"1","key":"5848_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10586-024-04829-1","volume":"28","author":"L Zhou","year":"2025","unstructured":"Zhou, L., Dong, Y., Ma, B., Yin, Z., Lu, F.: Object detection in low-light conditions based on DBS-YOLOv8. Cluster Comput. 28(1), 1\u201320 (2025)","journal-title":"Cluster Comput."},{"key":"5848_CR3","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 2965\u20132974. (2019)","DOI":"10.1109\/CVPR.2019.00308"},{"key":"5848_CR4","doi-asserted-by":"crossref","unstructured":"Guo, C., Zhang, B.F.Q., Xiang, S.: and Chunhong Pan. Augfpn: Improving multi-scale feature learning for object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 12595\u201312604. (2020)","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"5848_CR5","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R.: and Quoc V. Le. 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":"5848_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112078","author":"Junjie Ke","year":"2024","unstructured":"Ke, Junjie, He, Lihuo, Han, Bo., Li, Jie, Gao, Xinbo: ProFPN: Progressive feature pyramid network with soft proposal assignment for object detection. Knowledge-Based Systems (2024). https:\/\/doi.org\/10.1016\/j.knosys.2024.112078","journal-title":"Knowledge-Based Systems"},{"key":"5848_CR7","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1016\/j.neucom.2020.06.128","volume":"453","author":"Feng Chen","year":"2021","unstructured":"Chen, Feng, Wu, Fei, Xu, Jing, Gao, Guangwei, Ge, Qi., Jing, Xiao-Yuan.: Adaptive deformable convolutional network. Neurocomputing 453, 853\u2013864 (2021)","journal-title":"Neurocomputing"},{"key":"5848_CR8","doi-asserted-by":"crossref","unstructured":"Najibi, M., Singh, B., Larry, S., Davis: Autofocus: Efficient multi-scale inference. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 9745\u20139755. (2019)","DOI":"10.1109\/ICCV.2019.00984"},{"key":"5848_CR9","doi-asserted-by":"crossref","unstructured":"Du, B., Huang, Y., Chen, J., Huang, D.: Adaptive sparse convolutional networks with global context enhancement for faster object detection on drone images. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13435\u201313444. (2023)","DOI":"10.1109\/CVPR52729.2023.01291"},{"key":"5848_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111939","volume":"296","author":"Nguyen Hoanh","year":"2024","unstructured":"Hoanh, Nguyen, Pham, Tran Vu: Focus-Attention Approach in Optimizing DETR for Object Detection from High-Resolution Images. Knowledge-Based Systems 296, 111939 (2024)","journal-title":"Knowledge-Based Systems"},{"key":"5848_CR11","doi-asserted-by":"crossref","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)","DOI":"10.1109\/CVPR52733.2024.01605"},{"issue":"6","key":"5848_CR12","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R.: Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5848_CR13","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5848_CR14","doi-asserted-by":"crossref","unstructured":"Cai, Z.: and Nuno Vasconcelos. 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":"5848_CR15","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Yuan, L., Liu, Z., Wang, L., Li, H., and Yun Fu:. Rethinking classificationlocalization for object detection. In Proceedings of the IEEE\/CVF conference on computer visionpattern recognition, pp. 10186\u201310195. (2020)","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"5848_CR16","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":"5848_CR17","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":"5848_CR18","doi-asserted-by":"publisher","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., et al.: YOLOv6: A single-stage object detection framework for industrial applications. ArXiv Preprint arXiv:220902976 (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.02976","DOI":"10.48550\/arXiv.2209.02976"},{"key":"5848_CR19","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Alexander, C., Berg: 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 International Publishing, (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"5848_CR20","doi-asserted-by":"crossref","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. Cham: Springer International Publishing, (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"5848_CR21","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"5848_CR22","doi-asserted-by":"crossref","unstructured":"Wang, T., Yuan, L., Chen, Y., Feng, J.: and Shuicheng Yan. Pnp-detr: Towards efficient visual analysis with transformers. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 4661\u20134670. (2021)","DOI":"10.1109\/ICCV48922.2021.00462"},{"key":"5848_CR23","unstructured":"Roh, B., Shin, J.W., Shin, W., Kim, S.: Sparse detr: Efficient end-to-end object detection with learnable sparsity. arXiv preprint arXiv:2111.14330 (2021)"},{"key":"5848_CR24","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J.: Lionel M. Ni, and Heung-Yeung Shum. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"5848_CR25","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., Wang, J.: Conditional detr for fast training convergence. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 3651\u20133660. (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"5848_CR26","doi-asserted-by":"crossref","unstructured":"Sun, Z., Cao, S., Yang, Y., Kris, M.: Kitani. 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":"5848_CR27","doi-asserted-by":"crossref","unstructured":"Gao, P., Zheng, M., Wang, X., Dai, J., Li, H.: Fast convergence of detr with spatially modulated co-attention. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 3621\u20133630. (2021)","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"5848_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor detr: Query design for transformer-based detector. In Proceedings of the AAAI conference on artificial intelligence, vol. 36, no. 3, pp. 2567\u20132575. (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"5848_CR29","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M.: and Lei Zhang. Dn-detr: Accelerate detr training by introducing query denoising. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13619\u201313627. (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"5848_CR30","doi-asserted-by":"crossref","unstructured":"Jia, D., Yuan, Y., He, H., Wu, X., Yu, H., Lin, W., Sun, L., Zhang, C., Han, H.: Detrs with hybrid matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 19702\u201319712. (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"5848_CR31","doi-asserted-by":"crossref","unstructured":"He, L.: and Sinisa Todorovic. Destr: Object detection with split transformer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9377\u20139386. (2022)","DOI":"10.1109\/CVPR52688.2022.00916"},{"key":"5848_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Serge Belongie:. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer visionpattern recognition, pp. 2117\u20132125. (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"5848_CR33","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"},{"issue":"12","key":"5848_CR34","doi-asserted-by":"publisher","first-page":"9904","DOI":"10.1109\/TPAMI.2021.3132068","volume":"44","author":"Zechao Li","year":"2021","unstructured":"Li, Zechao, Sun, Yanpeng, Zhang, Liyan, Tang, Jinhui: CTNet: Context-based tandem network for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 44(12), 9904\u20139917 (2021)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"5848_CR35","doi-asserted-by":"crossref","unstructured":"Yang, C., Huang, Z., Wang, N.: QueryDet: Cascaded sparse query for accelerating high-resolution small object detection. In Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp. 13668\u201313677. (2022)","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"5848_CR36","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhang, Y., Ding, M., Ghanem, B.: Finding tiny faces in the wild with generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 21\u201330. (2018)","DOI":"10.1109\/CVPR.2018.00010"},{"key":"5848_CR37","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhang, Y., Ding, M.: and Bernard Ghanem. Sod-mtgan: Small object detection via multi-task generative adversarial network. In Proceedings of the European conference on computer vision (ECCV), pp. 206\u2013221. (2018)","DOI":"10.1007\/978-3-030-01261-8_13"},{"key":"5848_CR38","doi-asserted-by":"crossref","unstructured":"Li, J., Liang, X., Wei, Y., Xu, T., Feng, J.: and Shuicheng Yan. Perceptual generative adversarial networks for small object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1222\u20131230. (2017)","DOI":"10.1109\/CVPR.2017.211"},{"key":"5848_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Stan, Z., Li: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9759\u20139768. (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"5848_CR40","unstructured":"Liu, J., Chen, J.: A coarse to fine framework for object detection in high resolution image. ArXiv Preprint arXiv:230301219 (2023)"},{"key":"5848_CR41","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":"5848_CR42","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y.: and In So Kweon. 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"},{"issue":"11","key":"5848_CR43","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"Pengfei Zhu","year":"2021","unstructured":"Zhu, Pengfei, Wen, Longyin, Du, Dawei, Bian, Xiao, Fan, Heng, Hu, Qinghua, Ling, Haibin: Detection and tracking meet drones challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence 44(11), 7380\u20137399 (2021)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"5848_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Lawrence Zitnick, C.: Microsoft coco: Common objects in context. In Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer International Publishing, (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5848_CR45","doi-asserted-by":"crossref","unstructured":"Li, C., Yang, T., Zhu, S., Chen, C.: and Shanyue Guan. Density map guided object detection in aerial images. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp. 190\u2013191. (2020)","DOI":"10.1109\/CVPRW50498.2020.00103"},{"key":"5848_CR46","doi-asserted-by":"crossref","unstructured":"Meethal, A., Eric Granger, and, Pedersoli, M.: Cascaded zoom-in detector for high resolution aerial images. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2046\u20132055. (2023)","DOI":"10.1109\/CVPRW59228.2023.00198"},{"key":"5848_CR47","unstructured":"YOLOv8. [Online]. (2023). Available: https:\/\/github.com\/triple-Mu\/YOLOv8"},{"key":"5848_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Chien-Yao, I.-H., Yeh, Liao, H.-Y.M.: Yolov9: Learning what you want to learn using programmable gradient information. In European conference on computer vision, pp. 1\u201321. Cham: Springer Nature Switzerland, (2024)","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"5848_CR49","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: YOLOv10: Real-Time End-to-End object detection. arXiv 2024. arXiv preprint arXiv:2405.14458 (2024)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05848-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-025-05848-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05848-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T13:09:09Z","timestamp":1773925749000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-025-05848-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["5848"],"URL":"https:\/\/doi.org\/10.1007\/s10586-025-05848-2","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,19]]},"assertion":[{"value":"17 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 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 have no conflicts of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}}],"article-number":"43"}}