{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:11:59Z","timestamp":1782483119122,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3728424.3760769","type":"proceedings-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:17:42Z","timestamp":1761059862000},"page":"36-44","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["An Uncertainty-aware DETR Enhancement Framework for Object Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8200-4909","authenticated-orcid":false,"given":"Xingshu","family":"Chen","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7935-9424","authenticated-orcid":false,"given":"Sicheng","family":"Yu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9903-3719","authenticated-orcid":false,"given":"Chong","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3086-3128","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7148-5629","authenticated-orcid":false,"given":"Ting","family":"Tian","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Align-detr: Improving detr with simple iou-aware bce loss. arXiv preprint arXiv:2304.07527","author":"Cai Zhi","year":"2023","unstructured":"Zhi Cai, Songtao Liu, Guodong Wang, Zheng Ge, Xiangyu Zhang, and Di Huang. 2023. Align-detr: Improving detr with simple iou-aware bce loss. arXiv preprint arXiv:2304.07527 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Yifei Chen Chenyan Zhang Ben Chen Yiyu Huang Yifei Sun Changmiao Wang Xianjun Fu Yuxing Dai Feiwei Qin Yong Peng et al. 2024. Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases. Computers in biology and medicine Vol. 170 (2024) 107917.","DOI":"10.1016\/j.compbiomed.2024.107917"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00059"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1017\/jpr.2022.16","article-title":"Gromov-Wasserstein distances between Gaussian distributions","volume":"59","author":"Delon Julie","year":"2022","unstructured":"Julie Delon, Agnes Desolneux, and Antoine Salmona. 2022. Gromov-Wasserstein distances between Gaussian distributions. Journal of Applied Probability, Vol. 59, 4 (2022), 1178-1198.","journal-title":"Journal of Applied Probability"},{"key":"e_1_3_2_1_7_1","volume-title":"SIoU loss: More powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740","author":"Gevorgyan Zhora","year":"2022","unstructured":"Zhora Gevorgyan. 2022. SIoU loss: More powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740 (2022)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","first-page":"67987","DOI":"10.1109\/ACCESS.2023.3290905","article-title":"Blood cell detection method based on improved YOLOv5","volume":"11","author":"Guo Yecai","year":"2023","unstructured":"Yecai Guo and Mengyao Zhang. 2023. Blood cell detection method based on improved YOLOv5. IEEE Access, Vol. 11 (2023), 67987-67995.","journal-title":"IEEE Access"},{"key":"e_1_3_2_1_9_1","volume-title":"2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 87-93","author":"Harakeh Ali","year":"2020","unstructured":"Ali Harakeh, Michael Smart, and Steven L Waslander. 2020. Bayesod: A bayesian approach for uncertainty estimation in deep object detectors. In 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 87-93."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00300"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00300"},{"key":"e_1_3_2_1_13_1","volume-title":"European Conference on Computer Vision. Springer, 89-105","author":"Hou Xiuquan","year":"2025","unstructured":"Xiuquan Hou, Meiqin Liu, Senlin Zhang, Ping Wei, Badong Chen, and Xuguang Lan. 2025. Relation detr: Exploring explicit position relation prior for object detection. In European Conference on Computer Vision. Springer, 89-105."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 19702-19712","author":"Jia Ding","year":"2023","unstructured":"Ding Jia, Yuhui Yuan, Haodi He, Xiaopei Wu, Haojun Yu, Weihong Lin, Lei Sun, Chao Zhang, and Han Hu. 2023. Detrs with hybrid matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 19702-19712."},{"key":"e_1_3_2_1_15_1","volume-title":"Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_16_1","volume-title":"European Conference on Computer Vision. Springer, 27-42","author":"Lee Youngwan","year":"2022","unstructured":"Youngwan Lee, Joong-won Hwang, Hyung-Il Kim, Kimin Yun, Yongjin Kwon, Yuseok Bae, and Sung Ju Hwang. 2022. Localization uncertainty estimation for anchor-free object detection. In European Conference on Computer Vision. Springer, 27-42."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_1_19_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Pu Yifan","year":"2024","unstructured":"Yifan Pu, Weicong Liang, Yiduo Hao, Yuhui Yuan, Yukang Yang, Chao Zhang, Han Hu, and Gao Huang. 2024. Rank-DETR for high quality object detection. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13188-13197","author":"Qiu Heqian","year":"2020","unstructured":"Heqian Qiu, Hongliang Li, Qingbo Wu, and Hengcan Shi. 2020. Offset bin classification network for accurate object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13188-13197."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_26_1","volume-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Ren Shaoqing","year":"2016","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2016. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 6 (2016), 1137-1149."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.compmedimag.2011.01.003","article-title":"Automatic recognition of five types of white blood cells in peripheral blood","volume":"35","author":"Rezatofighi Seyed Hamid","year":"2011","unstructured":"Seyed Hamid Rezatofighi and Hamid Soltanian-Zadeh. 2011. Automatic recognition of five types of white blood cells in peripheral blood. Computerized Medical Imaging and Graphics, Vol. 35, 4 (2011), 333-343.","journal-title":"Computerized Medical Imaging and Graphics"},{"key":"e_1_3_2_1_29_1","volume-title":"FCOS: A simple and strong anchor-free object detector","author":"Tian Zhi","year":"2020","unstructured":"Zhi Tian, Chunhua Shen, Hao Chen, and Tong He. 2020. FCOS: A simple and strong anchor-free object detector. IEEE transactions on pattern analysis and machine intelligence, Vol. 44, 4 (2020), 1922-1933."},{"key":"e_1_3_2_1_30_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_31_1","volume-title":"Yolov10: Real-time end-to-end object detection. arXiv preprint arXiv:2405.14458","author":"Wang Ao","year":"2024","unstructured":"Ao Wang, Hui Chen, Lihao Liu, Kai Chen, Zijia Lin, Jungong Han, and Guiguang Ding. 2024a. Yolov10: Real-time end-to-end object detection. arXiv preprint arXiv:2405.14458 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Chengcheng","year":"2024","unstructured":"Chengcheng Wang, Wei He, Ying Nie, Jianyuan Guo, Chuanjian Liu, Yunhe Wang, and Kai Han. 2024b. Gold-YOLO: Efficient object detector via gather-and-distribute mechanism. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"e_1_3_2_1_34_1","volume-title":"European conference on computer vision. Springer, 1-21","author":"Wang Chien-Yao","year":"2025","unstructured":"Chien-Yao Wang, I-Hau Yeh, and Hong-Yuan Mark Liao. 2025. Yolov9: Learning what you want to learn using programmable gradient information. In European conference on computer vision. Springer, 1-21."},{"key":"e_1_3_2_1_35_1","volume-title":"A normalized Gaussian Wasserstein distance for tiny object detection. arXiv preprint arXiv:2110.13389","author":"Wang Jinwang","year":"2021","unstructured":"Jinwang Wang, Chang Xu, Wen Yang, and Lei Yu. 2021. A normalized Gaussian Wasserstein distance for tiny object detection. arXiv preprint arXiv:2110.13389 (2021)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103416"},{"key":"e_1_3_2_1_37_1","volume-title":"International conference on machine learning. PMLR, 11830-11841","author":"Yang Xue","year":"2021","unstructured":"Xue Yang, Junchi Yan, Qi Ming, Wentao Wang, Xiaopeng Zhang, and Qi Tian. 2021. Rethinking rotated object detection with gaussian wasserstein distance loss. In International conference on machine learning. PMLR, 11830-11841."},{"key":"e_1_3_2_1_38_1","volume-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605","author":"Zhang Hao","year":"2022","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel M Ni, and Heung-Yeung Shum. 2022. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"e_1_3_2_1_40_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2nd International Workshop on Multimedia Computing for Health and Medicine"],"original-title":[],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:18:10Z","timestamp":1761059890000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728424.3760769"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":40,"alternative-id":["10.1145\/3728424.3760769","10.1145\/3728424"],"URL":"https:\/\/doi.org\/10.1145\/3728424.3760769","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]},"assertion":[{"value":"2025-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}