{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T19:33:06Z","timestamp":1794079986104,"version":"4.8.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"content-version":"vor","delay-in-days":54,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Science and Technology Development Plan Project of Jilin Province","award":["20240304186SF"],"award-info":[{"award-number":["20240304186SF"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-48909-1","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:45:09Z","timestamp":1776357909000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["HA-DETR: accelerating real-time object detection by replacing decoder self-attention"],"prefix":"10.1038","volume":"16","author":[{"given":"Yanqiu","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"key":"48909_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B. & Xia, T. Multi-view 3d object detection network for autonomous driving. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 1907\u20131915 (2017).","DOI":"10.1109\/CVPR.2017.691"},{"key":"48909_CR2","doi-asserted-by":"publisher","first-page":"1707","DOI":"10.1177\/0278364910365417","volume":"29","author":"A Ess","year":"2010","unstructured":"Ess, A., Schindler, K., Leibe, B. & Van Gool, L. Object detection and tracking for autonomous navigation in dynamic environments. Int. J. Robot. Res. 29, 1707\u20131725 (2010).","journal-title":"Int. J. Robot. Res."},{"key":"48909_CR3","doi-asserted-by":"crossref","unstructured":"Redmon, J. You only look once: Unified, real-time object detection. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 779\u2013788 (2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"48909_CR4","doi-asserted-by":"crossref","unstructured":"Redmon, J. & Farhadi, A. Yolo9000: better, faster, stronger. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 7263\u20137271 (2017).","DOI":"10.1109\/CVPR.2017.690"},{"key":"48909_CR5","unstructured":"Bochkovskiy, A., Wang, C.-Y. & Liao, H.-Y.\u00a0M. Yolov4: Optimal speed and accuracy of object detection (2020)."},{"key":"48909_CR6","doi-asserted-by":"crossref","unstructured":"Carion, N. et al. End-to-end object detection with transformers. In European Conference on Computer Vision, pp. 213\u2013229 (Springer, 2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"48909_CR7","doi-asserted-by":"crossref","unstructured":"Meng, D. et al. Conditional detr for fast training convergence. In Proc. IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021).","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"48909_CR8","unstructured":"Zhang, H. et al. Dino: Detr with improved denoising anchor boxes for end-to-end object detection. In ICLR (2023)."},{"key":"48909_CR9","volume-title":"Proc. AAAI Conference on Artificial Intelligence","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Zhang, X. & Yang, T. Proc. AAAI Conference on Artificial Intelligence (Query design for transformer-based detector, 2022)."},{"key":"48909_CR10","doi-asserted-by":"crossref","unstructured":"Zhao, Y. et al. Detrs beat yolos on real-time object detection. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024).","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"48909_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. A convnet for the 2020s. Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022).","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"48909_CR12","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. ICLR (2021)."},{"key":"48909_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proc. IEEE\/CVF International Conference on Computer Vision (ICCV) (2021).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"48909_CR14","unstructured":"Chen, X., Li, S., Yang, Y. & Wang, Y. DECO: Unleashing the potential of convnets for query-based detection and segmentation. In The Thirteenth International Conference on Learning Representations (2025)."},{"key":"48909_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In CVPR (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"48909_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al. Microsoft coco: Common objects in context. In ECCV (2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"48909_CR17","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H. W. The hungarian method for the assignment problem. Naval Res. Logist. Quart. 2, 83\u201397 (1955).","journal-title":"Naval Res. Logist. Quart."},{"key":"48909_CR18","unstructured":"Zhu, X. et al. Deformable detr: Deformable transformers for end-to-end object detection. In International Conference on Learning Representations (2020)."},{"key":"48909_CR19","unstructured":"Lin, J. et al. D$$^{\\wedge }$$ 2etr: Decoder-only detr with computationally efficient cross-scale attention. Preprint at arXiv:2203.00860 (2022)."},{"key":"48909_CR20","doi-asserted-by":"crossref","unstructured":"Dai, X. et al. Dynamic detr: End-to-end object detection with dynamic attention. In Proc. IEEE\/CVF International Conference on Computer Vision (ICCV) (2021).","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"48909_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. Focal loss for dense object detection. In Proc. IEEE\/CVF International Conference on Computer Vision (2017).","DOI":"10.1109\/ICCV.2017.324"},{"key":"48909_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F. & Sunderhauf, N. Varifocalnet: An iou-aware dense object detector. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021).","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"48909_CR23","doi-asserted-by":"crossref","unstructured":"Huang, S. et al. Deim: Detr with improved matching for fast convergence. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025).","DOI":"10.1109\/CVPR52734.2025.01412"},{"key":"48909_CR24","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Yeh, I.-H. & Mark Liao, H.-Y. Yolov9: Learning what you want to learn using programmable gradient information. In European Conference on Computer Vision (2024).","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"48909_CR25","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H. et al. Generalized intersection over union: A metric and a loss for bounding box regression. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 658\u2013666 (2019).","DOI":"10.1109\/CVPR.2019.00075"},{"key":"48909_CR26","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems (2015)."},{"key":"48909_CR27","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H. & He, T. Fcos: Fully convolutional one-stage object detection. In Proc. IEEE\/CVF International Conference on Computer Vision (2019).","DOI":"10.1109\/ICCV.2019.00972"},{"key":"48909_CR28","doi-asserted-by":"crossref","unstructured":"Sun, P. et al. Sparse r-cnn: End-to-end object detection with learnable proposals. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021).","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"48909_CR29","doi-asserted-by":"crossref","unstructured":"Wang, J. et al. End-to-end object detection with fully convolutional network. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021).","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"48909_CR30","first-page":"26183","volume":"34","author":"Y Fang","year":"2021","unstructured":"Fang, Y. et al. You only look at one sequence: Rethinking transformer in vision through object detection. Adv. Neural Inf. Process. Syst. 34, 26183\u201326197 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"48909_CR31","doi-asserted-by":"crossref","unstructured":"Huang, S. et al. Deim: Detr with improved matching for fast convergence. In Proc. Computer Vision and Pattern Recognition Conference, 15162\u201315171 (2025).","DOI":"10.1109\/CVPR52734.2025.01412"},{"key":"48909_CR32","unstructured":"Liu, S. et al. DAB-DETR: Dynamic anchor boxes are better queries for DETR. In International Conference on Learning Representations (2022)."},{"key":"48909_CR33","unstructured":"Song, H. et al. Vidt: An efficient and effective fully transformer-based object detector. In International Conference on Learning Representation (2022)."},{"key":"48909_CR34","doi-asserted-by":"crossref","unstructured":"Liu, S. et al. Detection transformer with stable matching. In Proc. IEEE\/CVF International Conference on Computer Vision (ICCV) (2023).","DOI":"10.1109\/ICCV51070.2023.00597"},{"key":"48909_CR35","unstructured":"Dong, P. et al. Speeddetr: speed-aware transformers for end-to-end object detection. In Proc. 40th International Conference on Machine Learning (2023)."},{"key":"48909_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, S. et al. Dense distinct query for end-to-end object detection. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023).","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"48909_CR37","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G. & Liu, Y. Detrs with collaborative hybrid assignments training. In Proc. IEEE\/CVF International Conference on Computer Vision (2023).","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"48909_CR38","doi-asserted-by":"crossref","unstructured":"Jia, D. et al. Detrs with hybrid matching. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023).","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"48909_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., Chen, X. & Wang, Y. Less is more: Focus attention for efficient detr. In Proc. IEEE\/CVF International Conference on Computer Vision (2023).","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"48909_CR40","first-page":"16100","volume":"36","author":"Y Pu","year":"2023","unstructured":"Pu, Y. et al. Rank-detr for high quality object detection. Adv. Neural Inf. Process. Syst. 36, 16100\u201316113 (2023).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"48909_CR41","unstructured":"Lv, W. et al. Rt-detrv2: Improved baseline with bag-of-freebies for real-time detection transformer. Preprint at arXiv:2407.17140 (2024)."},{"key":"48909_CR42","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In International Conference on Learning Representations (2018)."},{"key":"48909_CR43","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition (2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"48909_CR44","doi-asserted-by":"crossref","unstructured":"Howard, A. et al. Searching for mobilenetv3. In Proc. IEEE\/CVF International Conference on Computer Vision, 1314\u20131324 (2019).","DOI":"10.1109\/ICCV.2019.00140"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48909-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48909-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48909-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T22:55:54Z","timestamp":1780959354000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-48909-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,16]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["48909"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-48909-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,16]]},"assertion":[{"value":"1 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2026","order":3,"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":"Competing interests"}}],"article-number":"17749"}}