{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T23:27:35Z","timestamp":1787268455271,"version":"build-2736575974"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":57,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Wenzhou major scientific and technological innovation project plan \"reveal the list\"","award":["ZG2023022"],"award-info":[{"award-number":["ZG2023022"]}]},{"DOI":"10.13039\/501100018553","name":"Wenzhou science and technology project","doi-asserted-by":"crossref","award":["G2022S0097"],"award-info":[{"award-number":["G2022S0097"]}],"id":[{"id":"10.13039\/501100018553","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-50585-0","type":"journal-article","created":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T13:13:44Z","timestamp":1777209224000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A novel object detection algorithm based on Swin Transformer"],"prefix":"10.1038","volume":"16","author":[{"given":"YueJing","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"ZengYou","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WeiJun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"issue":"2","key":"50585_CR1","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"T Lin","year":"2020","unstructured":"Lin, T., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318\u2013327. https:\/\/doi.org\/10.1109\/TPAMI.2018.2858826 (2020).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50585_CR2","doi-asserted-by":"crossref","unstructured":"Liu, W. et al. SSD: Single Shot MultiBox Detector BT - Computer Vision \u2013 ECCV 2016,., pp. 21\u201337. (2016).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"50585_CR3","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779\u2013788, (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"50585_CR4","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. 39(6), 1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031 (2017).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"50585_CR5","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R. & Mask, R-C-N-N. In: IEEE International Conference on Computer Vision (ICCV), 2980\u20132988, (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.322","DOI":"10.1109\/ICCV.2017.322"},{"key":"50585_CR6","unstructured":"Vaswani, A. et al. Attention is All You Need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 6000\u20136010. (2017)."},{"key":"50585_CR7","doi-asserted-by":"publisher","unstructured":"Wang, W. et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 2021, 548\u2013558. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00061","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"50585_CR8","doi-asserted-by":"publisher","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical Vision transformer using shifted windows, In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 9992\u201310002, (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"50585_CR9","unstructured":"Chu, X. et al. Twins: revisiting the design of spatial attention in vision transformers, in Advances in Neural Information Processing Systems (NeurIPS), 9256\u20139268. (2021)."},{"key":"50585_CR10","doi-asserted-by":"publisher","unstructured":"Chen, C. F. R., Fan, Q. & Panda, R. CrossViT: cross-attention multi-scale vision transformer for image classification. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 347\u2013356, (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00041","DOI":"10.1109\/ICCV48922.2021.00041"},{"issue":"3","key":"50585_CR11","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W. et al. PVT v2: Improved baselines with Pyramid Vision Transformer. Comput. Vis. Media 8(3), 415\u2013424. https:\/\/doi.org\/10.1007\/s41095-022-0274-8 (2022).","journal-title":"Comput. Vis. Media"},{"key":"50585_CR12","doi-asserted-by":"publisher","first-page":"26023","DOI":"10.1007\/s11042-020-09242-5","volume":"79","author":"MS Alam","year":"2020","unstructured":"Alam, M. S. et al. Efficient vehicle detection and tracking strategy in aerial videos by employing morphological operations and feature points motion analysis. Multimed Tools Appl. 79, 26023\u201326043 (2020).","journal-title":"Multimed Tools Appl."},{"key":"50585_CR13","unstructured":"Alam, M. S. et al. Real-time algorithm for simultaneous vehicle detection and tracking in aerial view videos (J. Real-Time Image Process, 2018)."},{"key":"50585_CR14","unstructured":"Alam, M. S. et al. Residual Channel-attention network for remote sensing image scene classification. IEEE Trans. Geosci. Remote Sens., (2025)."},{"key":"50585_CR15","doi-asserted-by":"publisher","unstructured":"Gomaa, A. & Saad, O. M. SCAR-Net: a selective channel attention with residuals network for high-resolution remote sensing scene classification, In: 2025 7th Novel Intelligent and Leading Emerging Sciences Conference (NILES), Giza, Egypt, 2025, 522\u2013525. https:\/\/doi.org\/10.1109\/NILES68063.2025.11232133","DOI":"10.1109\/NILES68063.2025.11232133"},{"key":"50585_CR16","unstructured":"Alam, M. S. et al. Detection of earthquake induced building damages using remote sensing data and deep learning: A case study of Mashiki Town (Japan, Remote Sens, 2023)."},{"key":"50585_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-02111-x","author":"A Rahman","year":"2025","unstructured":"Rahman, A. et al. Real-time driver drowsiness detection using transformer architectures: A novel deep learning approach. Sci. Rep. https:\/\/doi.org\/10.1038\/s41598-025-02111-x (2025).","journal-title":"Sci. Rep."},{"key":"50585_CR18","unstructured":"Hosny, K. M. et al. Advanced domain adaptation technique for object detection leveraging semi-automated dataset construction and enhanced yolov8, Pattern Recognit., (2024)."},{"key":"50585_CR19","unstructured":"Hosny, K. M. et al. Novel deep learning domain adaptation approach for object detection using semi-self building dataset and modified YOLOv4. (IEEE Access. 2024)."},{"key":"50585_CR20","doi-asserted-by":"publisher","unstructured":"van de Sande, K. E. A., Uijlings, J. R. R., Gevers, T. & Smeulders, A. W. M. Segmentation as selective search for object recognition. In: International Conference on Computer Vision, 2011, 1879\u20131886, (2011). https:\/\/doi.org\/10.1109\/ICCV.2011.6126456","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"50585_CR21","doi-asserted-by":"publisher","unstructured":"Girshick, R. & Fast, R-C-N-N. In: 2015 IEEE International Conference on Computer Vision (ICCV), 1440\u20131448, (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"50585_CR22","doi-asserted-by":"publisher","unstructured":"Cai, Z., Vasconcelos, N. & Cascade, R-C-N-N. delving into high quality object detection. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, 6154\u20136162. https:\/\/doi.org\/10.1109\/CVPR.2018.00644","DOI":"10.1109\/CVPR.2018.00644"},{"key":"50585_CR23","doi-asserted-by":"publisher","unstructured":"Lin, T. Y. et al. IEEE Conference on Computer Vision and Feature Pyramid Networks for Object Detection, in (CVPR). 936\u2013944, (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"50585_CR24","doi-asserted-by":"publisher","unstructured":"Song, G., Liu, Y. & Wang, X. Revisiting the sibling head in object detector. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, 11560\u201311569. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01158","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"50585_CR25","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3825532","author":"T Liang","year":"2022","unstructured":"Liang, T., Bao, H., Pan, W. & Pan, F. Traffic sign detection via improved sparse R-CNN for autonomous vehicles. J. Adv. Transp. (2022). https:\/\/doi.org\/10.1155\/2022\/3825532","journal-title":"J. Adv. Transp."},{"key":"50585_CR26","doi-asserted-by":"publisher","unstructured":"Zhang, H. et al. ResNeSt: split-attention networks. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2735\u20132745, (2022). https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00309","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"50585_CR27","doi-asserted-by":"publisher","first-page":"122774","DOI":"10.1109\/ACCESS.2021.3109606","volume":"9","author":"J Cao","year":"2021","unstructured":"Cao, J., Zhang, J. & Jin, X. A traffic-sign detection algorithm based on improved sparse R-CNN.. IEEE Access 9, 122774\u2013122788. https:\/\/doi.org\/10.1109\/ACCESS.2021.3109606 (2021).","journal-title":"IEEE Access"},{"key":"50585_CR28","doi-asserted-by":"publisher","unstructured":"Araki, R., Onishi, T., Hirakawa, T., Yamashita, T. & Fujiyoshi, H. MT-DSSD: deconvolutional single shot detector using multi task learning for object detection, segmentation, and grasping detection, In: IEEE International Conference on Robotics and Automation (ICRA). 10487\u201310493, (2020). https:\/\/doi.org\/10.1109\/ICRA40945.2020.9197251","DOI":"10.1109\/ICRA40945.2020.9197251"},{"key":"50585_CR29","doi-asserted-by":"publisher","unstructured":"Tan, M., Pang, R. & Le, Q. V. EfficientDet: scalable and efficient object detection. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10778\u201310787 (2020) https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"issue":"3","key":"50585_CR30","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1007\/s11263-019-01204-1","volume":"128","author":"H Law","year":"2020","unstructured":"Law, H. & Deng, J. CornerNet: Detecting objects as paired keypoints. Int. J. Comput. Vis. 128(3), 642\u2013656. https:\/\/doi.org\/10.1007\/s11263-019-01204-1 (2020).","journal-title":"Int. J. Comput. Vis."},{"key":"50585_CR31","doi-asserted-by":"publisher","unstructured":"Duan, K. et al. CenterNet: keypoint triplets for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 6568\u20136577, (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00667","DOI":"10.1109\/ICCV.2019.00667"},{"key":"50585_CR32","doi-asserted-by":"crossref","unstructured":"Liu, S., Huang, D. & Wang, Y. Receptive field block net for accurate and fast object detection BT - Computer Vision \u2013 ECCV 2018, 404\u2013419. (2018).","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"50585_CR33","doi-asserted-by":"publisher","unstructured":"Li, X., Wang, W., Hu, X. & Yang, J. Selective kernel networks. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 510\u2013519, (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00060","DOI":"10.1109\/CVPR.2019.00060"},{"key":"50585_CR34","doi-asserted-by":"publisher","unstructured":"Wang, Q. et al. ECA-Net: Efficient channel attention for deep convolutional neural networks. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 11531\u201311539, (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01155","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"50585_CR35","doi-asserted-by":"publisher","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J. & Jia, J. Path aggregation network for instance segmentation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 8759\u20138768, (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"50585_CR36","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770\u2013778, (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"50585_CR37","doi-asserted-by":"publisher","unstructured":"Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J. & Zisserman, A. The Pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303\u2013338. https:\/\/doi.org\/10.1007\/s11263-009-0275-4 (2010).","DOI":"10.1007\/s11263-009-0275-4"},{"key":"50585_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T. Y. et al. Microsoft COCO: Common Objects in Context BT - Computer Vision \u2013 ECCV 2014,., pp. 740\u2013755. (2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"50585_CR39","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet Classification with Deep Convolutional Neural Networks. BT - Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3\u20136, 2012, Lake Tahoe. 1106\u20131114, (2012)."},{"key":"50585_CR40","doi-asserted-by":"publisher","unstructured":"Bell, S., Zitnick, C. L., Bala, K., Girshick, R. & Recognition, P. In: IEEE Conference on Computer Vision and Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks, in (CVPR), 2874\u20132883, (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.314","DOI":"10.1109\/CVPR.2016.314"},{"key":"50585_CR41","unstructured":"Dai, J., Li, Y., He, K. & Sun, J. R-FCN: object detection via region-based fully convolutional networks, In: Proceedings of the 30th International Conference on Neural Information Processing Systems, 379\u2013387. (2016)."},{"key":"50585_CR42","doi-asserted-by":"publisher","unstructured":"Zhu, Y. et al. CoupleNet: Coupling global structure with local parts for object detection, In: IEEE International Conference on Computer Vision (ICCV), 4146\u20134154, (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.444","DOI":"10.1109\/ICCV.2017.444"},{"key":"50585_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104615","volume":"130","author":"H Liu","year":"2023","unstructured":"Liu, H., You, X., Wang, T. & Li, Y. Object detection via inner-inter relational reasoning network. Image Vis. Comput. 130, 104615. https:\/\/doi.org\/10.1016\/j.imavis.2022.104615 (2023).","journal-title":"Image Vis. Comput."},{"key":"50585_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, Z. et al. Single-shot object detection with enriched semantics, In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5813\u20135821, (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00609","DOI":"10.1109\/CVPR.2018.00609"},{"key":"50585_CR45","doi-asserted-by":"publisher","unstructured":"Li, S., Yang, L., Huang, J., Hua, X. S. & Zhang, L. Dynamic anchor feature selection for single-shot object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 6608\u20136617, (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00671","DOI":"10.1109\/ICCV.2019.00671"},{"key":"50585_CR46","doi-asserted-by":"crossref","unstructured":"M. Zand, A. Etemad, and M. Greenspan, ObjectBox: From Centers to Boxes for Anchor-Free Object Detection, Computer Vision \u2013 ECCV 2022. In: 17th European Conference, Tel Aviv,Israel, October 23\u201327, 2022, Proceedings, Part X, 2022, pp. 390\u2013406, doi: 10.1007\/978-3-031-20080-9_23.","DOI":"10.1007\/978-3-031-20080-9_23"},{"key":"50585_CR47","doi-asserted-by":"publisher","first-page":"110361","DOI":"10.1109\/ACCESS.2023.3321966","volume":"11","author":"W Wang","year":"2023","unstructured":"Wang, W. & Gou, Y. An anchor-free lightweight object detection network. IEEE Access 11, 110361\u2013110374. https:\/\/doi.org\/10.1109\/ACCESS.2023.3321966 (2023).","journal-title":"IEEE Access"},{"key":"50585_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2023.108695","volume":"108","author":"M Sirisha","year":"2023","unstructured":"Sirisha, M. & Sudha, S. V. TOD-Net: An end-to-end transformer-based object detection network. Comput. Electr. Eng. 108, 108695. https:\/\/doi.org\/10.1016\/j.compeleceng.2023.108695 (2023).","journal-title":"Comput. Electr. Eng."},{"key":"50585_CR49","unstructured":"Zhu, X. et al. Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (ICLR) (2021)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50585-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50585-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50585-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T23:41:12Z","timestamp":1782085272000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50585-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["50585"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-50585-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"22 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 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"}},{"value":"This study is a purely computational research project involving the development and evaluation of object detection algorithms. No human participants were recruited or involved in this research. All images used for experiments and qualitative analysis are sourced from publicly available benchmark datasets (PASCAL VOC and MS COCO), which are openly accessible for academic research purposes. Therefore, ethical approval and informed consent are not applicable to this study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"19274"}}