{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:52:57Z","timestamp":1785336777382,"version":"3.55.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11760-026-05441-z","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T19:52:15Z","timestamp":1781121135000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Rf-detr: advancing real-time transformer-based object detection model"],"prefix":"10.1007","volume":"20","author":[{"given":"Ajay B.","family":"Gadicha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vijay B.","family":"Gadicha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashu","family":"Abdul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh Reddy","family":"V","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahesh Kumar","family":"Morampudi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajeev","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"5441_CR1","unstructured":"Bochkovskiy, A., Wang, Y., and Liao, H.Y.M. YOLOv4: Optimal speed and accuracy of object detection, 2020. arXiv:2004.10934"},{"key":"5441_CR2","unstructured":"Redmon, J., and Farhadi, A. YOLOv3: An incremental improvement, (2018) . arXiv:1804.02767"},{"key":"5441_CR3","doi-asserted-by":"publisher","unstructured":"Wang, C.Y., Liao, H.Y.M, Wu, Y.H., Chen, P.Y., Hsieh, J.W., and Yeh, I.H.: CSPNet: A new backbone that can enhance learning capability of CNN. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 390\u2013391, 2020. https:\/\/doi.org\/10.1109\/CVPRW50498.2020.00203","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"5441_CR4","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I. :(2017). A ttention is all you need. In Advances in Neural Information Processing Systems (NeurIPS), volume 30, pp. 5998\u20136008, https:\/\/doi.org\/10.48550\/arXiv.1706.03762"},{"key":"5441_CR5","doi-asserted-by":"publisher","first-page":"4228610","DOI":"10.1155\/2023\/4228610","volume":"2023","author":"P Shi","year":"2023","unstructured":"Shi, P., Chen, X., Qi, H., Zhang, C., Liu, Z.: Object detection based on Swin deformable transformer-BiPAFPN-YOLOX. Comput. Intell. Neurosci. 2023, 4228610 (2023). https:\/\/doi.org\/10.1155\/2023\/4228610","journal-title":"Comput. Intell. Neurosci."},{"key":"5441_CR6","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S.: End-to-end object detection with transformers. In Proceedings of the European Conference on Computer Vision (ECCV), pp. 213\u2013229. Springer, Cham, (2020) https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"5441_CR7","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., and Dai, J.: Deformable DETR: Deformable transformers for end-to-end object detection. In Proceedings of the 9th International Conference on Learning Representations (ICLR), 2021. https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke"},{"key":"5441_CR8","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: Deformable transformers for end-to-end object detection, (2020). arXiv:2010.04159"},{"issue":"6","key":"5441_CR9","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 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5441_CR10","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. Ultralytics YOLOv8 (version 8.0.0), (2023) https:\/\/github.com\/ultralytics\/ultralytics. Software available at"},{"key":"5441_CR11","unstructured":"Chen, Q., Su, C., Dong, J., Zeng, A., Peng, Y., Li, Z., Ma, L., Zheng, M., Yuan, Z., Lu, T., Xu, Y., Ye, Q., and Wang, J. LW-DETR: A transformer replacement to YOLO for real-time detection, (2024). arXiv:2406.03459"},{"key":"5441_CR12","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, (2023). arXiv:2304.08069"},{"key":"5441_CR13","unstructured":"Sapkota, R., Cheppally, R.H., Sharda, A., and Karkee, M.: RF-DETR object detection vs YOLOv12: A study of transformer-based and CNN-based architectures for greenfruit detection, (2025). arXiv:2504.13099"},{"key":"5441_CR14","doi-asserted-by":"publisher","unstructured":"Li, F., Zhang, H., Xu, H., Liu, S., Zhang, L., Ni, L.M., and Shum, H.Y:. Mask DINO: Towards a unified transformer-based framework for object detection and segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3041\u20133050. IEEE\/CVF, (2023) . https:\/\/doi.org\/10.1109\/CVPR52729.2023.00297","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"5441_CR15","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., and Shum, H.Y.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection, (2022) . arXiv:2203.03605"},{"key":"5441_CR16","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Advances Neural Inform. Processing Syst. (NeurIPS) 25, 1097\u20131105 (2012)","journal-title":"Advances Neural Inform. Processing Syst. (NeurIPS)"},{"issue":"8","key":"5441_CR17","doi-asserted-by":"publisher","first-page":"5359","DOI":"10.1109\/TII.2021.3116377","volume":"18","author":"FMU Ullah","year":"2022","unstructured":"Ullah, F.M.U., Muhammad, K., Haq, K.U., Khan, N., Heidari, A.A., Baik, S.W., de Albuquerque, V.H.C.: AI-assisted edge vision for violence detection in IoT-based industrial surveillance networks. IEEE Trans. Industr. Inf. 18(8), 5359\u20135370 (2022). https:\/\/doi.org\/10.1109\/TII.2021.3116377","journal-title":"IEEE Trans. Industr. Inf."},{"key":"5441_CR18","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, S., Doll\u00e1r, P., Tu, Z., and He, K. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1492\u20131500, (2017) . https:\/\/doi.org\/10.1109\/CVPR.2017.634","DOI":"10.1109\/CVPR.2017.634"},{"key":"5441_CR19","doi-asserted-by":"publisher","unstructured":"Howard, A., Sandler, M., Chu, G, Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, W., Pang, R., and Vasudevan, V. Searching for MobileNetV3. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pages 1314\u20131324, (2019) . https:\/\/doi.org\/10.1109\/ICCV.2019.00140","DOI":"10.1109\/ICCV.2019.00140"},{"key":"5441_CR20","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1007\/s11554-021-01107-w","volume":"18","author":"C \u00c1lvarez Casado","year":"2021","unstructured":"\u00c1lvarez Casado, C., Bordallo L\u00f3pez, M.: Real-time face alignment: evaluation methods, training strategies and implementation optimization. J. Real-Time Image Proceeding 18, 2239\u20132267 (2021). https:\/\/doi.org\/10.1007\/s11554-021-01107-w","journal-title":"J. Real-Time Image Proceeding"},{"key":"5441_CR21","doi-asserted-by":"publisher","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., and Zhang, L. DN-DETR: Accelerate DETR training by introducing query denoising. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 13619\u201313627, (2022) . https:\/\/doi.org\/10.1109\/CVPR52688.2022.01325","DOI":"10.1109\/CVPR52688.2022.01325"},{"issue":"22","key":"5441_CR22","doi-asserted-by":"publisher","first-page":"10331","DOI":"10.3390\/app142210331","volume":"14","author":"L Chenyu","year":"2024","unstructured":"Chenyu, L., Wang, J., Zhang, X., Liu, S., Wei, H., Cong, F.: RS-DETR: An improved remote sensing object detection model based on RT-DETR. Appl. Sci. 14(22), 10331 (2024). https:\/\/doi.org\/10.3390\/app142210331","journal-title":"Appl. Sci."},{"issue":"7","key":"5441_CR23","doi-asserted-by":"publisher","first-page":"2190","DOI":"10.3390\/s25072190","volume":"25","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Liu, H., Chen, W., Li, Y., Wang, X.: SF-DETR: Scale-frequency detection transformer for drone-view object detection. Sensors 25(7), 2190 (2025). https:\/\/doi.org\/10.3390\/s25072190","journal-title":"Sensors"},{"key":"5441_CR24","doi-asserted-by":"publisher","unstructured":"Habe, T.T., Haataja, K., and Toivanen, P. Precision enhancement in wireless capsule endoscopy: a novel transformer-based approach for real-time video object detection. Frontiers in Artificial Intelligence, 8:1529814, (2025) . https:\/\/doi.org\/10.3389\/frai.2025.1529814","DOI":"10.3389\/frai.2025.1529814"},{"key":"5441_CR25","doi-asserted-by":"publisher","unstructured":"Allmendinger, A., Salt\u0131k, A.O., Peteinatos, G.G., Stein, A., Gerhards, R.: Assessing the capability of YOLO- and transformer-based object detectors for real-time weed detection. Precision Agric. (2025). https:\/\/doi.org\/10.1007\/s11119-025-10246-0","DOI":"10.1007\/s11119-025-10246-0"},{"key":"5441_CR26","doi-asserted-by":"publisher","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 (CVPR), pages 779\u2013788, (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"issue":"7","key":"5441_CR27","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.3390\/f15071096","volume":"15","author":"R Wang","year":"2024","unstructured":"Wang, R., Chen, Y., Liang, F., Wang, B., Mou, X., Zhang, G.: BPN-YOLO: A novel method for wood defect detection based on YOLOv7. Forests 15(7), 1096 (2024). https:\/\/doi.org\/10.3390\/f15071096","journal-title":"Forests"},{"key":"5441_CR28","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. . arXiv:1904.07850 (2019)"},{"key":"5441_CR29","doi-asserted-by":"publisher","unstructured":"Tan, M., Pang, R., Quoc, V.L.: EfficientDet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 10781\u201310790. IEEE\/CVF, 2020. https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"5441_CR30","unstructured":"Tian, Y., Ye, Q., Doermann, D.: YOLOv12: Attention-centric real-time object detectors, (2025). arXiv:2502.12524"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05441-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05441-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05441-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:52:15Z","timestamp":1782928335000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05441-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":30,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["5441"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05441-z","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"4 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2026","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 declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"410"}}