{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T07:02:06Z","timestamp":1791356526918,"version":"4.3.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Deanship of Scientific Research,  Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia","award":["KFU253697"],"award-info":[{"award-number":["KFU253697"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-27872-3","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T11:01:54Z","timestamp":1764241314000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["CATR: CNN augmented transformer for object detection in remote sensing imagery"],"prefix":"10.1038","volume":"15","author":[{"given":"Sahibzada Jawad","family":"Hadi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irfan","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abid","family":"Iqbal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali S.","family":"Alzahrani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,27]]},"reference":[{"key":"27872_CR1","volume":"134","author":"Z Chen","year":"2024","unstructured":"Chen, Z. et al. Object detection in aerial images using dota dataset: a survey. Int. J. Appl. Earth Observ. Geoinf. 134, 104208 (2024).","journal-title":"Int. J. Appl. Earth Observ. Geoinf."},{"issue":"4","key":"27872_CR2","doi-asserted-by":"publisher","first-page":"984","DOI":"10.3390\/rs14040984","volume":"14","author":"Q Li","year":"2022","unstructured":"Li, Q., Chen, Y. & Zeng, Y. Transformer with transfer CNN for remote-sensing-image object detection. Remote Sens. 14(4), 984 (2022).","journal-title":"Remote Sens."},{"key":"27872_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114602","volume":"172","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Sun, P., Wergeles, N. & Shang, Y. A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl. 172, 114602 (2021).","journal-title":"Expert Syst. Appl."},{"key":"27872_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A. & Zagoruyko, S. \u201cEnd-to-end object detection with transformers,\u201d in European Conference on Computer Vision, pp.\u00a0213\u2013229, Springer, (2020).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"27872_CR5","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P. & Girshick, R. \u201cMasked autoencoders are scalable vision learners,\u201d in Proceedings of the IEEE\/CVF Conference on vision and Pattern Recognition, pp.\u00a016000\u201316009, (2022).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"27872_CR6","first-page":"35632","volume":"35","author":"P Gao","year":"2022","unstructured":"Gao, P. et al. MCMAE: Masked convolution meets masked autoencoders. Adv. Neural Inf. Process.Syst. 35, 35632\u201335644 (2022).","journal-title":"Adv. Neural Inf. Process.Syst."},{"key":"27872_CR7","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.\u00a0770\u2013778, (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"27872_CR8","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B. & Belongie, S. Feature pyramid networks for object detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.\u00a02117\u20132125, (2017).","DOI":"10.1109\/CVPR.2017.106"},{"key":"27872_CR9","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":"27872_CR10","unstructured":"Redmon, J. & Farhadi, A. Yolov3: An incremental improvement, arXiv preprint arXiv:1804.02767, (2018)."},{"key":"27872_CR11","first-page":"107984","volume":"37","author":"A Wang","year":"2024","unstructured":"Wang, A. et al. Yolov10: Real-time end-to-end object detection. Adv. Neural Inf. Process. Syst. 37, 107984\u2013108011 (2024).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"27872_CR12","doi-asserted-by":"crossref","unstructured":"Hong, W., Lao, J., Ren, W., Wang, J., Chen, J. & Chu, W. Training object detectors from scratch: An empirical study in the era of vision transformer, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.\u00a04662\u20134671, (2022).","DOI":"10.1109\/CVPR52688.2022.00462"},{"key":"27872_CR13","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. An image is worth 16x16 words: Transformers for image recognition at scale, arXiv preprint arXiv:2010.11929, (2020)."},{"issue":"7","key":"27872_CR14","doi-asserted-by":"publisher","first-page":"1860","DOI":"10.3390\/rs15071860","volume":"15","author":"AA Aleissaee","year":"2023","unstructured":"Aleissaee, A. A. et al. Transformers in remote sensing: A survey. Remote Sens. 15(7), 1860 (2023).","journal-title":"Remote Sens."},{"key":"27872_CR15","unstructured":"Zhou, M., Li, X., Chen, Y. & Zhang, Y. Transformer-based person detection in rgbt aerial images with paired VTSaR, IEEE Transactions on Geoscience and Remote Sensing, (2023)."},{"issue":"2","key":"27872_CR16","doi-asserted-by":"publisher","first-page":"412","DOI":"10.3390\/rs16020412","volume":"15","author":"H Wang","year":"2023","unstructured":"Wang, H., Yang, J., Zhao, R., Li, W. & Gao, Y. Aerial person detection for search and rescue: Survey and benchmarks. Remote Sens. 15(2), 412 (2023).","journal-title":"Remote Sens."},{"key":"27872_CR17","first-page":"25","volume":"178","author":"H Liu","year":"2024","unstructured":"Liu, H., Zhang, R., Chen, G. & Li, Q. Robust aerial person detection with lightweight distillation network for edge deployment. Pattern Recognit. Lett. 178, 25\u201334 (2024).","journal-title":"Pattern Recognit. Lett."},{"key":"27872_CR18","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu, J. et al. Recent advances in convolutional neural networks. Pattern Recognit. 77, 354\u2013377 (2018).","journal-title":"Pattern Recognit."},{"key":"27872_CR19","doi-asserted-by":"crossref","unstructured":"Redmon, J. et al. You only look once: Unified, real-time object detection, in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, (2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"27872_CR20","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.\u00a03651\u20133660, (2021).","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"27872_CR21","doi-asserted-by":"publisher","first-page":"941","DOI":"10.3389\/fpls.2019.00941","volume":"10","author":"J Boulent","year":"2019","unstructured":"Boulent, J., Foucher, S., Th\u00e9au, J. & St-Charles, P.-L. Convolutional neural networks for the automatic identification of plant diseases. Front. Plant Sci. 10, 941 (2019).","journal-title":"Front. Plant Sci."},{"key":"27872_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2019.100616","volume":"52","author":"A Darwish","year":"2020","unstructured":"Darwish, A., Ezzat, D. & Hassanien, A. E. An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis. Swarm Evol. Comput. 52, 100616 (2020).","journal-title":"Swarm Evol. Comput."},{"issue":"3","key":"27872_CR23","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1007\/s11760-021-02024-y","volume":"16","author":"MP Mathew","year":"2022","unstructured":"Mathew, M. P. & Mahesh, T. Y. Leaf-based disease detection in bell pepper plant using yolo v5. Signal Image Vid. Process. 16(3), 841\u2013847 (2022).","journal-title":"Signal Image Vid. Process."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27872-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27872-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27872-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T11:02:03Z","timestamp":1764241323000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27872-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,27]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["27872"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-27872-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,27]]},"assertion":[{"value":"20 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2025","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":"42281"}}