{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:44:51Z","timestamp":1790876691177,"version":"4.1.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T00:00:00Z","timestamp":1763510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-24576-6","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T12:29:06Z","timestamp":1763555346000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["YOLO-SAM an end-to-end framework for efficient real time object detection and segmentation"],"prefix":"10.1038","volume":"15","author":[{"given":"XiuMei","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"XiaHua","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"WenChao","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"XuDong","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,19]]},"reference":[{"key":"24576_CR1","doi-asserted-by":"crossref","unstructured":"Girshick, R. Fast r-cnn, in Proceedings of the IEEE international conference on computer vision, 1440\u20131448 (2015).","DOI":"10.1109\/ICCV.2015.169"},{"key":"24576_CR2","doi-asserted-by":"crossref","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, 779\u2013788 (2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"24576_CR3","doi-asserted-by":"publisher","unstructured":"Liu, Y. et al. YOLOv8 Model for Weed Detection, in Wheat Fields Based on a Visual Converter and Multi-Scale Feature Fusion. Sensors (14248220), 24(13). (2024). https:\/\/doi.org\/10.3390\/s24134379","DOI":"10.3390\/s24134379"},{"key":"24576_CR4","doi-asserted-by":"publisher","unstructured":"Ren S , He K , Girshick R ,et al.Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 39(6):1137\u20131149.https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031 (2017).","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"24576_CR5","doi-asserted-by":"publisher","unstructured":"Zhang H , Li F , Liu S ,et al.DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection[J].arXiv e-prints, https:\/\/doi.org\/10.48550\/arXiv.2203.03605 (2022).","DOI":"10.48550\/arXiv.2203.03605"},{"key":"24576_CR6","unstructured":"Zhu, X. et al. Deformable detr: Deformable transformers for end-to-end object detection. arXiv 2020. arXiv preprint arXiv:2010.04159, 3, (2010)."},{"key":"24576_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, T. et al. Yolo-world: Real-time open-vocabulary object detection, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 16901\u201316911 (2024).","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"24576_CR8","doi-asserted-by":"publisher","unstructured":"Hendry, Chen R C .Automatic License Plate Recognition Via Sliding-Window Darknet-Yolo Deep Learning[J]. Image and Vision Computing, 87, 47\u201356.https:\/\/doi.org\/10.1016\/j.imavis.2019.04.007  (2019).","DOI":"10.1016\/j.imavis.2019.04.007"},{"key":"24576_CR9","doi-asserted-by":"publisher","unstructured":"Wang, C. Y. et al. CSPNet: A new backbone that can enhance learning capability of CNN. (2019). https:\/\/doi.org\/10.48550\/arXiv.1911.11929","DOI":"10.48550\/arXiv.1911.11929"},{"key":"24576_CR10","doi-asserted-by":"publisher","unstructured":"Ding, X. et al. RepVGG: making VGG-style ConvNets great Again. (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01352","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"24576_CR11","doi-asserted-by":"publisher","unstructured":"Xiong, Y. et al. EfficientSAM: leveraged masked image pretraining for efficient segment Anything. (IEEE, 2023). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01525","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"24576_CR12","unstructured":"Li C, Li L, Jiang H, et al. YOLOv6: A single-stage object detection framework for industrial applications[J]. arXiv preprint arXiv:2209.02976, (2022)."},{"key":"24576_CR13","doi-asserted-by":"publisher","unstructured":"Wang, C. Y., Bochkovskiy, A. & Liao, H. Y. M. .YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors.arXiv e-prints, (2022). https:\/\/doi.org\/10.48550\/arXiv.2207.02696","DOI":"10.48550\/arXiv.2207.02696"},{"key":"24576_CR14","unstructured":"Glenn Jocher, A., Chaurasia, Jing & Qiu Ultralytics yolov8. (2023). https:\/\/github.com\/ultralytics\/ultralytics,"},{"key":"24576_CR15","doi-asserted-by":"crossref","unstructured":"Wang, C., Yao, I. H., Yeh & Mark Liao, H. Y. YOLOv9: Learning What You Want toLearn Using Programmable Gradient Information. European Conference on Computer Vision (Springer, Cham, 2025).","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"24576_CR16","doi-asserted-by":"publisher","unstructured":"Radford, A. et al. Learning transferable visual models from natural Language Supervision. (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.00020","DOI":"10.48550\/arXiv.2103.00020"},{"key":"24576_CR17","doi-asserted-by":"crossref","unstructured":"Zareian, A. et al. Open-vocabulary object detection using captions. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 14393\u201314402. (2021).","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"24576_CR18","unstructured":"Gu X, Lin T Y, Kuo W, et al. Open-vocabulary object detection via vision and language knowledge distillation[J]. arXiv preprint arXiv:2104.13921, (2021)."},{"key":"24576_CR19","unstructured":"Kuo W, Cui Y, Gu X, et al. F-vlm: Open-vocabulary object detection upon frozen vision and language models[J]. arXiv preprint arXiv:2209.15639, (2022)."},{"key":"24576_CR20","doi-asserted-by":"crossref","unstructured":"Wang, M. et al. ESAM-CD: Fine-Tuned EfficientSAM Network with LoRA for Weakly Supervised Remote Sensing Image Change Detection (IEEE Transactions on Geoscience and Remote Sensing, 2024).","DOI":"10.1109\/TGRS.2024.3470808"},{"key":"24576_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Cai, H. & Han, S. Efficientvit-sam: Accelerated segment anything model without performance loss. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 7859\u20137863. (2024).","DOI":"10.1109\/CVPRW63382.2024.00782"},{"key":"24576_CR22","doi-asserted-by":"publisher","unstructured":"Chen, Z. et al. Recursive generalization transformer for image Super-Resolution.ArXiv, 2023, https:\/\/doi.org\/10.48550\/arXiv.2303.06373","DOI":"10.48550\/arXiv.2303.06373"},{"key":"24576_CR23","doi-asserted-by":"publisher","unstructured":"Yan, L. et al. LS-MambaNet: integrating large strip Convolution and Mamba network for remote sensing object. Detection Remote Sens. 17 (10). https:\/\/doi.org\/10.3390\/rs17101721 (2025).","DOI":"10.3390\/rs17101721"},{"key":"24576_CR24","doi-asserted-by":"publisher","unstructured":"Yan, L. et al. An intelligent weighted object detector for feature extraction to enrich global image Information. Applied sciences, 12(15), 2076\u20133417 (2022). https:\/\/doi.org\/10.3390\/app12157825","DOI":"10.3390\/app12157825"},{"key":"24576_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T. Y. et al. Microsoft coco: Common objects in context, in Computer Vision\u2013ECCV : 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13. 740\u2013755. (Springer, 2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"24576_CR26","doi-asserted-by":"crossref","unstructured":"Kamath, A. et al. Mdetr-modulated detection for end-to-end multi-modal understanding, in Proceedings of the IEEE\/CVF international conference on computer vision, 1780\u20131790. (2021).","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"24576_CR27","doi-asserted-by":"crossref","unstructured":"Li, L. H. et al. Grounded language-image pre-training, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10965\u201310975. (2022).","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"24576_CR28","doi-asserted-by":"crossref","unstructured":"Liu S, Zeng Z, Ren T, et al. Grounding dino: Marrying dino with grounded pre-training for open-set object detection[C]\/\/European conference on computer vision. Cham: Springer Nature Switzerland, 38\u201355 (2024).","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"24576_CR29","first-page":"9125","volume":"35","author":"L Yao","year":"2022","unstructured":"Yao, L. et al. Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection. Adv. Neural. Inf. Process. Syst. 35, 9125\u20139138 (2022).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24576_CR30","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1016\/j.procs.2022.01.135","volume":"199","author":"Peiyuan Jiang","year":"2022","unstructured":"Peiyuan, Jiang Daji, Ergu Fangyao, Liu Ying, Cai Bo, Ma (2022) A Review of Yolo Algorithm Developments Procedia Computer Science 1991066-1073 10.1016\/j.procs.2022.01.135","journal-title":"Procedia Computer Science"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24576-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24576-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24576-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T12:29:10Z","timestamp":1763555350000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-24576-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,19]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["24576"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-24576-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,19]]},"assertion":[{"value":"20 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 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":"40854"}}