{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:59:07Z","timestamp":1775325547083,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"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":[[2025,11]]},"DOI":"10.1007\/s11760-025-04512-x","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T07:50:56Z","timestamp":1752652256000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Small target detection model based on swin transformer and multiscale fusion"],"prefix":"10.1007","volume":"19","author":[{"given":"Jinjin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"4512_CR1","doi-asserted-by":"crossref","unstructured":"Xie, X., Cheng, G., Wang, J., Yao, X., Han, J., Oriented R-CNN for object detection, Proceedings of the IEEE\/CVF International Conference on Computer Vision, 3520\u20133529 (2021)","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"4512_CR2","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G., Yolov10: Real-time end-to-end object detection, arXiv preprint arXiv:2405.14458 (2024)"},{"key":"4512_CR3","doi-asserted-by":"crossref","unstructured":"Gong, Y., Yu, X., Ding, Y., Peng, X., Zhao, J., Han, Z., Effective fusion factor in FPN for tiny object detection, Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 1160\u20131168 (2021)","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"4512_CR4","unstructured":"Dong, J., Feng, B., Guessous, D., Liang, Y., He, H., Flex attention: A programming model for generating optimized attention kernels, arXiv preprint arXiv:2412.05496 (2024)"},{"issue":"4","key":"4512_CR5","first-page":"69","volume":"44","author":"A-FO Detector","year":"2022","unstructured":"Detector, A.-F.O.: FCOS: A simple and strong anchor-free object detector. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 69\u201376 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"4512_CR6","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1109\/TETCI.2023.3235381","volume":"7","author":"H Wang","year":"2023","unstructured":"Wang, H., Xu, Y., Wang, Z., Cai, Y., Chen, L., Li, Y.: CenterNet-Auto: A multi-object visual detection algorithm for autonomous driving scenes based on improved CenterNet. IEEE Transactions on Emerging Topics in Computational Intelligence 7(3), 742\u2013752 (2023)","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"4512_CR7","doi-asserted-by":"publisher","first-page":"113539","DOI":"10.1016\/j.knosys.2025.113539","volume":"318","author":"P Shi","year":"2025","unstructured":"Shi, P., Dong, X., Ge, R.: Dp-M3D: Monocular 3D object detection algorithm with depth perception capability. Knowl.-Based Syst. 318, 113539 (2025)","journal-title":"Knowl.-Based Syst."},{"key":"4512_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3510781","volume":"62","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Ye, M., Zhu, G., Liu, Y., Guo, P., Yan, J.: FFCA-YOLO for small object detection in remote sensing images. IEEE Trans. Geosci. Remote Sens. 62, 1\u201315 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"4512_CR9","doi-asserted-by":"publisher","first-page":"122669","DOI":"10.1016\/j.eswa.2023.122669","volume":"241","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Zhang, H., Huang, Q., Han, Y., Zhao, M.: DsP-YOLO: An anchor-free network with DsPAN for small object detection of multiscale defects. Expert Syst. Appl. 241, 122669 (2024)","journal-title":"Expert Syst. Appl."},{"key":"4512_CR10","doi-asserted-by":"publisher","first-page":"127685","DOI":"10.1016\/j.neucom.2024.127685","volume":"588","author":"S Sun","year":"2024","unstructured":"Sun, S., Mo, B., Xu, J., Li, D., Zhao, J., Han, S.: Multi-YOLOv8: An infrared moving small object detection model based on YOLOv8 for air vehicle. Neurocomputing 588, 127685 (2024)","journal-title":"Neurocomputing"},{"key":"4512_CR11","doi-asserted-by":"publisher","first-page":"102147","DOI":"10.1016\/j.inffus.2023.102147","volume":"103","author":"H Li","year":"2024","unstructured":"Li, H., Wu, X.-J.: CrossFuse: A novel cross attention mechanism based infrared and visible image fusion approach. Information Fusion 103, 102147 (2024)","journal-title":"Information Fusion"},{"key":"4512_CR12","doi-asserted-by":"publisher","first-page":"111392","DOI":"10.1016\/j.asoc.2024.111392","volume":"154","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Xia, R., Yang, K., Zou, K.: DNNAM: Image inpainting algorithm via deep neural networks and attention mechanism. Appl. Soft Comput. 154, 111392 (2024)","journal-title":"Appl. Soft Comput."},{"key":"4512_CR13","doi-asserted-by":"publisher","first-page":"121726","DOI":"10.1016\/j.eswa.2023.121726","volume":"238","author":"J Tang","year":"2024","unstructured":"Tang, J., Wang, Z., Zhang, H., Li, H., Wu, P., Zeng, N.: A lightweight surface defect detection framework combined with dual-domain attention mechanism. Expert Syst. Appl. 238, 121726 (2024)","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"4512_CR14","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1177\/03611981241258753","volume":"2679","author":"X Dong","year":"2025","unstructured":"Dong, X., Shi, P., Liang, T.: CTAFFNet: CNN\u2013transformer adaptive feature fusion object detection algorithm for complex traffic scenarios. Transp. Res. Rec. 2679(1), 1947\u20131965 (2025)","journal-title":"Transp. Res. Rec."},{"key":"4512_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102814","volume":"84","author":"X Dong","year":"2024","unstructured":"Dong, X., Shi, P., Qi, H.: TS-BEV: BEV object detection algorithm based on temporal-spatial feature fusion. Displays 84, 102814 (2024)","journal-title":"Displays"},{"key":"4512_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, L., Yuan, B., Du, J., Chen, B., Xie, H., Tian, J., Yuan, Z., MFFSODNet: Multi-scale feature fusion small object detection network for UAV aerial images, IEEE Transactions on Instrumentation and Measurement (2024)","DOI":"10.1109\/TIM.2024.3381272"},{"key":"4512_CR17","first-page":"1","volume":"71","author":"N Zeng","year":"2022","unstructured":"Zeng, N., Wu, P., Wang, Z., Li, H., Liu, W., Liu, X.: A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection. IEEE Trans. Instrum. Meas. 71, 1\u201314 (2022)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"4512_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B., Swin Transformer: Hierarchical vision transformer using shifted windows, Proceedings of the IEEE\/CVF International Conference on Computer Vision, 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"4512_CR19","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V., EfficientDet: Scalable and efficient object detection, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"4512_CR20","doi-asserted-by":"publisher","first-page":"6817","DOI":"10.1109\/JSTARS.2022.3198517","volume":"15","author":"W Wang","year":"2022","unstructured":"Wang, W., Tan, X., Zhang, P., Wang, X.: A CBAM-based multiscale transformer fusion approach for remote sensing image change detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 15, 6817\u20136825 (2022)","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"4512_CR21","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., Peng, T., Zheng, J., Wang, X., Zhang, Y., et al., VisDrone-DET2019: The vision meets drone object detection in image challenge results, Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, 0- 0 (2019)"},{"key":"4512_CR22","doi-asserted-by":"crossref","unstructured":"Song, J., Zhou, M., Luo, J., Pu, H., Feng, Y., Wei, X., Jia, W., Boundary-Aware Feature Fusion with Dual-Stream Attention for Remote Sensing Small Object Detection, IEEE Transactions on Geoscience and Remote Sensing (2024)","DOI":"10.1109\/TGRS.2024.3514376"},{"key":"4512_CR23","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C., SSD: Single Shot MultiBox Detector, European Conference on Computer Vision, 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"4512_CR24","doi-asserted-by":"crossref","unstructured":"Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., Chen, Y., RON: Reverse Connection with Objectness Prior Networks for Object Detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5936\u20135944 (2017)","DOI":"10.1109\/CVPR.2017.557"},{"key":"4512_CR25","doi-asserted-by":"crossref","unstructured":"Yang, F., Fan, H., Chu, P., Blasch, E., Ling, H., Clustered Object Detection in Aerial Images, Proceedings of the IEEE International Conference on Computer Vision, 8311\u20138320 (2019)","DOI":"10.1109\/ICCV.2019.00840"},{"key":"4512_CR26","doi-asserted-by":"crossref","unstructured":"Li, C., Yang, T., Zhu, S., Chen, C., Guan, S., Density Map Guided Object Detection in Aerial Images, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 190\u2013191 (2020)","DOI":"10.1109\/CVPRW50498.2020.00103"},{"key":"4512_CR27","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. Adv. Neural. Inf. Process. Syst. 33, 21002\u201321012 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4512_CR28","doi-asserted-by":"crossref","unstructured":"Duan, C., Wei, Z., Zhang, C., Qu, S., Wang, H., Coarse-grained density map guided object detection in aerial images, Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2789\u20132798 (2021)","DOI":"10.1109\/ICCVW54120.2021.00313"},{"key":"4512_CR29","doi-asserted-by":"crossref","unstructured":"Yang, C., Huang, Z., Wang, N., QueryDet: Cascaded sparse query for accelerating high-resolution small object detection, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 13668\u201313677 (2022)","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"4512_CR30","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.-Y., DINO: DETR with improved denoising anchor boxes for end-to-end object detection, arXiv preprint arXiv:2203.03605 (2022)"},{"key":"4512_CR31","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J., DETRs beat YOLOs on real-time object detection, Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04512-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04512-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04512-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T11:53:44Z","timestamp":1757246024000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04512-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":31,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["4512"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04512-x","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,16]]},"assertion":[{"value":"30 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2025","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}],"article-number":"884"}}