{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T08:30:55Z","timestamp":1758702655059,"version":"3.44.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T00:00:00Z","timestamp":1748476800000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-03933-6","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T10:38:09Z","timestamp":1748515089000},"page":"9395-9408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MPA-Det: multi-path aggregation-based object detection framework for aerial visual computing"],"prefix":"10.1007","volume":"41","author":[{"given":"Yaolin","family":"Lei","sequence":"first","affiliation":[]},{"given":"Kai","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Zifeng","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Yiming","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Huihui","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Wenzhi","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,29]]},"reference":[{"issue":"11","key":"3933_CR1","doi-asserted-by":"publisher","first-page":"14426","DOI":"10.1007\/s10489-022-04108-9","volume":"53","author":"Z Xiong","year":"2023","unstructured":"Xiong, Z., Song, T., He, S., Yao, Z., Wu, X.: A unified and costless approach for improving small and long-tail object detection in aerial images of traffic scenarios. Appl. Intell. 53(11), 14426\u201314447 (2023)","journal-title":"Appl. Intell."},{"key":"3933_CR2","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.1007\/s10489-020-01882-2","volume":"51","author":"X Dai","year":"2021","unstructured":"Dai, X., Yuan, X., Wei, X.: Tirnet: object detection in thermal infrared images for autonomous driving. Appl. Intell. 51, 1244\u20131261 (2021)","journal-title":"Appl. Intell."},{"key":"3933_CR3","first-page":"1","volume":"8","author":"W Sun","year":"2021","unstructured":"Sun, W., Dai, L., Zhang, X., Chang, P., He, X.: Rsod: real-time small object detection algorithm in uav-based traffic monitoring. Appl. Intell. 8, 1\u201316 (2021)","journal-title":"Appl. Intell."},{"key":"3933_CR4","first-page":"1","volume":"7","author":"G Tian","year":"2022","unstructured":"Tian, G., Liu, J., Zhao, H., Yang, W.: Small object detection via dual inspection mechanism for uav visual images. Appl. Intell. 7, 1\u201314 (2022)","journal-title":"Appl. Intell."},{"issue":"2","key":"3933_CR5","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MGRS.2016.2540798","volume":"4","author":"L Zhang","year":"2016","unstructured":"Zhang, L., Zhang, L., Du, B.: Deep learning for remote sensing data: a technical tutorial on the state of the art. IEEE Geosci. Remote Sens. Mag. 4(2), 22\u201340 (2016)","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"3933_CR6","first-page":"473","volume":"3","author":"D Marmanis","year":"2016","unstructured":"Marmanis, D., Wegner, J.D., Galliani, S., Schindler, K., Datcu, M., Stilla, U.: Semantic segmentation of aerial images with an ensemble of cnns. ISPRS Ann. Photogram. Remote Sens. Spat. Inf. Sci. 3, 473\u2013480 (2016)","journal-title":"ISPRS Ann. Photogram. Remote Sens. Spat. Inf. Sci."},{"issue":"1","key":"3933_CR7","doi-asserted-by":"publisher","first-page":"139","DOI":"10.3390\/rs10010139","volume":"10","author":"Z Chen","year":"2018","unstructured":"Chen, Z., Zhang, T., Ouyang, C.: End-to-end airplane detection using transfer learning in remote sensing images. Remote Sens. 10(1), 139 (2018)","journal-title":"Remote Sens."},{"issue":"11","key":"3933_CR8","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.3390\/rs11111382","volume":"11","author":"D Peng","year":"2019","unstructured":"Peng, D., Zhang, Y., Guan, H.: End-to-end change detection for high resolution satellite images using improved unet++. Remote Sens. 11(11), 1382 (2019)","journal-title":"Remote Sens."},{"issue":"91\u2013110","key":"3933_CR9","first-page":"2","volume":"2","author":"G Lowe","year":"2004","unstructured":"Lowe, G.: Sift-the scale invariant feature transform. Int. J. 2(91\u2013110), 2 (2004)","journal-title":"Int. J."},{"key":"3933_CR10","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., Van\u00a0Gool, L.: Surf: speeded up robust features. In: Computer Vision\u2013ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7\u201313, 2006. Proceedings, Part I 9, pp. 404\u2013417. Springer (2006)","DOI":"10.1007\/11744023_32"},{"issue":"11","key":"3933_CR11","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"3933_CR12","first-page":"56","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 56 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3933_CR13","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"3933_CR14","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. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3933_CR15","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3933_CR16","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"3933_CR17","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. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3933_CR18","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"issue":"8","key":"3933_CR19","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.3390\/s21082799","volume":"21","author":"K Roy","year":"2021","unstructured":"Roy, K., Hasan, M., Rupty, L., Hossain, M.S., Sengupta, S., Taus, S.N., Mohammed, N.: Bi-fpnfas: Bi-directional feature pyramid network for pixel-wise face anti-spoofing by leveraging Fourier spectra. Sensors 21(8), 2799 (2021)","journal-title":"Sensors"},{"key":"3933_CR20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81","volume-title":"Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation","author":"R Girshick","year":"2014","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. IEEE Computer Society (2014)"},{"key":"3933_CR21","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. Computer Science (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"3933_CR22","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3933_CR23","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Computer Vision & Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3933_CR24","unstructured":"Berg, A.C., Fu, C.Y., Szegedy, C., Anguelov, D., Erhan, D., Reed, S., Liu, W.: SSD: single shot multibox detector (2015)"},{"key":"3933_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3933_CR26","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Li, L., Yuan, Z., Wang, C.: Sparse r-cnn: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"3933_CR27","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"3933_CR28","first-page":"1","volume":"8","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Yang, D., Song, T., Ye, Y., Zhang, X.: Yolo-ssp: an object detection model based on pyramid spatial attention and improved downsampling strategy for remote sensing images. Vis. Comput. 8, 1\u201318 (2024)","journal-title":"Vis. Comput."},{"key":"3933_CR29","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: Panet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9197\u20139206 (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"3933_CR30","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra r-cnn: towards balanced learning for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 821\u2013830 (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"issue":"8","key":"3933_CR31","doi-asserted-by":"publisher","first-page":"5772","DOI":"10.1109\/TGRS.2020.2969979","volume":"58","author":"H Guo","year":"2020","unstructured":"Guo, H., Yang, X., Wang, N., Song, B., Gao, X.: A rotational libra r-cnn method for ship detection. IEEE Trans. Geosci. Remote Sens. 58(8), 5772\u20135781 (2020)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3933_CR32","first-page":"1","volume":"60","author":"X Yang","year":"2022","unstructured":"Yang, X., Zhang, J., Chen, C., Yang, D.: An efficient and lightweight cnn model with soft quantification for ship detection in sar images. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"3933_CR33","first-page":"1","volume":"62","author":"X Yang","year":"2023","unstructured":"Yang, X., Zhang, S., Duan, S., Yang, W.: An effective and lightweight hybrid network for object detection in remote sensing images. IEEE Trans. Geosci. Remote Sens. 62, 1\u201311 (2023)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"10","key":"3933_CR34","doi-asserted-by":"publisher","first-page":"11725","DOI":"10.1007\/s10489-021-02955-6","volume":"52","author":"K Ren","year":"2022","unstructured":"Ren, K., Gao, Y., Wan, M., Gu, G., Chen, Q.: Infrared small target detection via region super resolution generative adversarial network. Appl. Intell. 52(10), 11725\u201311737 (2022)","journal-title":"Appl. Intell."},{"key":"3933_CR35","first-page":"1","volume":"7","author":"Z Li","year":"2024","unstructured":"Li, Z., He, Q., Yang, W.: E-fpn: an enhanced feature pyramid network for uav scenarios detection. Vis. Comput. 7, 1\u201319 (2024)","journal-title":"Vis. Comput."},{"key":"3933_CR36","first-page":"1","volume":"7","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Yang, D., Song, T., Ye, Y., Zhang, X.: Yolo-ssp: an object detection model based on pyramid spatial attention and improved downsampling strategy for remote sensing images. Vis. Comput. 7, 1\u201318 (2024)","journal-title":"Vis. Comput."},{"key":"3933_CR37","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"3933_CR38","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"3933_CR39","unstructured":"Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, pp. 315\u2013323 (2011)"},{"key":"3933_CR40","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., Peng, T., Zheng, J., Wang, X., Zhang, Y.: Visdrone-det2019: the vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 0\u20130 (2019)"},{"key":"3933_CR41","unstructured":"Airbus: Airbus Ship Detection Challenge (2019). Available: https:\/\/www.kaggle.com\/c\/airbus-ship-detection"},{"key":"3933_CR42","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"3933_CR43","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03933-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03933-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03933-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:36:47Z","timestamp":1757929007000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03933-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,29]]},"references-count":43,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["3933"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03933-6","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2025,5,29]]},"assertion":[{"value":"21 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Data collection must comply with all relevant local, national, and international laws, regulations, and ethical guidelines. For the data used in this research, informed consent was obtained from all participating individuals or entities. No personally identifiable information was included in the dataset used for this research. We are committed to adhering to the highest ethical standards and ensuring the protection of the rights and privacy of our participants.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}]}}