{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T07:45:45Z","timestamp":1793173545491,"version":"4.5.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T00:00:00Z","timestamp":1684972800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T00:00:00Z","timestamp":1684972800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Hebei Province important research project","award":["22370301D"],"award-info":[{"award-number":["22370301D"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00371-023-02886-y","type":"journal-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T05:02:42Z","timestamp":1684990962000},"page":"1787-1803","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":118,"title":["SCA-YOLO: a new small object detection model for UAV images"],"prefix":"10.1007","volume":"40","author":[{"given":"Shuang","family":"Zeng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyan","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,25]]},"reference":[{"issue":"08","key":"2886_CR1","doi-asserted-by":"publisher","first-page":"2250147","DOI":"10.1142\/S021812662250147X","volume":"31","author":"B Jiang","year":"2022","unstructured":"Jiang, B., Qu, R., Li, Y., Li, C.: VC-YOLO: towards real-time object detection in aerial images. J. Circuits Syst. Comput. 31(08), 2250147 (2022)","journal-title":"J. Circuits Syst. Comput."},{"key":"2886_CR2","unstructured":"Chandana, R., Ramachandra, A.: Real time object detection system with YOLO and CNN models: a review (2022)"},{"issue":"2","key":"2886_CR3","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/s00371-020-02033-x","volume":"38","author":"F An","year":"2022","unstructured":"An, F., Liu, J., Bai, L.: Object recognition algorithm based on optimized nonlinear activation function-global convolutional neural network. Vis. Comput. 38(2), 541\u2013553 (2022)","journal-title":"Vis. Comput."},{"issue":"8","key":"2886_CR4","doi-asserted-by":"publisher","first-page":"2939","DOI":"10.1007\/s00371-021-02166-7","volume":"38","author":"K Bayoudh","year":"2022","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis. Comput. 38(8), 2939\u20132970 (2022)","journal-title":"Vis. Comput."},{"key":"2886_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-022-02758-x","author":"H Yang","year":"2023","unstructured":"Yang, H., Zhang, Y.: A context- and level-aware feature pyramid network for object detection with attention mechanism. Vis Comput (2023). https:\/\/doi.org\/10.1007\/s00371-022-02758-x","journal-title":"Vis Comput"},{"key":"2886_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02357-2","author":"T Zhang","year":"2022","unstructured":"Zhang, T., Li, Z., Sun, Z., Zhu, L.: A fully convolutional anchor-free object detector. Vis Comput (2022). https:\/\/doi.org\/10.1007\/s00371-021-02357-2","journal-title":"Vis Comput"},{"key":"2886_CR7","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"2886_CR8","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"2886_CR9","unstructured":"Redmon, J., Farhadi, A., Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"2886_CR10","unstructured":"Bochkovskiy, A., Wang, C., Liao, H., Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"2886_CR11","doi-asserted-by":"crossref","unstructured":"Wei, L., Dragomir, A., Dumitru, E., Christian, S., Scott, R., Yang, F., and etc, SSD: Single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2886_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T., Goyal, P., Girshick, R., He, K., and Dollar, 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":"2886_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE international conference on computer vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"2886_CR14","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"2886_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., and 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":"2886_CR16","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S.: End-to-end object detection with transformers. In: European conference on computer vision, Springer, Cham, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2886_CR17","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Wei, Z., et al.: Sparse R-CNN: end-to-end object detection with learnable proposals. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"2886_CR18","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: ICLR (2020)"},{"key":"2886_CR19","unstructured":"Cui, Y., Yang, L., Liu, D.: Dynamic proposals for efficient object detection. arXiv preprint arXiv:2207.05252 (2022)"},{"key":"2886_CR20","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"2886_CR21","unstructured":"Fu, C., Liu, W., Ranga, A., Tyagi, A., and Berg, A.: DSSD: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)"},{"key":"2886_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104197","volume":"111","author":"G Liu","year":"2021","unstructured":"Liu, G., Han, J., Rong, W.: Feedback-driven loss function for small object detection. Image Vis. Comput. 111, 104197 (2021)","journal-title":"Image Vis. Comput."},{"key":"2886_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhang, H., Lu, X., and Han, X.: Anchor-free small object detection algorithm based on multi-scale feature fusion. In: 2022 5th international conference on pattern recognition and artificial intelligence (PRAI). IEEE, pp. 370\u2013374 (2022)","DOI":"10.1109\/PRAI55851.2022.9904251"},{"issue":"11","key":"2886_CR24","doi-asserted-by":"publisher","first-page":"4241","DOI":"10.1080\/01431161.2021.1892858","volume":"42","author":"L Shi","year":"2021","unstructured":"Shi, L., Tang, Z., Wang, T., Xu, X., Liu, J., Zhang, J.: Aircraft detection in remote sensing images based on deconvolution and position attention. Int. J. Remote Sens. 42(11), 4241\u20134260 (2021)","journal-title":"Int. J. Remote Sens."},{"issue":"15","key":"2886_CR25","doi-asserted-by":"publisher","first-page":"5764","DOI":"10.1080\/01431161.2021.1931537","volume":"42","author":"X Zhao","year":"2021","unstructured":"Zhao, X., Zhang, J., Tian, J., Zhuo, L., Zhang, J.: Multiscale object detection in high-resolution remote sensing images via rotation invariant deep features driven by channel attention. Int. J. Remote Sens. 42(15), 5764\u20135783 (2021)","journal-title":"Int. J. Remote Sens."},{"key":"2886_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, H., Hong, X., and Zhou, Q.: Small object detection based on modified FSSD and model compression. (2021)","DOI":"10.1109\/ICSIP52628.2021.9688896"},{"key":"2886_CR27","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yan, L., Cao, Z., and Liu, D.: Tf-blender: temporal feature blender for video object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 8138\u20138147 (2021)","DOI":"10.1109\/ICCV48922.2021.00803"},{"key":"2886_CR28","doi-asserted-by":"crossref","unstructured":"Liu, D., Cui, Y., Tan, W., and Chen, Y.: Sg-net: spatial granularity network for one-stage video instance segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9816\u20139825 (2021)","DOI":"10.1109\/CVPR46437.2021.00969"},{"key":"2886_CR29","doi-asserted-by":"crossref","unstructured":"Yan, L., Wang, Q., Cui, Y., Feng, F., Quan, X., Zhang, X., et al.: Gl-rg: global-local representation granularity for video captioning. arXiv preprint arXiv:2205.10706 (2022)","DOI":"10.24963\/ijcai.2022\/384"},{"key":"2886_CR30","doi-asserted-by":"crossref","unstructured":"Wang, C. Y., Liao, H., Wu, Y., Chen, P., Hsieh, J., and Yeh, I.: 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, pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"2886_CR31","doi-asserted-by":"crossref","unstructured":"He, K. M., Zhang, X., Ren, S., and 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":"2886_CR32","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Dollar, 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, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"2886_CR33","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Laurens, V., and Weinberger, K.: Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"2886_CR34","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., and 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"},{"key":"2886_CR35","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T., Le, Q.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"2886_CR36","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"issue":"1","key":"2886_CR37","doi-asserted-by":"publisher","first-page":"132","DOI":"10.3390\/rs10010132","volume":"10","author":"X Yang","year":"2018","unstructured":"Yang, X., Sun, H., Fu, K., Yang, J., Sun, X., Yan, M., Guo, Z.: Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sensing 10(1), 132 (2018)","journal-title":"Remote Sensing"},{"issue":"2","key":"2886_CR38","doi-asserted-by":"publisher","first-page":"420","DOI":"10.3390\/rs14020420","volume":"14","author":"G Qi","year":"2022","unstructured":"Qi, G., Zhang, Y., Wang, K., Mazur, N., Liu, Y., Malaviya, D.: Small object detection method based on adaptive spatial parallel convolution and fast multi-scale fusion. Remote Sensing 14(2), 420 (2022)","journal-title":"Remote Sensing"},{"issue":"1","key":"2886_CR39","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1109\/TCSVT.2021.3056725","volume":"32","author":"J Liu","year":"2021","unstructured":"Liu, J., Fan, X., Jiang, J., Liu, R., Luo, Z.: Learning a deep multi-scale feature ensemble and edge-attention guidance for image fusion. IEEE Trans. Circuits Syst. Video Technol. 32(1), 105\u2013119 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2886_CR40","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":"2886_CR41","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J. Lee, J., and Kweon, I.: CBAM: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2886_CR42","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"2886_CR43","unstructured":"Yang, L., Zhang, R., Li, L., and Xie, X.: SimAM: a simple, parameter-free attention module for convolutional neural networks. In: International conference on machine learning. PMLR, pp. 11863\u201311874 (2021)"},{"issue":"4","key":"2886_CR44","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1080\/01431161.2022.2038396","volume":"43","author":"K Wang","year":"2022","unstructured":"Wang, K., Wei, Z.: YOLO V4 with hybrid dilated convolution attention module for object detection in the aerial dataset. Int. J. Remote Sens. 43(4), 1323\u20131344 (2022)","journal-title":"Int. J. Remote Sens."},{"issue":"5","key":"2886_CR45","doi-asserted-by":"publisher","first-page":"2068","DOI":"10.3390\/s22052068","volume":"22","author":"K Gromada","year":"2022","unstructured":"Gromada, K., Siemiatkowska, B., Stecz, W., Plochocki, K., Wozniak, K.: Real-time object detection and classification by UAV equipped with SAR. Sensors 22(5), 2068 (2022)","journal-title":"Sensors"},{"key":"2886_CR46","doi-asserted-by":"crossref","unstructured":"Mozaffari, M., Li, Y., and Ko, Y.: Detecting flashover in a room fire based on the sequence of thermal infrared images using convolutional neural networks. In: Proceedings of the Canadian conference on artificial intelligence (2022)","DOI":"10.21428\/594757db.7c1cd4e1"},{"key":"2886_CR47","doi-asserted-by":"crossref","unstructured":"Yu, W., Yang, T., Chen, C.: Towards resolving the challenge of long-tail distribution in UAV images for object detection. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 3258\u20133267 (2021)","DOI":"10.1109\/WACV48630.2021.00330"},{"key":"2886_CR48","doi-asserted-by":"crossref","unstructured":"Albaba, B., Ozer, S.: SyNet: an ensemble network for object detection in UAV images. In: 2020 25th international conference on pattern recognition (ICPR), IEEE, pp. 10227\u201310234 (2021)","DOI":"10.1109\/ICPR48806.2021.9412847"},{"key":"2886_CR49","doi-asserted-by":"crossref","unstructured":"Ali, S., Siddique, A., Ates, H., and Gunturk, B.: Improved YOLOv4 for aerial object detection. In: 2021 29th signal processing and communications applications conference (SIU). IEEE, pp. 1\u20134 (2021)","DOI":"10.1109\/SIU53274.2021.9478027"},{"key":"2886_CR50","doi-asserted-by":"crossref","unstructured":"Cao, Y., He, Z., Wang, L., Wang, W., Yuan, Y., Zhang, D., et al.: VisDrone-DET2021: the vision meets drone object detection challenge results. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 2847\u20132854 (2021)","DOI":"10.1109\/ICCVW54120.2021.00319"},{"key":"2886_CR51","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., et al.: VisDrone-DET2019: the vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops (ICCVW). Seoul: IEEE Press, pp. 213\u2013226 (2019)"},{"issue":"7","key":"2886_CR52","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.3390\/s20071861","volume":"20","author":"H Zhao","year":"2020","unstructured":"Zhao, H., Zhou, Y., Zhang, L., Peng, Y., Hu, X., Peng, H., et al.: Mixed YOLOv3-LITE: a lightweight real-time object detection method. Sensors 20(7), 1861 (2020)","journal-title":"Sensors"},{"issue":"12","key":"2886_CR53","doi-asserted-by":"publisher","first-page":"326738","DOI":"10.7527\/S1000-6893.2021.326738","volume":"43","author":"GT Mao","year":"2022","unstructured":"Mao, G.T., Deng, T., Yun, J.: Object detection in UAV images based on multi-scale split attention. Acta Aeronaut. Astronaut. Sin 43(12), 326738 (2022). https:\/\/doi.org\/10.7527\/S1000-6893.2021.326738","journal-title":"Acta Aeronaut. Astronaut. Sin"},{"key":"2886_CR54","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1016\/j.image.2021.116402","volume":"98","author":"Q Yin","year":"2021","unstructured":"Yin, Q., Yang, W., Ran, M., Wang, S.: FD-SSD: an improved SSD object detection algorithm based on feature fusion and dilated convolution. Signal Process. Image Commun. 98, 1164 (2021)","journal-title":"Signal Process. Image Commun."},{"key":"2886_CR55","doi-asserted-by":"crossref","unstructured":"Qu, Z., Shang, X., Xia, S., Yi, T., and Zhou, D.: A method of single-shot target detection with multi-scale feature fusion and feature enhancement. IET Image Process. 16 (2022)","DOI":"10.1049\/ipr2.12445"},{"issue":"9","key":"2886_CR56","doi-asserted-by":"publisher","first-page":"3280","DOI":"10.1080\/01431161.2022.2089539","volume":"43","author":"L Zhang","year":"2022","unstructured":"Zhang, L., Wang, L., Jin, M., Geng, X., Shen, Q.: Small object detection in remote sensing images based on attention mechanism and multi-scale feature fusion. Int. J. Remote Sens. 43(9), 3280\u20133297 (2022)","journal-title":"Int. J. Remote Sens."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02886-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02886-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02886-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,18]],"date-time":"2024-02-18T18:30:17Z","timestamp":1708281017000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02886-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,25]]},"references-count":56,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["2886"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02886-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,25]]},"assertion":[{"value":"23 April 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}