{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T20:32:41Z","timestamp":1793046761207,"version":"4.5.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072002, 62172004, and 62273001"],"award-info":[{"award-number":["62072002, 62172004, and 62273001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11760-025-03850-0","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T19:38:34Z","timestamp":1739907514000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Small object detection in UAV imagery based on channel-spatial fusion cross attention"],"prefix":"10.1007","volume":"19","author":[{"given":"JianLong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhou","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,18]]},"reference":[{"issue":"16","key":"3850_CR1","doi-asserted-by":"crossref","first-page":"7966","DOI":"10.3390\/app12167966","volume":"12","author":"O Kainz","year":"2022","unstructured":"Kainz, O., Dopiriak, M., Michalko, M., Jakab, F., Nov\u00e1kov\u00e1, I.: Traffic monitoring from the perspective of an unmanned aerial vehicle. Appl. Sci. 12(16), 7966 (2022)","journal-title":"Appl. Sci."},{"key":"3850_CR2","doi-asserted-by":"crossref","unstructured":"Abdelfattah, R., Wang, X., Wang, S.: Ttpla: An aerial-image dataset for detection and segmentation of transmission towers and power lines. In: Proceedings of the Asian conference on computer vision (2020)","DOI":"10.1007\/978-3-030-69544-6_36"},{"key":"3850_CR3","doi-asserted-by":"crossref","unstructured":"Xue, Y., Jin, G., Shen, T., Tan, L., Wang, N., Gao, J., Wang, L.: Smalltrack: Wavelet pooling and graphenhanced classification for UAV small object tracking. IEEE Trans. Geosci. Remote Sens. 61, 1\u201315 (2023)","DOI":"10.1109\/TGRS.2023.3305728"},{"issue":"9","key":"3850_CR4","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.cja.2023.03.048","volume":"36","author":"Y Xue","year":"2023","unstructured":"Xue, Y., Jin, G., Shen, T., Tan, L., Wang, L.: Template-guided frequency attention and adaptive cross-entropy loss for UAV visual tracking. Chin. J. Aeronautics 36(9), 299\u2013312 (2023)","journal-title":"Chin. J. Aeronautics"},{"issue":"12","key":"3850_CR5","doi-asserted-by":"crossref","first-page":"3300","DOI":"10.1049\/ipr2.12565","volume":"16","author":"Y Xue","year":"2022","unstructured":"Xue, Y., Jin, G., Shen, T., Tan, L., Yang, J., Hou, X.: Mobiletrack: Siamese efficient mobile network for high-speed UAV tracking. IET Image Process. 16(12), 3300\u20133313 (2022)","journal-title":"IET Image Process."},{"key":"3850_CR6","doi-asserted-by":"crossref","unstructured":"Xue, Y., Jin, G., Shen, T., Tan, L., Wang, N., Gao, J., Wang, L.: Consistent representation mining for multi-drone single object tracking. IEEE Trans. Circuits Syst. Video Technol. 34(11), 10845\u201310859 (2024)","DOI":"10.1109\/TCSVT.2024.3411301"},{"key":"3850_CR7","first-page":"1","volume":"73","author":"Y Xue","year":"2024","unstructured":"Xue, Y., Shen, T., Jin, G., Tan, L., Wang, N., Wang, L., Gao, J.: Handling occlusion in UAV visual tracking with query-guided redetection. IEEE Trans. Instrum. Meas. 73, 1\u201317 (2024)","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"3850_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. 2117\u20132125, (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"3850_CR9","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105057","volume":"147","author":"M Kang","year":"2024","unstructured":"Kang, M., Ting, C.-M., Ting, F.F., Phan, R.C.-W.: Asf-yolo: A novel yolo model with attentional scale sequence fusion for cell instance segmentation. Image Vis. Comput. 147, 105057 (2024)","journal-title":"Image Vis. Comput."},{"key":"3850_CR10","doi-asserted-by":"crossref","unstructured":"Lim, J.-S., Astrid, M., Yoon, H.-J., Lee, S.-I.: Small object detection using context and attention. In: 2021 International conference on artificial intelligence in information and communication (ICAIIC), pp. 181\u2013186. IEEE, (2021)","DOI":"10.1109\/ICAIIC51459.2021.9415217"},{"key":"3850_CR11","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: Eca-net: Efficient channel attention for deep convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11534\u201311542, (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"3850_CR12","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":"3850_CR13","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":"3850_CR14","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: 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":"3850_CR15","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. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops, pp. 0\u20130, (2019)"},{"key":"3850_CR16","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1007\/s11263-019-01266-1","volume":"128","author":"H Yu","year":"2020","unstructured":"Yu, H., Li, G., Zhang, W., Huang, Q., Du, D., Tian, Q., Sebe, N.: The unmanned aerial vehicle benchmark: Object detection, tracking and baseline. Int. J. Comput. Vis. 128, 1141\u20131159 (2020)","journal-title":"Int. J. Comput. Vis."},{"issue":"6","key":"3850_CR17","doi-asserted-by":"crossref","first-page":"1758","DOI":"10.1109\/TCSVT.2019.2905881","volume":"30","author":"X Liang","year":"2019","unstructured":"Liang, X., Zhang, J., Zhuo, L., Li, Y., Tian, Q.: Small object detection in unmanned aerial vehicle images using feature fusion and scaling-based single shot detector with spatial context analysis. IEEE Trans. Circuits Syst. Video Technol. 30(6), 1758\u20131770 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3850_CR18","doi-asserted-by":"crossref","unstructured":"Pawar, N., Waghmare, A., Pratap, A., Thorat, A., Ghogale, K.N., Karamtoth, S.N.R., Shaikh, N.F.: Miniscule object detection in aerial images using yolor: a review. In: Proceedings of International conference on communication and computational technologies: ICCCT 2022, pp. 697\u2013708. Springer, (2022)","DOI":"10.1007\/978-981-19-3951-8_52"},{"key":"3850_CR19","doi-asserted-by":"crossref","unstructured":"Hong, S., Kang, S., Cho, D.: Patch-level augmentation for object detection in aerial images. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops, pp. 0\u20130, (2019)","DOI":"10.1109\/ICCVW.2019.00021"},{"key":"3850_CR20","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108998","volume":"133","author":"B Bosquet","year":"2023","unstructured":"Bosquet, B., Cores, D., Seidenari, L., Brea, V.M., Mucientes, M., Del Bimbo, A.: A full data augmentation pipeline for small object detection based on generative adversarial networks. Pattern Recognit. 133, 108998 (2023)","journal-title":"Pattern Recognit."},{"key":"3850_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chen, J., Huang, D.: Ufpmp-det: Toward accurate and efficient object detection on drone imagery. In: Proceedings of the AAAI conference on artificial intelligence, vol. 36, pp. 1026\u20131033, (2022)","DOI":"10.1609\/aaai.v36i1.19986"},{"key":"3850_CR22","volume":"119","author":"A Amudhan","year":"2022","unstructured":"Amudhan, A., Sudheer, A.: Lightweight and computationally faster hypermetropic convolutional neural network for small size object detection. Image Vis. Comput. 119, 104396 (2022)","journal-title":"Image Vis. Comput."},{"key":"3850_CR23","first-page":"1","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":"3850_CR24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2020.3011973","volume":"19","author":"M Hong","year":"2021","unstructured":"Hong, M., Li, S., Yang, Y., Zhu, F., Zhao, Q., Lu, L.: Sspnet: Scale selection pyramid network for tiny person detection from UAV images. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2021)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"3850_CR25","unstructured":"Xu, J., Li, Y., Wang, S.: Adazoom: Adaptive zoom network for multi-scale object detection in large scenes. arXiv preprint arXiv:2106.10409 (2021)"},{"issue":"3","key":"3850_CR26","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.1109\/TCSVT.2022.3210207","volume":"33","author":"J Leng","year":"2022","unstructured":"Leng, J., Mo, M., Zhou, Y., Gao, C., Li, W., Gao, X.: Pareto refocusing for drone-view object detection. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1320\u20131334 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3850_CR27","doi-asserted-by":"crossref","unstructured":"Yang, X., Yang, J., Yan, J., Zhang, Y., Zhang, T., Guo, Z., Xian, S., Fu, K.S.: Towards more robust detection for small, cluttered and rotated objects. arxiv 2018. arXiv preprint arXiv:1811.07126","DOI":"10.1109\/ICCV.2019.00832"},{"key":"3850_CR28","doi-asserted-by":"crossref","first-page":"92791","DOI":"10.1109\/ACCESS.2020.2994379","volume":"8","author":"M Zhang","year":"2020","unstructured":"Zhang, M., Zhang, B., Liu, M., Xin, M.: Robust object detection in aerial imagery based on multi-scale detector and soft densely connected. IEEE Access 8, 92791\u201392801 (2020)","journal-title":"IEEE Access"},{"issue":"9","key":"3850_CR29","doi-asserted-by":"crossref","first-page":"3456","DOI":"10.1109\/TCSVT.2020.3038649","volume":"31","author":"J Nie","year":"2020","unstructured":"Nie, J., Pang, Y., Zhao, S., Han, J., Li, X.: Efficient selective context network for accurate object detection. IEEE Trans. Circuits Syst. Video Technol. 31(9), 3456\u20133468 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3850_CR30","doi-asserted-by":"crossref","first-page":"4341","DOI":"10.1109\/TIP.2023.3297408","volume":"32","author":"Y Quan","year":"2023","unstructured":"Quan, Y., Zhang, D., Zhang, L., Tang, J.: Centralized feature pyramid for object detection. IEEE Trans. Image Process. 32, 4341\u20134354 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"3850_CR31","doi-asserted-by":"crossref","unstructured":"Singh, B., Davis, L.S.: An analysis of scale invariance in object detection snip. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3578\u20133587, (2018)","DOI":"10.1109\/CVPR.2018.00377"},{"key":"3850_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 7794\u20137803, (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"3850_CR33","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp. 3146\u20133154, (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"3850_CR34","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops, pp. 0\u20130, (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"3850_CR35","unstructured":"Xia, B.N., Gong, Y., Zhang, Y., Poellabauer, C.: Second-order non-local attention networks for person re-identification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 3760\u20133769, (2019)"},{"key":"3850_CR36","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 510\u2013519, (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"3850_CR37","unstructured":"Liu, Y., Shao, Z., Hoffmann, N.: Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv:2112.05561 (2021)"},{"issue":"6","key":"3850_CR38","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transac. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Transac. Pattern Anal. Mach. Intell."},{"key":"3850_CR39","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":"3850_CR40","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al.: Yolov6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"3850_CR41","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G.: YOLOv10: Real-time end-to-end object detection https:\/\/arxiv.org\/abs\/2405.14458 (2024)"},{"key":"3850_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9759\u20139768, (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"3850_CR43","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: Tood: Task-aligned one-stage object detection. In: 2021 IEEE\/CVF International conference on computer vision (ICCV), pp. 3490\u20133499. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"3850_CR44","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":"3850_CR45","unstructured":"Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., Chen, K.: Rtmdet: An empirical study of designing real-time object detectors. arxiv 2022. arXiv preprint arXiv:2212.07784"},{"key":"3850_CR46","unstructured":"Ross, T.-Y., Doll\u00e1r, G.: Focal loss for dense object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2980\u20132988, (2017)"},{"key":"3850_CR47","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. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 16965\u201316974, (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"3850_CR48","doi-asserted-by":"crossref","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)","DOI":"10.1109\/TGRS.2024.3363057"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03850-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-03850-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-03850-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T03:21:36Z","timestamp":1743564096000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-03850-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,18]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["3850"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-03850-0","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,18]]},"assertion":[{"value":"8 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 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 no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"302"}}