{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:58:45Z","timestamp":1787165925762,"version":"build-2736575974"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T00:00:00Z","timestamp":1776988800000},"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":"crossref","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s11760-026-05222-8","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:24:30Z","timestamp":1777058670000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["ARCAF-YOLO: event-based multimodal algorithm for small object detection in aerial images"],"prefix":"10.1007","volume":"20","author":[{"given":"Jiannan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwen","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiteng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Shuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"5222_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2021.103906","volume":"118","author":"Y Xue","year":"2021","unstructured":"Xue, Y., Ju, Z., Li, Y., Zhang, W.: Maf-yolo: multi-modal attention fusion based yolo for pedestrian detection. Infrared Physics & Technology 118, 103906 (2021)","journal-title":"Infrared Physics & Technology"},{"issue":"50","key":"5222_CR2","doi-asserted-by":"publisher","first-page":"10725","DOI":"10.1523\/JNEUROSCI.1695-18.2018","volume":"38","author":"S Nicholas","year":"2018","unstructured":"Nicholas, S., Supple, J., Leibbrandt, R., Gonzalez-Bellido, P.T., Nordstr\u00f6m, K.: Integration of small-and wide-field visual features in target-selective descending neurons of both predatory and nonpredatory dipterans. J. Neurosci. 38(50), 10725\u201310733 (2018)","journal-title":"J. Neurosci."},{"issue":"7","key":"5222_CR3","doi-asserted-by":"publisher","first-page":"2115","DOI":"10.1016\/j.celrep.2020.01.061","volume":"30","author":"MF Kele\u015f","year":"2020","unstructured":"Kele\u015f, M.F., Hardcastle, B.J., St\u00e4dele, C., Xiao, Q., Frye, M.A.: Inhibitory interactions and columnar inputs to an object motion detector in drosophila. Cell Rep. 30(7), 2115\u20132124 (2020)","journal-title":"Cell Rep."},{"key":"5222_CR4","doi-asserted-by":"crossref","unstructured":"Tomy, A., Paigwar, A., Mann, K.S., Renzaglia, A., Laugier, C.: Fusing event-based and rgb camera for robust object detection in adverse conditions. In: 2022 International Conference on Robotics and Automation (ICRA), 933\u2013939 (2022). IEEE","DOI":"10.1109\/ICRA46639.2022.9812059"},{"key":"5222_CR5","doi-asserted-by":"crossref","unstructured":"Hu, Y., Liu, S.-C., Delbruck, T.: v2e: From video frames to realistic dvs events. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 1312\u20131321 (2021)","DOI":"10.1109\/CVPRW53098.2021.00144"},{"key":"5222_CR6","doi-asserted-by":"crossref","unstructured":"Bai, Y., Zhang, Y., Ding, M., Ghanem, B.: Sod-mtgan: Small object detection via multi-task generative adversarial network. In: Proceedings of the European Conference on Computer Vision (ECCV). 206\u2013221 (2018)","DOI":"10.1007\/978-3-030-01261-8_13"},{"key":"5222_CR7","doi-asserted-by":"crossref","unstructured":"Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1222\u20131230 (2017)","DOI":"10.1109\/CVPR.2017.211"},{"key":"5222_CR8","doi-asserted-by":"crossref","unstructured":"Yu, B., Chen, W., Wang, W.: Research on industrial non-destructive testing technology based on improved yolov5s. In: 2023 12th International Conference of Information and Communication Technology (ICTech). 435\u2013440 (2023). IEEE","DOI":"10.1109\/ICTech58362.2023.00088"},{"key":"5222_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, T., Xie, G., Xie, X., Li, L., Zhang, H., Liang, Y.: An efficient bidirectional weighted global feature extraction algorithm for steel surface defects. In: 2023 China Automation Congress (CAC). 6370\u20136375 (2023). IEEE","DOI":"10.1109\/CAC59555.2023.10451161"},{"issue":"11","key":"5222_CR10","first-page":"13467","volume":"45","author":"G Cheng","year":"2023","unstructured":"Cheng, G., Yuan, X., Yao, X., Yan, K., Zeng, Q., Xie, X., Han, J.: Towards large-scale small object detection: survey and benchmarks. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13467\u201313488 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"5222_CR11","doi-asserted-by":"publisher","first-page":"6340","DOI":"10.1109\/TCYB.2022.3170699","volume":"53","author":"H Wang","year":"2022","unstructured":"Wang, H., Zhao, J., Wang, H., Hu, C., Peng, J., Yue, S.: Attention and prediction-guided motion detection for low-contrast small moving targets. IEEE Transactions on Cybernetics 53(10), 6340\u20136352 (2022)","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"1","key":"5222_CR12","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1109\/TNNLS.2021.3094205","volume":"34","author":"H Wang","year":"2021","unstructured":"Wang, H., Wang, H., Zhao, J., Hu, C., Peng, J., Yue, S.: A time-delay feedback neural network for discriminating small, fast-moving targets in complex dynamic environments. IEEE Transactions on Neural Networks and Learning Systems 34(1), 316\u2013330 (2021)","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"5222_CR13","doi-asserted-by":"crossref","unstructured":"Li, R., An, W., Ying, X., Wang, Y., Dai, Y., Wang, L., Li, M., Guo, Y., Liu, L.: Probing deep into temporal profile makes the infrared small target detector much better. arXiv preprint arXiv:2506.12766 (2025)","DOI":"10.1109\/TPAMI.2026.3683258"},{"issue":"1","key":"5222_CR14","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1109\/TNNLS.2023.3331004","volume":"36","author":"R Li","year":"2023","unstructured":"Li, R., An, W., Xiao, C., Li, B., Wang, Y., Li, M., Guo, Y.: Direction-coded temporal u-shape module for multiframe infrared small target detection. IEEE Transactions on Neural Networks and Learning Systems. 36(1), 555\u2013568 (2023)","journal-title":"IEEE Transactions on Neural Networks and Learning Systems."},{"key":"5222_CR15","unstructured":"Perot, E., De Tournemire, P., Nitti, D., Masci, J., Sironi, A.: Learning to detect objects with a 1 megapixel event camera. Adv. Neural. Inf. Process. Syst. 33, 16639\u201316652 (2020)"},{"key":"5222_CR16","doi-asserted-by":"crossref","unstructured":"Gehrig, M., Scaramuzza, D.: Recurrent vision transformers for object detection with event cameras. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13884\u201313893 (2023)","DOI":"10.1109\/CVPR52729.2023.01334"},{"key":"5222_CR17","doi-asserted-by":"crossref","unstructured":"Chen, N., Xiao, C., Dai, Y., He, S., Li, M., An, W.: Event-based tiny object detection: A benchmark dataset and baseline. arXiv preprint arXiv:2506.23575 (2025)","DOI":"10.1109\/ICCV51701.2025.00677"},{"key":"5222_CR18","doi-asserted-by":"crossref","unstructured":"Chen, N., Li, B., Wang, Y., Ying, X., Wang, L., Zhang, C., Guo, Y., Li, M., An, W.: Motion and appearance decoupling representation for event cameras. IEEE Transactions on Image Processing (2025)","DOI":"10.1109\/TIP.2025.3607632"},{"key":"5222_CR19","doi-asserted-by":"crossref","unstructured":"Chen, N.F.: Pseudo-labels for supervised learning on dynamic vision sensor data, applied to object detection under ego-motion. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 644\u2013653 (2018)","DOI":"10.1109\/CVPRW.2018.00107"},{"key":"5222_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Xia, P., Huang, K., Stechele, W., Chen, G., Bing, Z., Knoll, A.: Mixed frame-\/event-driven fast pedestrian detection. In: 2019 International Conference on Robotics and Automation (ICRA). 8332\u20138338 (2019). IEEE","DOI":"10.1109\/ICRA.2019.8793924"},{"key":"5222_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Wu, Z., Boutteau, R., Yang, F., Demonceaux, C., Ginhac, D.: Rgb-event fusion for moving object detection in autonomous driving. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). 7808\u20137815 (2023). IEEE","DOI":"10.1109\/ICRA48891.2023.10161563"},{"key":"5222_CR22","unstructured":"Zhang, X., Liu, C., Yang, D., Song, T., Ye, Y., Li, K., Song, Y.: Rfaconv: Innovating spatial attention and standard convolutional operation. arXiv preprint arXiv:2304.03198 (2023)"},{"key":"5222_CR23","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. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"5222_CR24","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"5222_CR25","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision. 213\u2013229 (2020). Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"5222_CR26","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. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"5222_CR27","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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05222-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05222-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05222-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T18:39:42Z","timestamp":1778870382000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05222-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":27,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["5222"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05222-8","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"assertion":[{"value":"19 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2026","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"283"}}