{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T08:05:10Z","timestamp":1774166710942,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"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":["61672466"],"award-info":[{"award-number":["61672466"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11554-025-01777-w","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T15:46:28Z","timestamp":1760543188000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["HyperEdge-DETR: hypergraph-enhanced edge-aware detection transformer for small object detection in UAV"],"prefix":"10.1007","volume":"22","author":[{"given":"Cheng","family":"Shen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shusen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haixiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingfeng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"1777_CR1","unstructured":"Du, D., Qi, Y., Yu, H., Yang, Y., Duan, K., Li, G., Zhang, W., Huang, Q., Tian, Q.: Visdrone-det2019: The vision meets drone object detection in image challenge results. In: European Conference on Computer Vision Workshops (2019)"},{"key":"1777_CR2","doi-asserted-by":"crossref","unstructured":"Tang, G., Ni, J., Zhao, Y., Gu, Y., Cao, W.: A survey of object detection for UAVs based on deep learning. Remote. Sens. 16(1), 149 (2023)","DOI":"10.3390\/rs16010149"},{"key":"1777_CR3","volume":"131","author":"Y Xie","year":"2024","unstructured":"Xie, Y., Zhan, N., Zhu, J., Bingli, X., Chen, H., Mao, W., Luo, X., Ya, H.: Landslide extraction from aerial imagery considering context association characteristics. Int. J. Appl. Earth Obs. Geoinf. 131, 103950 (2024)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"issue":"1","key":"1777_CR4","doi-asserted-by":"publisher","first-page":"2346259","DOI":"10.1080\/17538947.2024.2346259","volume":"17","author":"J Zhu","year":"2024","unstructured":"Zhu, J., Zhang, J., Chen, H., Xie, Y., Hengchao, G., Lian, H.: A cross-view intelligent person search method based on multi-feature constraints. Int. J. Digit. Earth 17(1), 2346259 (2024)","journal-title":"Int. J. Digit. Earth"},{"key":"1777_CR5","doi-asserted-by":"crossref","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 (2016)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"1777_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1777_CR7","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1777_CR8","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1777_CR9","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Yolov8 by ultralytics. https:\/\/github.com\/ultralytics\/ultralytics (2023)"},{"key":"1777_CR10","first-page":"107984","volume":"37","author":"A Wang","year":"2024","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., et al.: Yolov10: real-time end-to-end object detection. Adv. Neural. Inf. Process. Syst. 37, 107984\u2013108011 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1777_CR11","doi-asserted-by":"crossref","unstructured":"Xie, Y., Liu, S., Chen, H., Cao, S., Zhang, H., Feng, D., Wan, Q., Zhu, J., Zhu, Q.: Localization, balance and affinity: a stronger multifaceted collaborative salient object detector in remote sensing images. IEEE Trans. Geosci. Remote Sens. 63, 4700117 (2024)","DOI":"10.1109\/TGRS.2024.3506630"},{"key":"1777_CR12","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"},{"key":"1777_CR13","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"},{"issue":"17","key":"1777_CR14","doi-asserted-by":"publisher","first-page":"5496","DOI":"10.3390\/s24175496","volume":"24","author":"Y Kong","year":"2024","unstructured":"Kong, Y., Shang, X., Jia, S.: Drone-detr: efficient small object detection for remote sensing image using enhanced rt-detr model. Sensors 24(17), 5496 (2024)","journal-title":"Sensors"},{"issue":"22","key":"1777_CR15","doi-asserted-by":"publisher","first-page":"7376","DOI":"10.3390\/s24227376","volume":"24","author":"X Wei","year":"2024","unstructured":"Wei, X., Yin, L., Zhang, L., Fei, W.: Dv-detr: improved uav aerial small target detection algorithm based on rt-detr. Sensors 24(22), 7376 (2024)","journal-title":"Sensors"},{"key":"1777_CR16","doi-asserted-by":"crossref","unstructured":"Song, G., Du, H., Zhang, X., Bao, F., Zhang, Y.: Small object detection in unmanned aerial vehicle images using multi-scale hybrid attention. Eng. Appl. Artif. Intell. 128, 107455 (2024)","DOI":"10.1016\/j.engappai.2023.107455"},{"key":"1777_CR17","doi-asserted-by":"crossref","unstructured":"Feng, Y., Huang, J., Du, S., Ying, S., Yong, J.-H., Li, Y., Ding, G., Ji, R., Gao, Y.: Hyper-yolo: when visual object detection meets hypergraph computation. IEEE Trans. Pattern Anal. Mach. Intell. 47(4), 2388\u2013 2401 (2024)","DOI":"10.1109\/TPAMI.2024.3524377"},{"key":"1777_CR18","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"1777_CR19","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, 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1777_CR20","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. In: European Conference on Computer Vision, 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1777_CR21","unstructured":"Khanam, R., Hussain, M.: Yolov11: an overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725 (2024)"},{"key":"1777_CR22","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. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1777_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110080","volume":"259","author":"L Wang","year":"2023","unstructured":"Wang, L., Song, Z., Zhang, X., Wang, C., Zhang, G., Zhu, L., Li, J., Liu, H.: Sat-gcn: self-attention graph convolutional network-based 3d object detection for autonomous driving. Knowl.-Based Syst. 259, 110080 (2023)","journal-title":"Knowl.-Based Syst."},{"key":"1777_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107656","volume":"130","author":"M-M Huang","year":"2024","unstructured":"Huang, M.-M., Yang-Geng, F., Liu, G.-G., Guo, L.-K., Liu, W.-L.: Gmp-net: graph based missing part patching network for point cloud completion. Eng. Appl. Artif. Intell. 130, 107656 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1777_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107525","volume":"233","author":"C Liu","year":"2021","unstructured":"Liu, C., Xiaolong, X.: Amff: a new attention-based multi-feature fusion method for intention recognition. Knowl.-Based Syst. 233, 107525 (2021)","journal-title":"Knowl.-Based Syst."},{"key":"1777_CR26","doi-asserted-by":"crossref","unstructured":"He, J., Zhang, S., Yang, M., Shan, Y., Huang, T.: Bi-directional cascade network for perceptual edge detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3828\u20133837 (2019)","DOI":"10.1109\/CVPR.2019.00395"},{"key":"1777_CR27","unstructured":"Vaswani, V., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS'17). Curran Associates Inc., Red Hook, NY (2017). ISBN 978-1-5108-6096-4"},{"key":"1777_CR28","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on computer vision, 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"1","key":"1777_CR29","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1038\/s41597-023-02066-6","volume":"10","author":"J Suo","year":"2023","unstructured":"Suo, J., Wang, T., Zhang, X., Chen, H., Zhou, W., Shi, W.: Hit-uav: a high-altitude infrared thermal dataset for unmanned aerial vehicle-based object detection. Sci. Data 10(1), 227 (2023)","journal-title":"Sci. Data"},{"issue":"11","key":"1777_CR30","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2021","unstructured":"Zhu, P., Wen, L., Dawei, D., Bian, X., Fan, H., Qinghua, H., Ling, H.: Detection and tracking meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7380\u20137399 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1777_CR31","unstructured":"Zahran, M.S.: Crowdhuman dataset. https:\/\/universe.roboflow.com\/muhammad-suzaki-zahran\/crowdhuman-rmy5m, (2023), (accessed Aug. 27 2025)"},{"key":"1777_CR32","unstructured":"Li, H., Li, S., Dai, W., Li, C., Zou, J., Xiong, H.: Frequency-aware transformer for learned image compression. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"1777_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, S., Li, H.: Depth information assisted collaborative mutual promotion network for single image dehazing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2846\u20132855 (2024)","DOI":"10.1109\/CVPR52733.2024.00275"},{"key":"1777_CR34","doi-asserted-by":"crossref","unstructured":"Yan, Q., Feng, Y., Zhang, C., Pang, G., Shi, K., Wu, P., Dong, W., Sun, J., Zhang, Y.: Hvi: a new color space for low-light image enhancement. arXiv preprint arXiv:2502.20272 (2025)","DOI":"10.1109\/CVPR52734.2025.00533"},{"key":"1777_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Z., Guan, Q., Zhao, K., Yang, J., Xu, X., Long, H., Tang, Y.: Multi-branch auxiliary fusion yolo with re-parameterization heterogeneous convolutional for accurate object detection. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pages 492\u2013505. Springer (2024)","DOI":"10.1007\/978-981-97-8858-3_34"},{"key":"1777_CR36","doi-asserted-by":"crossref","unstructured":"Wang, H., Cao, P., Wang, J., Zaiane, O.R.: Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence 36(3), 2441\u20132449 (2022)","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"1777_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101870","volume":"99","author":"L Tang","year":"2023","unstructured":"Tang, L., Zhang, H., Han, X., Ma, J.: Rethinking the necessity of image fusion in high-level vision tasks: a practical infrared and visible image fusion network based on progressive semantic injection and scene fidelity. Inform. Fusion 99, 101870 (2023)","journal-title":"Inform. Fusion"},{"key":"1777_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, Z., He, A., Wu, Y., Yao, R., Xie, X., Li, T.: Spatial-frequency dual domain attention network for medical image segmentation. In: 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 4076\u20134081 (2024)","DOI":"10.1109\/BIBM62325.2024.10822613"},{"key":"1777_CR39","doi-asserted-by":"publisher","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":"1777_CR40","first-page":"1","volume":"19","author":"H Bai","year":"2021","unstructured":"Bai, H., Cheng, J., Huang, X., Liu, S., Deng, C.: Hcanet: a hierarchical context aggregation network for semantic segmentation of high-resolution remote sensing images. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2021)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"1777_CR41","doi-asserted-by":"publisher","first-page":"5465","DOI":"10.1109\/TIP.2023.3318967","volume":"32","author":"K Li","year":"2023","unstructured":"Li, K., Geng, Q., Wan, M., Cao, X., Zhou, Z.: Context and spatial feature calibration for real-time semantic segmentation. IEEE Trans. Image Process. 32, 5465\u20135477 (2023)","journal-title":"IEEE Trans. Image Process."}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01777-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-025-01777-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-025-01777-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T07:04:25Z","timestamp":1762758265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-025-01777-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["1777"],"URL":"https:\/\/doi.org\/10.1007\/s11554-025-01777-w","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]},"assertion":[{"value":"23 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2025","order":3,"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":"Conflict of interest"}}],"article-number":"206"}}