{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T22:24:46Z","timestamp":1784154286767,"version":"3.55.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["72174203"],"award-info":[{"award-number":["72174203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72174203"],"award-info":[{"award-number":["72174203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s00371-025-04321-w","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T14:34:21Z","timestamp":1768833261000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing multi-domain UAV object detection via state space modeling and hypergraph feature fusion"],"prefix":"10.1007","volume":"42","author":[{"given":"Weizeng","family":"Qin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaolong","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,19]]},"reference":[{"issue":"1","key":"4321_CR1","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1109\/mgrs.2021.3115137","volume":"10","author":"X Wu","year":"2022","unstructured":"Wu, X., Li, W., Hong, D., et al.: Deep learning for unmanned aerial vehicle-based object detection and tracking: a survey. IEEE Geosci. Remote. Sens. Mag. 10(1), 91\u2013124 (2022). https:\/\/doi.org\/10.1109\/mgrs.2021.3115137","journal-title":"IEEE Geosci. Remote. Sens. Mag."},{"issue":"2","key":"4321_CR2","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1109\/TITS.2021.3122567","volume":"24","author":"R Liu","year":"2023","unstructured":"Liu, R., Liu, A., Qu, Z., et al.: An uav-enabled intelligent connected transportation system with 6g communications for internet of vehicles. IEEE Trans. Intell. Transp. Syst. 24(2), 2045\u20132059 (2023). https:\/\/doi.org\/10.1109\/TITS.2021.3122567","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"4321_CR3","doi-asserted-by":"publisher","first-page":"64","DOI":"10.3390\/safety9030064","volume":"9","author":"K AL-Dosari","year":"2023","unstructured":"AL-Dosari, K., Fetais, N.: A new shift in implementing unmanned aerial vehicles (uavs) in the safety and security of smart cities: a systematic literature review. Safety 9(3), 64 (2023). https:\/\/doi.org\/10.3390\/safety9030064","journal-title":"Safety"},{"issue":"7","key":"4321_CR4","doi-asserted-by":"publisher","first-page":"154","DOI":"10.3390\/drones6070154","volume":"6","author":"SH Alsamhi","year":"2022","unstructured":"Alsamhi, S.H., Shvetsov, A.V., Kumar, S., et al.: Uav computing-assisted search and rescue mission framework for disaster and harsh environment mitigation. Drones 6(7), 154 (2022). https:\/\/doi.org\/10.3390\/drones6070154","journal-title":"Drones"},{"key":"4321_CR5","doi-asserted-by":"publisher","unstructured":"Moranduzzo, T., Melgani, F.: A sift-svm method for detecting cars in uav images. In: 2012 IEEE International Geoscience and Remote Sensing Symposium, pp. 6868\u20136871. (2012) https:\/\/doi.org\/10.1109\/IGARSS.2012.6352585","DOI":"10.1109\/IGARSS.2012.6352585"},{"issue":"8","key":"4321_CR6","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.3390\/s16081325","volume":"16","author":"Y Xu","year":"2016","unstructured":"Xu, Y., Yu, G., Wang, Y., et al.: A hybrid vehicle detection method based on viola-jones and hog + svm from uav images. Sensors 16(8), 1325 (2016). https:\/\/doi.org\/10.3390\/s16081325","journal-title":"Sensors"},{"key":"4321_CR7","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., et\u00a0al.: Rich feature hierarchies for accurate object detection and semantic segmentation. (2014). arXiv:1311.2524","DOI":"10.1109\/CVPR.2014.81"},{"key":"4321_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. (2015) arXiv:1504.08083","DOI":"10.1109\/ICCV.2015.169"},{"key":"4321_CR9","doi-asserted-by":"crossref","unstructured":"Ren, S., He, K., Girshick, R., et\u00a0al.: Faster r-cnn: towards real-time object detection with region proposal networks. (2016). arXiv:1506.01497","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"4321_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et\u00a0al.: Mask r-cnn. (2018) arXiv:1703.06870","DOI":"10.1109\/ICCV.2017.322"},{"key":"4321_CR11","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., et\u00a0al.: You only look once: Unified, real-time object detection.(2016) arXiv:1506.02640","DOI":"10.1109\/CVPR.2016.91"},{"key":"4321_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. (2016) arXiv:1612.08242","DOI":"10.1109\/CVPR.2017.690"},{"key":"4321_CR13","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. (2018) arXiv:1804.02767"},{"key":"4321_CR14","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. (2020) arXiv:2004.10934"},{"key":"4321_CR15","unstructured":"Li, C., Li, L., Jiang, H., et\u00a0al.: Yolov6: a single-stage object detection framework for industrial applications. (2022) arXiv:2209.02976"},{"key":"4321_CR16","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. (2022) arXiv:2207.02696","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"4321_CR17","unstructured":"Wang, A., Chen, H., Liu, L., et\u00a0al.: Yolov10: real-time end-to-end object detection. (2024) arXiv:2405.14458"},{"key":"4321_CR18","unstructured":"Khanam, R., Hussain, M.: Yolov11: an overview of the key architectural enhancements. (2024) arXiv:2410.17725"},{"key":"4321_CR19","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"SSD: Single Shot MultiBox Detector","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., et al.: SSD: Single Shot MultiBox Detector, pp. 21\u201337. Springer, Berlin (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"4321_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3241825","volume":"72","author":"T Ye","year":"2023","unstructured":"Ye, T., Qin, W., Zhao, Z., et al.: Real-time object detection network in uav-vision based on cnn and transformer. IEEE Trans. Instrum. Meas. 72, 1\u201313 (2023). https:\/\/doi.org\/10.1109\/TIM.2023.3241825","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"4321_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2022.3196319","volume":"71","author":"T Ye","year":"2022","unstructured":"Ye, T., Qin, W., Li, Y., et al.: Dense and small object detection in uav-vision based on a global-local feature enhanced network. IEEE Trans. Instrum. Meas. 71, 1\u201313 (2022). https:\/\/doi.org\/10.1109\/TIM.2022.3196319","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"4321_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121366","volume":"686","author":"Q Fan","year":"2025","unstructured":"Fan, Q., Li, Y., Deveci, M., et al.: Lud-yolo: a novel lightweight object detection network for unmanned aerial vehicle. Inf. Sci. 686, 121366 (2025). https:\/\/doi.org\/10.1016\/j.ins.2024.121366","journal-title":"Inf. Sci."},{"key":"4321_CR23","first-page":"1","volume":"41","author":"J Yang","year":"2024","unstructured":"Yang, J., Zhang, X., Song, C.: Research on a small target object detection method for aerial photography based on improved yolov7. Vis. Comput. 41, 1\u201315 (2024)","journal-title":"Vis. Comput."},{"key":"4321_CR24","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S., Huang, W., et al.: Eapt: efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2023). https:\/\/doi.org\/10.1109\/TMM.2021.3120873","journal-title":"IEEE Trans. Multimed."},{"issue":"7","key":"4321_CR25","doi-asserted-by":"publisher","first-page":"4759","DOI":"10.1007\/s00371-024-03689-5","volume":"41","author":"MH Junos","year":"2025","unstructured":"Junos, M.H., Khairuddin, A.S.M.: Yolo-mms for aerial object detection model based on hybrid feature extractor and improved multi-scale prediction. Vis. Comput. 41(7), 4759\u20134778 (2025)","journal-title":"Vis. Comput."},{"key":"4321_CR26","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. (2015) arXiv:1409.1556"},{"key":"4321_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: Deep residual learning for image recognition. (2015) arXiv:1512.03385","DOI":"10.1109\/CVPR.2016.90"},{"key":"4321_CR28","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van\u00a0der Maaten, L., et\u00a0al.: Densely connected convolutional networks. (2018) arXiv:1608.06993","DOI":"10.1109\/CVPR.2017.243"},{"key":"4321_CR29","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. (2021) arXiv:2010.11929"},{"key":"4321_CR30","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces.(2024) arXiv:2312.00752"},{"key":"4321_CR31","unstructured":"Liu, Y., Tian, Y., Zhao, Y., et\u00a0al.: Vmamba: Visual state space model. (2024) arXiv:2401.10166"},{"key":"4321_CR32","doi-asserted-by":"crossref","unstructured":"Chen, T., Ye, Z., Tan, Z., et\u00a0al.: Mim-istd: Mamba-in-mamba for efficient infrared small target detection. (2024) arXiv:2403.02148","DOI":"10.1109\/TGRS.2024.3485721"},{"key":"4321_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et\u00a0al.: Feature pyramid networks for object detection. (2017) arXiv:1612.03144","DOI":"10.1109\/CVPR.2017.106"},{"key":"4321_CR34","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., et\u00a0al.: Path aggregation network for instance segmentation. (2018) arXiv:1803.01534","DOI":"10.1109\/CVPR.2018.00913"},{"key":"4321_CR35","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., et\u00a0al.: Repvgg: Making vgg-style convnets great again. (2021) arXiv:2101.03697","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"4321_CR36","unstructured":"Chen, C., Guo, Z., Zeng, H., et\u00a0al.: Repghost: A hardware-efficient ghost module via re-parameterization. (2024) arXiv:2211.06088"},{"key":"4321_CR37","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Zhou, Y., et\u00a0al.: Scaling up your kernels to 31x31: Revisiting large kernel design in cnns. (2022) arXiv:2203.06717","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"4321_CR38","first-page":"1","volume":"73","author":"J Shen","year":"2024","unstructured":"Shen, J., Liu, N., Sun, H., et al.: An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features. IEEE Trans. Instrum. Meas. 73, 1\u201316 (2024)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1","key":"4321_CR39","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2201","volume":"35","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Yao, X., Zhang, J., et al.: Tmsdnet: Transformer with multi-scale dense network for single and multi-view 3d reconstruction. Comput. Animat. Virtual Worlds 35(1), e2201 (2024)","journal-title":"Comput. Animat. Virtual Worlds"},{"issue":"1","key":"4321_CR40","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1038\/s40494-025-01565-6","volume":"13","author":"J Shen","year":"2025","unstructured":"Shen, J., Liu, N., Sun, H., et al.: An algorithm based on lightweight semantic features for ancient mural element object detection. npj Herit. Sci. 13(1), 70 (2025)","journal-title":"npj Herit. Sci."},{"key":"4321_CR41","unstructured":"Feng, Y., Huang, J., Du, S., et\u00a0al.: Hyper-yolo: When visual object detection meets hypergraph computation.(2024) arXiv:2408.04804"},{"key":"4321_CR42","unstructured":"Zhu, P., Wen, L., Bian, X., et\u00a0al.: Vision meets drones: A challenge.(2018) arXiv:1804.07437"},{"issue":"1","key":"4321_CR43","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., et al.: Hit-uav: A high-altitude infrared thermal dataset for unmanned aerial vehicle-based object detection. Sci. Data 10(1), 227 (2023). https:\/\/doi.org\/10.1038\/s41597-023-02066-6","journal-title":"Sci. Data"},{"key":"4321_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et\u00a0al.: 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"},{"issue":"5","key":"4321_CR45","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: high quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1483\u20131498 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4321_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., et\u00a0al.: 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":"4321_CR47","unstructured":"Zhang, H., Li, F., Liu, S., et\u00a0al.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection. (2022) arXiv preprint arXiv:2203.03605"},{"key":"4321_CR48","unstructured":"Lyu, C., Zhang, W., Huang, H., et\u00a0al.: Rtmdet: An empirical study of designing real-time object detectors. (2022) arXiv preprint arXiv:2212.07784"},{"key":"4321_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., et\u00a0al.: Detrs beat yolos on real-time object detection. (2023) arXiv:2304.08069","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"4321_CR50","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et\u00a0al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022. (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"4321_CR51","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., et\u00a0al.: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578. (2021)","DOI":"10.1109\/ICCV48922.2021.00061"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04321-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04321-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04321-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T12:45:50Z","timestamp":1772628350000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04321-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["4321"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04321-w","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"16 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors declare that they have no competing financial interests or personal relationships that could influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors. The datasets used in the manuscript are derived from publicly available data sets and may be obtained from the appropriate authors upon reasonable request.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent"}}],"article-number":"131"}}