{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T13:08:14Z","timestamp":1784725694411,"version":"3.55.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00530-026-02395-7","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T10:32:13Z","timestamp":1780741933000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LMI-DETR: research on multi-scale feature interaction based object detection method under limited imaging conditions"],"prefix":"10.1007","volume":"32","author":[{"given":"Zidian","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linghan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunwang","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"key":"2395_CR1","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., et al.: 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":"2395_CR2","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":"2395_CR3","doi-asserted-by":"publisher","first-page":"8077","DOI":"10.1109\/JSTARS.2021.3103261","volume":"14","author":"C Wang","year":"2021","unstructured":"Wang, C., Wang, L.: Multidirectional ring top-hat transformation for infrared small target detection. IEEE J Select Topics Appl Earth Observ Remote Sensing 14, 8077\u20138088 (2021)","journal-title":"IEEE J Select Topics Appl Earth Observ Remote Sensing"},{"key":"2395_CR4","doi-asserted-by":"crossref","unstructured":"Liu, R., Ren, C., Fu, M., et al.: Platelet detection based on improved YOLO_v3. Cyborg and Bionic Systems (2022)","DOI":"10.34133\/2022\/9780569"},{"key":"2395_CR5","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., et al.: Microsoft coco: Common objects in context. In: European Conference on Computer Vision. Cham: Springer International Publishing pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"2","key":"2395_CR6","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., et al.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"2395_CR7","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"issue":"9","key":"2395_CR8","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., et al.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2395_CR9","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":"2395_CR10","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28 (2015)"},{"key":"2395_CR11","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., et al.: Ssd: Single shot multibox detector. In: European Conference on Computer Vision. Cham: Springer International Publishing, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2395_CR12","doi-asserted-by":"crossref","unstructured":"Chen, N., Li, B., Wang, Y., et al.: Motion and appearance decoupling representation for event cameras. IEEE Transactions on Image Processing (2025)","DOI":"10.1109\/TIP.2025.3607632"},{"issue":"5","key":"2395_CR13","doi-asserted-by":"publisher","first-page":"1814","DOI":"10.1109\/TCDS.2024.3386664","volume":"16","author":"H Zhou","year":"2024","unstructured":"Zhou, H., Qi, L., Huang, H., et al.: Spatiotemporal feature enhancement network for blur robust underwater object detection. IEEE Trans. Cogn. Dev. Syst. 16(5), 1814\u20131828 (2024)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"2395_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et al.: 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":"2395_CR15","doi-asserted-by":"crossref","unstructured":"Rathinam, S., Almeida, P., Kim, Z.W., et al.: Autonomous searching and tracking of a river using an UAV. In: 2007 American Control Conference. IEEE, pp. 359\u2013364 (2007)","DOI":"10.1109\/ACC.2007.4282475"},{"key":"2395_CR16","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/j.neucom.2019.07.073","volume":"366","author":"J Zhou","year":"2019","unstructured":"Zhou, J., Vong, C.M., Liu, Q., et al.: Scale adaptive image crop** for UAV object detection. Neurocomputing 366, 305\u2013313 (2019)","journal-title":"Neurocomputing"},{"key":"2395_CR17","doi-asserted-by":"crossref","unstructured":"Wang, S.: Vehicle detection on aerial images by extracting corner features for rotational invariant shape matching. In: 2011 IEEE 11th International Conference on Computer and Information Technology. IEEE 171\u2013175 (2011)","DOI":"10.1109\/CIT.2011.56"},{"key":"2395_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., et al.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2395_CR19","doi-asserted-by":"crossref","unstructured":"Zhou, S., Chen, D., Pan, J., et al.: Adapt or perish: Adaptive sparse transformer with attentive feature refinement for image restoration. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 2952\u20132963 (2024)","DOI":"10.1109\/CVPR52733.2024.00285"},{"key":"2395_CR20","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhang, H., Atapour-Abarghouei, A., et al.: SEM-Net: efficient pixel modelling for image inpainting with spatially enhanced SSM. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, pp. 461\u2013471 (2025)","DOI":"10.1109\/WACV61041.2025.00055"},{"key":"2395_CR21","doi-asserted-by":"crossref","unstructured":"Yin, D., Hu, L., Li, B., et al.: 5%> 100%: Breaking performance shackles of full fine-tuning on visual recognition tasks. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 20071\u201320081 (2025)","DOI":"10.1109\/CVPR52734.2025.01869"},{"issue":"1","key":"2395_CR22","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. Scient. Data 10(1), 227 (2023)","journal-title":"Scient. Data"},{"key":"2395_CR23","doi-asserted-by":"crossref","unstructured":"Liu, J., Fan, X., Huang, Z., et al.: Target-aware dual adversarial learning and a multi-scenario multi-modality benchmark to fuse infrared and visible for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 5802\u20135811 (2022)","DOI":"10.1109\/CVPR52688.2022.00571"},{"key":"2395_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et al.: 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":"2395_CR25","doi-asserted-by":"crossref","unstructured":"Qin, D., Leichner, C., Delakis, M., et al.: MobileNetV4: universal models for the mobile ecosystem. In: European Conference on Computer Vision. Cham: Springer Nature Switzerland, pp. 78\u201396 (2024)","DOI":"10.1007\/978-3-031-73661-2_5"},{"key":"2395_CR26","doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., et al.: Convnext v2: Co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"2395_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Hu, J., Wen, Y., et al.: Rethinking vision transformers for mobilenet size and speed. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 16889\u201316900 (2023)","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"2395_CR28","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, Y., Ge, Y., et al.: Unireplknet: A universal perception large-kernel convnet for audio video point cloud time-series and image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5513\u20135524 (2024)","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"2395_CR29","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Chen, D., et al.: Cswin transformer: A general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern recognition. pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"2395_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, X., Dai, Y., et al.: LSKNet: a foundation lightweight backbone for remote sensing: Y. Li et al. Int. J. Comput. Vision 133(3), 1410\u20131431 (2025)","DOI":"10.1007\/s11263-024-02247-9"},{"key":"2395_CR31","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., et al.: Context and spatial feature calibration for real-time semantic segmentation. IEEE Trans. Image Process. 32, 5465\u20135477 (2023)","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"2395_CR32","doi-asserted-by":"publisher","first-page":"10763","DOI":"10.1109\/TPAMI.2024.3449959","volume":"46","author":"L Chen","year":"2024","unstructured":"Chen, L., Fu, Y., Gu, L., et al.: Frequency-aware feature fusion for dense image prediction. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 10763\u201310780 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"2395_CR33","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1080\/2150704X.2024.2388853","volume":"15","author":"T Ma","year":"2024","unstructured":"Ma, T., Yin, H.: MAFPN: a mixed local-global attention feature pyramid network for aerial object detection. Remote Sens. Lett. 15(9), 907\u2013918 (2024)","journal-title":"Remote Sens. Lett."},{"key":"2395_CR34","volume":"170","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Zhang, C., Chen, B., et al.: Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases. CoRR 170, 107917 (2024)","journal-title":"CoRR"},{"issue":"3","key":"2395_CR35","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","volume":"21","author":"H Li","year":"2024","unstructured":"Li, H., Li, J., Wei, H., et al.: Slim-neck by GSConv: a lightweight-design for real-time detector architectures. J. Real-Time Image Proc. 21(3), 62 (2024)","journal-title":"J. Real-Time Image Proc."},{"key":"2395_CR36","unstructured":"Zhang, T.: CAS-ViT: Convolutional additive self-attention vision transformers for efficient mobile applications"},{"key":"2395_CR37","doi-asserted-by":"crossref","unstructured":"Ji, Y., Zhang, R., Wang, H., et al.: Multi-compound transformer for accurate biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Cham: Springer International Publishing, pp. 326\u2013336 (2021)","DOI":"10.1007\/978-3-030-87193-2_31"},{"key":"2395_CR38","doi-asserted-by":"crossref","unstructured":"Sun, S., Ren, W., Gao, X., et al.: Restoring images in adverse weather conditions via histogram transformer. In: European Conference on Computer Vision. Cham: Springer Nature Switzerland, pp. 111\u2013129 (2024)","DOI":"10.1007\/978-3-031-72670-5_7"},{"issue":"5","key":"2395_CR39","doi-asserted-by":"publisher","first-page":"3123","DOI":"10.1109\/TPAMI.2023.3341806","volume":"46","author":"W Wang","year":"2023","unstructured":"Wang, W., Chen, W., Qiu, Q., et al.: Crossformer++: a versatile vision transformer hinging on cross-scale attention. IEEE Trans. Pattern Anal. Mach. Intell. 46(5), 3123\u20133136 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2395_CR40","doi-asserted-by":"publisher","first-page":"14541","DOI":"10.52202\/068431-1057","volume":"35","author":"Z Pan","year":"2022","unstructured":"Pan, Z., Cai, J., Zhuang, B.: Fast vision transformers with hilo attention. Adv. Neural. Inf. Process. Syst. 35, 14541\u201314554 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2395_CR41","unstructured":"Zhang, H., Li, F., Liu, S., et al.: DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection. In: The Eleventh International Conference on Learning Representations"},{"key":"2395_CR42","doi-asserted-by":"crossref","unstructured":"Huang, Y.X., Liu, H.I., Shuai, H.H., et al.: Dq-detr: Detr with dynamic query for tiny object detection. In: European Conference on Computer Vision. Cham: Springer Nature Switzerland, pp. 290\u2013305 (2024)","DOI":"10.1007\/978-3-031-73116-7_17"},{"key":"2395_CR43","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., Wang, W., Wu, L., et al.: 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":"2395_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., et al.: Varifocalnet: An iou-aware dense object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"2395_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., et al.: 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":"2395_CR46","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":"2395_CR47","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., et al.: Tood: Task-aligned one-stage object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE Computer Society, pp. 3490\u20133499 (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"2395_CR48","unstructured":"Zhu, X., Su, W., Lu, L., et al.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations"},{"key":"2395_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., et al.: 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"},{"issue":"1","key":"2395_CR50","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1109\/TIP.2018.2867951","volume":"28","author":"B Li","year":"2018","unstructured":"Li, B., Ren, W., Fu, D., et al.: Benchmarking single-image dehazing and beyond. IEEE Trans. Image Process. 28(1), 492\u2013505 (2018)","journal-title":"IEEE Trans. Image Process."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02395-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02395-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02395-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T12:56:50Z","timestamp":1784725010000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02395-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":50,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["2395"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02395-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]},"assertion":[{"value":"17 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"342"}}