{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T10:58:36Z","timestamp":1774522716361,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"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":["51804250"],"award-info":[{"award-number":["51804250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s13042-025-02881-w","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T10:50:25Z","timestamp":1771239025000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RCV-fusion net: dynamic feature re-extraction and cross-modal fusion for enhanced vehicle small target detection"],"prefix":"10.1007","volume":"17","author":[{"given":"Xuecun","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhonghua","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shushan","family":"Qiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"issue":"3","key":"2881_CR1","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou Z, Chen K, Shi Z, Guo Y, Ye J (2023) Object detection in 20 years: a survey. Proc IEEE 111(3):257\u2013276","journal-title":"Proc IEEE"},{"key":"2881_CR2","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"2881_CR3","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume":"9905","author":"W Liu","year":"2016","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed SE, Cheng-Yang F, Berg AC (2016) SSD: single shot multibox detector. Lect Notes Comput Sci (LNCS) 9905:21\u201337","journal-title":"Lect Notes Comput Sci (LNCS)"},{"key":"2881_CR4","first-page":"2999","volume":"99","author":"TY Lin","year":"2017","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 99:2999\u20133007","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2881_CR5","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le Q (2020) EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10778\u201310787","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2881_CR6","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B, (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9992\u201310002","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2881_CR7","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Comput Soc: 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"2881_CR8","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: International Conference on Computer Vision. arXiv preprint arXiv:1504.08083","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"2881_CR9","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Ross FR-CNN towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2881_CR10","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2017) Cascade R-CNN: delving into high quality object detection, pp. 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2881_CR11","doi-asserted-by":"crossref","unstructured":"Lin TY, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"2881_CR12","doi-asserted-by":"crossref","unstructured":"Qiao S, Chen LC, Yuille A (2021) DetectoRS: detecting objects with recursive feature pyramid and switchable atrous convolution. Comput Vis Pattern Recogn: 10213\u201310224","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"2881_CR13","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/TITS.2024.3432761","volume":"25","author":"N Hoanh","year":"2024","unstructured":"Hoanh N, Pham TV (2024) A multi-task framework for car detection from high-resolution UAV imagery focusing on road regions. IEEE Trans Intell Transp Syst 25:11","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2881_CR14","doi-asserted-by":"crossref","unstructured":"Xingchen Z, Shuhao X, Jihuan R, Xiang W (2023) Improved faster R-CNN detection algorithm for small unmanned aerial vehicle targets. In: Proceedings of the International Conference on Autonomous Unmanned Systems. Springer Nature Singapore, 204\u2013213","DOI":"10.1007\/978-981-97-1083-6_19"},{"key":"2881_CR15","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s12145-025-01751-x","volume":"18","author":"H Nguyen","year":"2025","unstructured":"Nguyen H, Ngo TQ, Uyen HTT, Duong MK (2025) Enhanced object recognition from remote sensing images based on hybrid convolution and transformer structure. Earth Sci Inf 18:2","journal-title":"Earth Sci Inf"},{"issue":"4","key":"2881_CR16","first-page":"3483","volume":"52","author":"Y Guanxiang","year":"2022","unstructured":"Guanxiang Y, Meng Yu, Yuejin YZ (2022) Research on highway vehicle detection based on faster R-CNN and domain adaptation. Appl Intell Int J Artif Intell Neural Netw Complex Prob Solving Technol 52(4):3483\u20133498","journal-title":"Appl Intell Int J Artif Intell Neural Netw Complex Prob Solving Technol"},{"key":"2881_CR17","doi-asserted-by":"crossref","unstructured":"Lim JS, Astrid M, Yoon HJ, Lee SI (2019) Small object detection using context and attention: 181\u2013186","DOI":"10.1109\/ICAIIC51459.2021.9415217"},{"issue":"1","key":"2881_CR18","first-page":"1","volume":"14","author":"J Su","year":"2024","unstructured":"Su J, Qin Y, Jia Z, Liang B (2024) MPE-YOLO: enhanced small target detection in aerial imaging. Sci Rep 14(1):1\u201316","journal-title":"Sci Rep"},{"issue":"1","key":"2881_CR19","doi-asserted-by":"crossref","first-page":"2069","DOI":"10.1038\/s41598-024-52560-z","volume":"14","author":"Q Cheng","year":"2024","unstructured":"Cheng Q, Wang Y, He W, Bai Y (2024) Lightweight air-to-air unmanned aerial vehicle target detection model. Sci Rep 14(1):2069","journal-title":"Sci Rep"},{"issue":"Suppl 1","key":"2881_CR20","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1007\/s11760-024-03176-3","volume":"18","author":"A Mu","year":"2024","unstructured":"Mu A, Wang H, Meng W, Chen Y (2024) Small target detection in drone aerial images based on feature fusion. SIViP 18(Suppl 1):585\u2013598","journal-title":"SIViP"},{"key":"2881_CR21","doi-asserted-by":"publisher","first-page":"8166","DOI":"10.1109\/JSTARS.2023.3294624","volume":"16","author":"Y Wu","year":"2023","unstructured":"Wu Y, Guan X, Zhao B, Ni L, Huang M (2023) Vehicle detection based on adaptive multimodal feature fusion and cross-modal vehicle index using RGB-T images. IEEE J Sel Top Appl Earth Obs Remote Sens 16:8166\u20138177","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"key":"2881_CR22","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.aej.2024.07.107","volume":"108","author":"H Gao","year":"2024","unstructured":"Gao H, Wang Y, Sun J, Jiang Y, Gai Y (2024) Efficient multi-level cross-modal fusion and detection network for infrared and visible image. Alex Eng J Elsevier 108:306\u2013318","journal-title":"Alex Eng J Elsevier"},{"key":"2881_CR23","doi-asserted-by":"crossref","unstructured":"Sun J, Yin M, Wang Z, Xie T, Bei S (2024) Multispectral object detection based on multilevel feature fusion and dual feature modulation. Electronics (2079-9292) 13:2","DOI":"10.3390\/electronics13020443"},{"key":"2881_CR24","doi-asserted-by":"crossref","unstructured":"Wang H, Wang C, Fu Q, Zhang D, Kou R (2024) Cross-modal oriented object detection of UAV aerial images based on image feature. IEEE Trans Geosci Remote Sens 62","DOI":"10.1109\/TGRS.2024.3367934"},{"key":"2881_CR25","first-page":"5637215","volume":"62","author":"S Xu","year":"2024","unstructured":"Xu S, Chen X, Li H, Liu T, Chen Z, Gao H, Zhang Y (2024) Airborne small target detection method based on multi-modal and adaptive feature fusion. IEEE Trans Geosci Remote Sens 62:5637215","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2881_CR26","first-page":"036519-1-036519","volume":"16, 3","author":"X Zhang","year":"2022","unstructured":"Zhang X, Peng L, Lu X (2022) Vehicle fusion detection in visible and infrared thermal images via spare network and dynamic weight coefficient-based Dempster-Shafer evidence theory. J Appl Remote Sens 16, 3:036519-1-036519\u201317","journal-title":"J Appl Remote Sens"},{"key":"2881_CR27","doi-asserted-by":"crossref","unstructured":"Zhu H, Ni J, Yang X, Zhang L (2024) CMIGNet: cross-modal inverse guidance network for RGB-depth salient object detection. Pattern Recogn 155","DOI":"10.1016\/j.patcog.2024.110693"},{"key":"2881_CR28","doi-asserted-by":"crossref","unstructured":"Sun L (2024) ACDF-YOLO Attentive and cross-differential fusion network for multimodal remote sensing object detection. Remote Sens 18:3532","DOI":"10.3390\/rs16183532"},{"key":"2881_CR29","doi-asserted-by":"crossref","unstructured":"Luo J, Li Y, Li B, Zhang X, Li C, Chenjin Z, He J, Liang Y (2024) Transformer-based cross-modality interaction guidance network for RGB-T salient object detection. Neurocomputing 600","DOI":"10.1016\/j.neucom.2024.128149"},{"key":"2881_CR30","unstructured":"Jocher G, Chaurasia A, Stoken A, others (2022) ultralytics\/yolov5: v6. 2-yolov5 classification models, apple m1, reproducibility, clearml and deci. ai integrations, Zenodo"},{"key":"2881_CR31","unstructured":"Alkin B, Beck M, Pppel K, Hochreiter S, Brandstetter J (2024) Vision-LSTM: xLSTM as generic vision backbone"},{"key":"2881_CR32","doi-asserted-by":"crossref","unstructured":"Chen H, Gu J, Zhang Z (2021) Attention in attention network for image super-resolution. arXiv preprint arXiv:2104.09497","DOI":"10.1016\/j.patcog.2021.108349"},{"key":"2881_CR33","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) MobileNets: efficient convolutional neural networks for mobile vision applications"},{"key":"2881_CR34","unstructured":"S\u00e9bastien R, Fr\u00e9d\u00e9ric J, (2016) vehicle detection in aerial imagery : a small target detection benchmark. J Vis Commun Image Represent"},{"issue":"10","key":"2881_CR35","doi-asserted-by":"publisher","first-page":"6700","DOI":"10.1109\/TCSVT.2022.3168279","volume":"32","author":"Y Sun","year":"2022","unstructured":"Sun Y, Cao B, Hu ZQ (2022) Drone-based RGB-infrared cross-modality vehicle detection via uncertainty-aware learning. IEEE Trans Circ Syst Video Technol 32(10):6700\u20136713","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"2881_CR36","first-page":"1","volume":"61","author":"J Zhang","year":"2023","unstructured":"Zhang J, Lei J, Xie W, Fang Z, Li Y (2023) SuperYOLO: super resolution assisted object detection in multimodal remote sensing imagery. IEEE Trans Geosci Remote Sens 61:1\u201315","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2881_CR37","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/s11042-023-15333-w","volume":"82","author":"X Cheng","year":"2023","unstructured":"Cheng X, Geng K, Wang Z, Wang J, Sun Y, Ding P (2023) SLBAF-net: super-lightweight bimodal adaptive fusion network for UAV detection in low recognition environment. Multimed Tools Appl 82:30","journal-title":"Multimed Tools Appl"},{"key":"2881_CR38","doi-asserted-by":"crossref","unstructured":"Wang Y, Bashir SM, Khan M, Ullah Q, Wang R, Song Y, Guo Z, Niu Y (2021) Remote sensing image super-resolution and object detection: benchmark and state of the art","DOI":"10.1016\/j.eswa.2022.116793"},{"key":"2881_CR39","doi-asserted-by":"crossref","unstructured":"Fu H, others (2023) LRAF\u2013Net: long\u2013range attention fusion network for visible\u2013infrared object detection. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2023.3266452"},{"key":"2881_CR40","unstructured":"Zheng Y, Izzat IH, Ziaee S (2019) GFD-SSD: gated fusion double SSD for multispectral pedestrian detection. arXiv preprint arXiv:1903.06999"},{"key":"2881_CR41","doi-asserted-by":"crossref","unstructured":"Zhang H, Fromont E, Lefevre S, Avignon B (2020) Multispectral fusion for object detection with cyclic fuse-and-refine blocks. In: Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, Oct, pp. 276\u2013280","DOI":"10.1109\/ICIP40778.2020.9191080"},{"key":"2881_CR42","doi-asserted-by":"publisher","first-page":"2562","DOI":"10.1109\/LSP.2022.3229571","volume":"29","author":"Z An","year":"2022","unstructured":"An Z, Liu C, Han Y (2022) Effectiveness guided cross-modal information sharing for aligned RGB-T object detection. IEEE Signal Process Lett 29:2562\u20132566","journal-title":"IEEE Signal Process Lett"},{"key":"2881_CR43","doi-asserted-by":"crossref","unstructured":"Yuan M, Wang Y, Wei X (2022) Translation, Scale and Rotation: Cross-Modal Alignment Meets RGBInfrared Vehicle Detection, Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel, Oct, pp. 509\u2013525","DOI":"10.1007\/978-3-031-20077-9_30"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02881-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02881-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02881-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T10:01:39Z","timestamp":1774519299000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02881-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["2881"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02881-w","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,16]]},"assertion":[{"value":"17 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 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":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"117"}}