{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:11:26Z","timestamp":1757617886229,"version":"3.44.0"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T00:00:00Z","timestamp":1740528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["21BTJ071"],"award-info":[{"award-number":["21BTJ071"]}],"id":[{"id":"10.13039\/501100012456","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":[[2025,9]]},"DOI":"10.1007\/s13042-025-02582-4","type":"journal-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T14:05:10Z","timestamp":1740578710000},"page":"5509-5525","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep interactive query design and progressive search for end-to-end detection of tiny object in aerial images"],"prefix":"10.1007","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4891-8622","authenticated-orcid":false,"given":"Chuan","family":"Jin","sequence":"first","affiliation":[]},{"given":"Anqi","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Zhaoying","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Changqing","family":"Tong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,26]]},"reference":[{"issue":"4","key":"2582_CR1","doi-asserted-by":"publisher","first-page":"1685","DOI":"10.1007\/s12145-021-00621-6","volume":"14","author":"D Sara","year":"2021","unstructured":"Sara D, Mandava AK, Kumar A, Duela S, Jude A (2021) Hyperspectral and multispectral image fusion techniques for high resolution applications: a review. Earth Sci Inf 14(4):1685\u20131705","journal-title":"Earth Sci Inf"},{"issue":"12","key":"2582_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3664598","volume":"56","author":"J Leng","year":"2024","unstructured":"Leng J, Ye Y, Mo M, Gao C, Gan J, Xiao B, Gao X (2024) Recent advances for aerial object detection: a survey. ACM Comput Surv 56(12):1\u201336","journal-title":"ACM Comput Surv"},{"issue":"2","key":"2582_CR3","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/S2095-3119(15)61304-1","volume":"16","author":"J Tao","year":"2017","unstructured":"Tao J, Wu W, Yong Z, Yu W, Jiang Y (2017) Mapping winter wheat using phenological feature of peak before winter on the North China plain based on time-series MODIS data. J Integr Agric 16(2):348\u2013359","journal-title":"J Integr Agric"},{"key":"2582_CR4","doi-asserted-by":"publisher","first-page":"126946","DOI":"10.1016\/j.ufug.2020.126946","volume":"57","author":"AR Shahtahmassebi","year":"2021","unstructured":"Shahtahmassebi AR, Li C, Fan Y, Wu Y, Gan M, Wang K, Malik A, Blackburn GA (2021) Remote sensing of urban green spaces: a review. Urban Forestry Urban Green 57:126946","journal-title":"Urban Forestry Urban Green"},{"issue":"11","key":"2582_CR5","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, Du D, Bian X, Fan H, Hu Q, Ling H (2021) Detection and tracking meet drones challenge. IEEE Trans Pattern Anal Mach Intell 44(11):7380\u20137399","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2582_CR6","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.rse.2017.05.001","volume":"196","author":"X Huang","year":"2017","unstructured":"Huang X, Wen D, Li J, Qin R (2017) Multi-level monitoring of subtle urban changes for the megacities of China using high-resolution multi-view satellite imagery. Remote Sens Environ 196:56\u201375","journal-title":"Remote Sens Environ"},{"key":"2582_CR7","doi-asserted-by":"publisher","first-page":"112075","DOI":"10.1016\/j.knosys.2024.112075","volume":"299","author":"S Gu","year":"2024","unstructured":"Gu S, Zhang M, Xiao Q, Shi W (2024) Cascaded matching based on detection box area for multi-object tracking. Knowl Based Syst 299:112075","journal-title":"Knowl Based Syst"},{"key":"2582_CR8","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, vol 25"},{"key":"2582_CR9","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, vol 28"},{"key":"2582_CR10","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) SSD: single shot multibox detector. In: Computer vision\u2014ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14. Springer, Berlin, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2582_CR11","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 conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"2582_CR12","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"2582_CR13","doi-asserted-by":"crossref","unstructured":"Lu P, Jiang T, Li Y, Li X, Chen K, Yang W (2024) RTMO: towards high-performance one-stage real-time multi-person pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1491\u20131500","DOI":"10.1109\/CVPR52733.2024.00148"},{"key":"2582_CR14","doi-asserted-by":"publisher","first-page":"105066","DOI":"10.1016\/j.imavis.2024.105066","volume":"147","author":"J Guo","year":"2024","unstructured":"Guo J, Du H, Hao X, Zhang M (2024) IGIE-NET: cross-modality person re-identification via intermediate modality image generation and discriminative information enhancement. Image Vis Comput 147:105066","journal-title":"Image Vis Comput"},{"key":"2582_CR15","doi-asserted-by":"crossref","unstructured":"Shen Z, Liu Z, Li J, Jiang Y-G, Chen Y, Xue X (2017) DSOD: learning deeply supervised object detectors from scratch. In: Proceedings of the IEEE international conference on computer vision, pp 1919\u20131927","DOI":"10.1109\/ICCV.2017.212"},{"key":"2582_CR16","doi-asserted-by":"crossref","unstructured":"Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 764\u2013773","DOI":"10.1109\/ICCV.2017.89"},{"key":"2582_CR17","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) Centernet: keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"key":"2582_CR18","doi-asserted-by":"crossref","unstructured":"Noh J, Bae W, Lee W, Seo J, Kim G (2019) Better to follow, follow to be better: towards precise supervision of feature super-resolution for small object detection. In: Proceedings of the IEEE\/CVF International conference on computer vision, pp 9725\u20139734","DOI":"10.1109\/ICCV.2019.00982"},{"key":"2582_CR19","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin T-Y, Le QV (2019) NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7036\u20137045","DOI":"10.1109\/CVPR.2019.00720"},{"key":"2582_CR20","doi-asserted-by":"crossref","unstructured":"Yang X, Yang J, Yan J, Zhang Y, Zhang T, Guo Z, Sun X, Fu K (2019) Scrdet: towards more robust detection for small, cluttered and rotated objects. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8232\u20138241","DOI":"10.1109\/ICCV.2019.00832"},{"key":"2582_CR21","doi-asserted-by":"crossref","unstructured":"Wang J, Yang W, Guo H, Zhang R, Xia G-S (2021) Tiny object detection in aerial images. In: 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 3791\u20133798","DOI":"10.1109\/ICPR48806.2021.9413340"},{"key":"2582_CR22","doi-asserted-by":"publisher","first-page":"116675","DOI":"10.1016\/j.image.2022.116675","volume":"104","author":"OC Koyun","year":"2022","unstructured":"Koyun OC, Keser RK, Akkaya IB, T\u00f6reyin BU (2022) Focus-and-detect: a small object detection framework for aerial images. Signal Process Image Commun 104:116675","journal-title":"Signal Process Image Commun"},{"key":"2582_CR23","unstructured":"Borji A, Iranmanesh SM (2019) Empirical upper bound in object detection and more. arXiv preprint arXiv:1911.12451"},{"key":"2582_CR24","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 111:257\u2013276","journal-title":"Proc IEEE"},{"key":"2582_CR25","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision. Springer, Berlin, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2582_CR26","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable detr: deformable transformers for end-to-end object detection. In: International conference on learning representations"},{"key":"2582_CR27","unstructured":"Liu S, Li F, Zhang H, Yang X, Qi X, Su H, Zhu J, Zhang L (2021) Dab-detr: dynamic anchor boxes are better queries for detr. In: International conference on learning representations"},{"key":"2582_CR28","doi-asserted-by":"crossref","unstructured":"Li F, Zhang H, Liu S, Guo J, Ni LM, Zhang L (2022) Dn-detr: accelerate detr training by introducing query denoising. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13619\u201313627","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"2582_CR29","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Computer Vision\u2014ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part V 13. Springer, Berlin, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2582_CR30","doi-asserted-by":"crossref","unstructured":"Xia G-S, Bai X, Ding J, Zhu Z, Belongie S, Luo J, Datcu M, Pelillo M, Zhang L (2018) DOTA: a large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3974\u20133983","DOI":"10.1109\/CVPR.2018.00418"},{"key":"2582_CR31","doi-asserted-by":"crossref","unstructured":"Cao Y, He Z, Wang L, Wang W, Yuan Y, Zhang D, Zhang J, Zhu P, Van\u00a0Gool L, Han J, Hoi S, Hu Q, Liu M (2021) Visdrone-det2021: the vision meets drone object detection challenge results. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2847\u20132854","DOI":"10.1109\/ICCVW54120.2021.00319"},{"key":"2582_CR32","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"2582_CR33","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: etecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2582_CR34","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2582_CR35","doi-asserted-by":"crossref","unstructured":"Lu X, Li B, Yue Y, Li Q, Yan J (2019) Grid R-CNN. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 7363\u20137372","DOI":"10.1109\/CVPR.2019.00754"},{"key":"2582_CR36","doi-asserted-by":"crossref","unstructured":"Hu H, Gu J, Zhang Z, Dai J, Wei Y (2018) Relation networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3588\u20133597","DOI":"10.1109\/CVPR.2018.00378"},{"key":"2582_CR37","unstructured":"Zhang H, Li F, Liu S, Zhang L, Su H, Zhu J, Ni L, Shum H (2022) Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arxiv 2022. arXiv preprint arXiv:2203.03605"},{"key":"2582_CR38","doi-asserted-by":"crossref","unstructured":"Zheng D, Dong W, Hu H, Chen X, Wang Y (2023) Less is more: focus attention for efficient detr. arXiv preprint arXiv:2307.12612","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"2582_CR39","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"2582_CR40","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2582_CR41","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2582_CR42","doi-asserted-by":"publisher","first-page":"119132","DOI":"10.1016\/j.eswa.2022.119132","volume":"214","author":"S Chen","year":"2023","unstructured":"Chen S, Zhao J, Zhou Y, Wang H, Yao R, Zhang L, Xue Y (2023) Info-FPN: an informative feature pyramid network for object detection in remote sensing images. Expert Syst Appl 214:119132","journal-title":"Expert Syst Appl"},{"key":"2582_CR43","doi-asserted-by":"crossref","unstructured":"Wang T, Anwer RM, Cholakkal H, Khan FS, Pang Y, Shao L (2019) Learning rich features at high-speed for single-shot object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1971\u20131980","DOI":"10.1109\/ICCV.2019.00206"},{"key":"2582_CR44","doi-asserted-by":"crossref","unstructured":"Ren J, Chen X, Liu J, Sun W, Pang J, Yan Q, Tai Y-W, Xu L (2017) Accurate single stage detector using recurrent rolling convolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5420\u20135428","DOI":"10.1109\/CVPR.2017.87"},{"key":"2582_CR45","doi-asserted-by":"crossref","unstructured":"Zhang S, Wen L, Bian X, Lei Z, Li SZ (2018) Single-shot refinement neural network for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4203\u20134212","DOI":"10.1109\/CVPR.2018.00442"},{"key":"2582_CR46","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114"},{"key":"2582_CR47","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, vol 27"},{"key":"2582_CR48","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-cnn: Delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2582_CR49","doi-asserted-by":"crossref","unstructured":"Akyon FC, Altinuc SO, Temizel A (2022) Slicing aided hyper inference and fine-tuning for small object detection. In: 2022 IEEE international conference on image processing (ICIP). IEEE, pp 966\u2013970","DOI":"10.1109\/ICIP46576.2022.9897990"},{"key":"2582_CR50","doi-asserted-by":"crossref","unstructured":"De\u00a0Ridder V, Dey B, Blanco V, Halder S, Van\u00a0Waeyenberge B (2023) Improved defect detection and classification method for advanced IC nodes by using slicing aided hyper inference with refinement strategy. arXiv preprint arXiv:2311.11439","DOI":"10.1063\/5.0214058"},{"key":"2582_CR51","doi-asserted-by":"crossref","unstructured":"Sun B, Li B, Cai S, Yuan Y, Zhang C (2021) FSCE: few-shot object detection via contrastive proposal encoding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7352\u20137362","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"2582_CR52","doi-asserted-by":"crossref","unstructured":"Qi Q, Yan Y, Wang H (2023) Class-aware dual-supervised aggregation network for video object detection. IEEE Trans Multimed","DOI":"10.1109\/TMM.2023.3292615"},{"key":"2582_CR53","doi-asserted-by":"crossref","unstructured":"Yuan X, Cheng G, Yan K, Zeng Q, Han J (2023) Small object detection via coarse-to-fine proposal generation and imitation learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6317\u20136327","DOI":"10.1109\/ICCV51070.2023.00581"},{"key":"2582_CR54","doi-asserted-by":"publisher","first-page":"118665","DOI":"10.1016\/j.eswa.2022.118665","volume":"211","author":"J Xiao","year":"2023","unstructured":"Xiao J, Guo H, Zhou J, Zhao T, Yu Q, Chen Y, Wang Z (2023) Tiny object detection with context enhancement and feature purification. Expert Syst Appl 211:118665","journal-title":"Expert Syst Appl"},{"key":"2582_CR55","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.neucom.2020.12.093","volume":"433","author":"J Leng","year":"2021","unstructured":"Leng J, Ren Y, Jiang W, Sun X, Wang Y (2021) Realize your surroundings: exploiting context information for small object detection. Neurocomputing 433:287\u2013299","journal-title":"Neurocomputing"},{"key":"2582_CR56","doi-asserted-by":"crossref","unstructured":"Meng D, Chen X, Fan Z, Zeng G, Li H, Yuan Y, Sun L, Wang J (2021) Conditional detr for fast training convergence. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3651\u20133660","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"2582_CR57","doi-asserted-by":"crossref","unstructured":"Sun P, Zhang R, Jiang Y, Kong T, Xu C, Zhan W, Tomizuka M, Li L, Yuan Z, Wang C, Luo P (2021) Sparse R-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14454\u201314463","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"2582_CR58","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2582_CR59","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, vol 30"},{"key":"2582_CR60","doi-asserted-by":"crossref","unstructured":"Oksuz K, Cam BC, Akbas E, Kalkan S (2018) Localization recall precision (LRP): a new performance metric for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 504\u2013519","DOI":"10.1007\/978-3-030-01234-2_31"},{"key":"2582_CR61","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767"},{"issue":"4","key":"2582_CR62","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s11554-024-01485-x","volume":"21","author":"L Zihan","year":"2024","unstructured":"Zihan L, Xu W, Linyun Z, Panlin Y (2024) Lightyolo-s: a lightweight algorithm for detecting small targets. J Real-Time Image Process 21(4):111","journal-title":"J Real-Time Image Process"},{"issue":"2","key":"2582_CR63","doi-asserted-by":"publisher","first-page":"2384","DOI":"10.1109\/TPAMI.2022.3166956","volume":"45","author":"X Yang","year":"2022","unstructured":"Yang X, Yan J, Liao W, Yang X, Tang J, He T (2022) Scrdet++: detecting small, cluttered and rotated objects via instance-level feature denoising and rotation loss smoothing. IEEE Trans Pattern Anal Mach Intell 45(2):2384\u20132399","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2582_CR64","doi-asserted-by":"publisher","first-page":"110097","DOI":"10.1016\/j.knosys.2022.110097","volume":"260","author":"X Chen","year":"2023","unstructured":"Chen X, Wang C, Li Z, Liu M, Li Q, Qi H, Ma D, Li Z, Wang Y (2023) Coupled global-local object detection for large VHR aerial images. Knowl-Based Syst 260:110097","journal-title":"Knowl-Based Syst"},{"issue":"24","key":"2582_CR65","doi-asserted-by":"publisher","first-page":"2930","DOI":"10.3390\/rs11242930","volume":"11","author":"J Wang","year":"2019","unstructured":"Wang J, Ding J, Guo H, Cheng W, Pan T, Yang W (2019) Mask OBB: a semantic attention-based mask oriented bounding box representation for multi-category object detection in aerial images. Remote Sens 11(24):2930","journal-title":"Remote Sens"},{"key":"2582_CR66","doi-asserted-by":"publisher","first-page":"108315","DOI":"10.1016\/j.patcog.2021.108315","volume":"122","author":"Q Lin","year":"2022","unstructured":"Lin Q, Long C, Zhao J, Fu G, Yuan Z (2022) DDBN: dual detection branch network for semantic diversity predictions. Pattern Recogn 122:108315","journal-title":"Pattern Recogn"},{"key":"2582_CR67","doi-asserted-by":"publisher","first-page":"2721","DOI":"10.1109\/JSTARS.2022.3158903","volume":"15","author":"Z Wei","year":"2022","unstructured":"Wei Z, Liang D, Zhang D, Zhang L, Geng Q, Wei M, Zhou H (2022) Learning calibrated-guidance for object detection in aerial images. IEEE J Sel Top Appl Earth Observ Remote Sens 15:2721\u20132733","journal-title":"IEEE J Sel Top Appl Earth Observ Remote Sens"},{"key":"2582_CR68","doi-asserted-by":"crossref","unstructured":"Min X, Zhou W, Hu R, Wu Y, Pang Y, Yi J (2024) Lwuavdet: a lightweight UAV object detection network on edge devices. IEEE Internet Things J","DOI":"10.1109\/JIOT.2024.3388045"},{"key":"2582_CR69","doi-asserted-by":"crossref","unstructured":"Zhou Z, Zhu Y (2024) Kldet: detecting tiny objects in remote sensing images via Kullback\u2013Leibler divergence. IEEE Trans Geosci Remote Sens","DOI":"10.1109\/TGRS.2024.3382099"},{"key":"2582_CR70","doi-asserted-by":"crossref","unstructured":"Davis J, Goadrich M (2006) The relationship between precision-recall and ROC curves. In: Proceedings of the 23rd international conference on machine learning, pp 233\u2013240","DOI":"10.1145\/1143844.1143874"},{"key":"2582_CR71","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham M, Eslami SA, Van Gool L, Williams CK, Winn J, Zisserman A (2015) The pascal visual object classes challenge: a retrospective. Int J Comput Vis 111:98\u2013136","journal-title":"Int J Comput Vis"},{"key":"2582_CR72","doi-asserted-by":"crossref","unstructured":"Li Z, Peng C, Yu G, Zhang X, Deng Y, Sun J (2018) DetNet: a backbone network for object detection. arXiv e-prints, arXiv:1804.06215","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"2582_CR73","unstructured":"Li Z, Peng C, Yu G, Zhang X, Deng Y, Sun J (2017) Light-head r-cnn: In defense of two-stage object detector. arXiv preprint arXiv:1711.07264"},{"key":"2582_CR74","doi-asserted-by":"crossref","unstructured":"Li Y, Chen Y, Wang N, Zhang Z (2019) Scale-aware trident networks for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6054\u20136063","DOI":"10.1109\/ICCV.2019.00615"},{"key":"2582_CR75","doi-asserted-by":"crossref","unstructured":"Yang Z, Liu S, Hu H, Wang L, Lin S (2019) Reppoints: point set representation for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9657\u20139666","DOI":"10.1109\/ICCV.2019.00975"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02582-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02582-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02582-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:59:22Z","timestamp":1757156362000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02582-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,26]]},"references-count":75,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["2582"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02582-4","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2025,2,26]]},"assertion":[{"value":"14 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 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 conflict of interest.","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.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The participant has consented to the submission of the case report to the journal.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}