{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T17:22:29Z","timestamp":1793035349061,"version":"4.5.0"},"reference-count":259,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:00Z","timestamp":1740182400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:00:00Z","timestamp":1740182400000},"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":["Knowl Inf Syst"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s10115-025-02375-9","type":"journal-article","created":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T11:51:03Z","timestamp":1740225063000},"page":"3825-3913","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Comprehensive review of deep learning-based tiny object detection: challenges, strategies, and future directions"],"prefix":"10.1007","volume":"67","author":[{"given":"Muhamad","family":"Muzammul","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,22]]},"reference":[{"key":"2375_CR1","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot MultiBox detector. In: European conference on computer vision, pp 21\u201337. Springer, Cham","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2375_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 conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"2375_CR3","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Zitnick CL (2014) Microsoft COCO: common objects in context. In: European conference on computer vision, pp 740\u2013755. Springer, Cham","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2375_CR4","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"},{"issue":"7553","key":"2375_CR5","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"2375_CR6","doi-asserted-by":"crossref","unstructured":"Zhou P, Ni B, Geng C, Hu J, Xu Y (2019) Scale-transferrable object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 528\u2013537","DOI":"10.1109\/CVPR.2018.00062"},{"key":"2375_CR7","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting 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":"2375_CR8","doi-asserted-by":"crossref","unstructured":"Zhu X, Hu H, Lin S, Dai J (2019) Deformable ConvNets v2: more deformable, better results. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9308\u20139316","DOI":"10.1109\/CVPR.2019.00953"},{"key":"2375_CR9","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":"2375_CR10","doi-asserted-by":"crossref","unstructured":"Qin Z, Li Z, Zhang Z, Bao Y, Yu G, Peng Y, Sun J (2019) Thundernet: towards real-time generic object detection on mobile devices. In: ICCV, pp 6717\u20136726","DOI":"10.1109\/ICCV.2019.00682"},{"key":"2375_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: CVPR, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"2375_CR12","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint http:\/\/arxiv.org\/abs\/1804.02767"},{"key":"2375_CR13","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: ICCV, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"2375_CR14","unstructured":"Zhou X, Wang D, Krahenbuhl P (2019) Objects as points. arXiv preprint http:\/\/arxiv.org\/abs\/1904.07850"},{"key":"2375_CR15","unstructured":"Zhu P, Wen L, Bian X, Haibin L, Yan Q (2018) Vision meets drones: a challenge. arXiv preprint http:\/\/arxiv.org\/abs\/1804.07437"},{"key":"2375_CR16","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, pp 91\u201399"},{"key":"2375_CR17","unstructured":"Lam M, Bosch M, Zhu Z, Dolan JM, Kochenderfer MJ (2018) xView: objects in context in overhead imagery. arXiv preprint http:\/\/arxiv.org\/abs\/1802.07856"},{"key":"2375_CR18","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2375_CR19","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"2375_CR20","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In: 2015 IEEE international conference on computer vision (ICCV), pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"2375_CR21","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren S, He K, Girshick R, Sun J (2016) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2375_CR22","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"2375_CR23","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, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37:1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2375_CR24","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r 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 936\u2013944","DOI":"10.1109\/CVPR.2017.106"},{"key":"2375_CR25","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY et al. (2016) SSD: single shot multibox detector. In: European conference on computer vision, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2375_CR26","doi-asserted-by":"crossref","unstructured":"Zhu C, He Y, Savvides M (2019) Feature selective anchor-free module for single-shot object detection. In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 840\u2013849","DOI":"10.1109\/CVPR.2019.00093"},{"key":"2375_CR27","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) CornerNet: detecting objects as paired keypoints. In: European conference on computer vision, pp 765\u2013781","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2375_CR28","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: fully convolutional one-stage object detection. In: 2019 IEEE\/CVF international conference on computer vision (ICCV), pp 9626\u20139635","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2375_CR29","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P, Objects as points, preprint http:\/\/arxiv.org\/abs\/1904.07850"},{"key":"2375_CR30","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"Z Zhao","year":"2019","unstructured":"Zhao Z, Zheng P, Xu ST, Wu X (2019) Object detection with deep learning: a review. IEEE Trans Neural Netw Learn Syst 30:3212\u20133232","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2375_CR31","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.isprsjprs.2019.11.023","volume":"159","author":"K Li","year":"2020","unstructured":"Li K, Wan G, Cheng G, Meng L, Han J (2020) Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J Photogramm Remote Sens 159:296\u2013307","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"2375_CR32","doi-asserted-by":"publisher","unstructured":"Gong Y, Yu X, Ding Y, Peng X, Zhao J, Han Z (2021) Effective fusion factor in FPN for tiny object detection. In: 2021 IEEE winter conference on applications of computer vision (WACV), pp 1159\u20131167. https:\/\/doi.org\/10.1109\/WACV48630.2021.00120","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"2375_CR33","doi-asserted-by":"publisher","first-page":"128837","DOI":"10.1109\/ACCESS.2019.2939201","volume":"7","author":"L Jiao","year":"2019","unstructured":"Jiao L, Zhang F, Liu F, Yang S, Li L, Feng Z et al (2019) A survey of deep learning-based object detection. IEEE Access 7:128837\u2013128868","journal-title":"IEEE Access"},{"key":"2375_CR34","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.cviu.2019.03.001","volume":"182","author":"SD Khan","year":"2019","unstructured":"Khan SD, Ullah H (2019) A survey of advances in vision-based vehicle re-identification. Comput Vis Image Underst 182:50\u201363","journal-title":"Comput Vis Image Underst"},{"issue":"8","key":"2375_CR35","doi-asserted-by":"publisher","first-page":"9489","DOI":"10.1007\/s13369-021-06288-x","volume":"47","author":"SD Khan","year":"2022","unstructured":"Khan SD, Alarabi L, Basalamah S (2022) A unified deep learning framework of multi-scale detectors for geo-spatial object detection in high-resolution satellite images. Arab J Sci Eng 47(8):9489\u20139504","journal-title":"Arab J Sci Eng"},{"key":"2375_CR36","unstructured":"Oksuz K, Cam BC, Kalkan S, Akbas E, Imbalance problems in object detection: a review, preprint, http:\/\/arxiv.org\/abs\/1909.00169"},{"key":"2375_CR37","unstructured":"Rekavandi AM, Xu L, Boussaid F, Seghouane AK, Hoefs S, Bennamoun M, A guide to image and video based small object detection using deep learning: case study of maritime surveillance, preprint, http:\/\/arxiv.org\/abs\/2207.12926"},{"key":"2375_CR38","doi-asserted-by":"publisher","first-page":"104019","DOI":"10.1016\/j.jag.2024.104019","volume":"132","author":"P Yan","year":"2024","unstructured":"Yan P, Zhao J, Hou R, Duan X, Cai S, Wang X (2024) Clustered remote sensing target distribution detection aided by density-based spatial analysis. Int J Appl Earth Obs Geoinf 132:104019. https:\/\/doi.org\/10.1016\/j.jag.2024.104019","journal-title":"Int J Appl Earth Obs Geoinf"},{"key":"2375_CR39","doi-asserted-by":"publisher","first-page":"103910","DOI":"10.1016\/j.imavis.2020.103910","volume":"97","author":"K Tong","year":"2020","unstructured":"Tong K, Wu Y, Zhou F (2020) Recent advances in small object detection based on deep learning: A review. Image Vis Comput 97:103910","journal-title":"Image Vis Comput"},{"key":"2375_CR40","doi-asserted-by":"crossref","unstructured":"Zhu P, Wen L, Du D, Bian X, Ling H, Hu Q, Ma Z (2018) VisDrone-VDT2018: the vision meets drone video detection and tracking challenge results. In: Proceedings of the European conference on computer vision (ECCV) workshops","DOI":"10.1007\/978-3-030-11021-5_29"},{"key":"2375_CR41","doi-asserted-by":"publisher","first-page":"104471","DOI":"10.1016\/j.imavis.2022.104471","volume":"123","author":"K Tong","year":"2022","unstructured":"Tong K, Wu Y (2022) Deep learning-based detection from the perspective of small or tiny objects: a survey. Image Vis Comput 123:104471","journal-title":"Image Vis Comput"},{"key":"2375_CR42","unstructured":"Chen K, Wang J, Pang J, Cao Y, Xiong Y, Li X et al MMDetection: open mmlab detection toolbox and benchmark, preprint, http:\/\/arxiv.org\/abs\/1906.07155"},{"key":"2375_CR43","unstructured":"Menezes AG, de Moura G, Alves C, de Carvalho ACPLF, Continual object detection: a review of definitions, strategies, and challenges, preprint, http:\/\/arxiv.org\/abs\/2205.15445"},{"key":"2375_CR44","doi-asserted-by":"publisher","first-page":"3195","DOI":"10.1109\/TNNLS.2021.3053249","volume":"33","author":"L Jiao","year":"2022","unstructured":"Jiao L, Zhang R, Liu F, Yang S, Hou B, Li L et al (2022) New generation deep learning for video object detection: a survey. IEEE Trans Neural Netw Learn Syst 33:3195\u20133215","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2375_CR45","doi-asserted-by":"crossref","unstructured":"Ku J, Pon AD, Waslander SL (2019) Monocular 3d object detection leveraging accurate proposals and shape reconstruction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11867\u201311876","DOI":"10.1109\/CVPR.2019.01214"},{"key":"2375_CR46","doi-asserted-by":"publisher","first-page":"114602","DOI":"10.1016\/j.eswa.2021.114602","volume":"172","author":"Y Liu","year":"2021","unstructured":"Liu Y, Sun P, Wergeles N, Shang Y (2021) A survey and performance evaluation of deep learning methods for small object detection. Expert Syst Appl 172:114602","journal-title":"Expert Syst Appl"},{"key":"2375_CR47","unstructured":"Cheng G, Yuan X, Yao X, Yan K, Zeng Q, Han J, Towards large-scale small object detection: survey and benchmarks, preprint, http:\/\/arxiv.org\/abs\/2207.14096"},{"key":"2375_CR48","doi-asserted-by":"crossref","unstructured":"Eggert C, Brehm S, Winschel A, Zecha D, Lienhart R (2017) A closer look: small object detection in faster R-CNN. In: 2017 IEEE international conference on multimedia and expo (ICME), pp 421\u2013426","DOI":"10.1109\/ICME.2017.8019550"},{"key":"2375_CR49","first-page":"214","volume":"10115","author":"C Chen","year":"2017","unstructured":"Chen C, Liu MY, Tuzel O, Xiao J (2017) R-CNN for small object detection. Asian Conf Comput Vis 10115:214\u2013230","journal-title":"Asian Conf Comput Vis"},{"key":"2375_CR50","doi-asserted-by":"crossref","unstructured":"Yang S, Luo P, Loy CC, Tang X (2016) WIDER FACE: a face detection benchmark. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 5525\u20135533","DOI":"10.1109\/CVPR.2016.596"},{"key":"2375_CR51","doi-asserted-by":"crossref","unstructured":"Chan AB, Liang ZSJ, Vasconcelos N (2008) Privacy preserving crowd monitoring: counting people without people models or tracking. In: 2008 IEEE conference on computer vision and pattern recognition, pp 1\u20137","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"2375_CR52","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D et al Microsoft COCO: common objects in context. In: European conference on computer vision, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"12","key":"2375_CR53","doi-asserted-by":"publisher","first-page":"6077","DOI":"10.1109\/TIP.2019.2922095","volume":"28","author":"Z Fu","year":"2019","unstructured":"Fu Z, Chen Y, Yong H, Jiang R, Zhang L, Hua XS (2019) Foreground gating and background refining network for surveillance object detection. IEEE Trans Image Process 28(12):6077\u20136090","journal-title":"IEEE Trans Image Process"},{"key":"2375_CR54","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2375_CR55","doi-asserted-by":"crossref","unstructured":"Zhang H, Wu C, Zhang Z, Zhu Y, Lin H, Zhang Z, Sun Y, He T, Mueller J, Manmatha R et al (2022) Resnest: split-attention networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2736\u20132746","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"2375_CR56","doi-asserted-by":"crossref","unstructured":"Dai Y, Gieseke F, Oehmcke S, Wu Y, Barnard K (2021) Attentional feature fusion. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 3560\u20133569","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"2375_CR57","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2009","unstructured":"Everingham M, Gool LV, Williams CKI, Winn JM, Zisserman A (2009) The Pascal visual object classes (VOC) challenge. Int J Comput Vis 88:303\u2013338","journal-title":"Int J Comput Vis"},{"issue":"12","key":"2375_CR58","doi-asserted-by":"publisher","first-page":"4996","DOI":"10.1109\/TIP.2013.2281420","volume":"22","author":"C Gao","year":"2013","unstructured":"Gao C, Meng D, Yang Y, Wang Y, Zhou X, Hauptmann AG (2013) Infrared patch-image model for small target detection in a single image. IEEE Trans Image Process 22(12):4996\u20135009","journal-title":"IEEE Trans Image Process"},{"key":"2375_CR59","doi-asserted-by":"crossref","unstructured":"Chen C, Zhang Y, Lv Q, Wei S, Wang X, Sun X, Dong J (2019) Rrnet: a hybrid detector for object detection in drone-captured images. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops","DOI":"10.1109\/ICCVW.2019.00018"},{"key":"2375_CR60","doi-asserted-by":"crossref","unstructured":"Kisantal M, Wojna Z, Murawski J, Naruniec J, Cho K (2019) Augmentation for small object detection. arXiv preprint http:\/\/arxiv.org\/abs\/1902.07296","DOI":"10.5121\/csit.2019.91713"},{"key":"2375_CR61","unstructured":"Zhao M, Cheng L, Yang X, Feng P, Liu L, Wu N (2019) Tbc-net: a real-time detector for infrared small target detection using semantic constraint. arXiv preprint http:\/\/arxiv.org\/abs\/2001.05852"},{"key":"2375_CR62","doi-asserted-by":"crossref","unstructured":"Li X, Wang W, Hu X, Yang J (2019) Selective kernel networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 510\u2013519","DOI":"10.1109\/CVPR.2019.00060"},{"key":"2375_CR63","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.infrared.2019.02.012","volume":"98","author":"T Yu","year":"2019","unstructured":"Yu T, Mo B, Liu F, Qi H, Liu Y (2019) Robust thermal infrared object tracking with continuous correlation filters and adaptive feature fusion. Infrared Phys Technol 98:69\u201381. https:\/\/doi.org\/10.1016\/j.infrared.2019.02.012","journal-title":"Infrared Phys Technol"},{"key":"2375_CR64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3266837","author":"D Yuan","year":"2023","unstructured":"Yuan D, Chang X, Liu Q, Yang Y, Wang D, Shu M, He Z, Shi G (2023) Active learning for deep visual tracking. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2023.3266837","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2375_CR65","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2375_CR66","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: ICLR"},{"issue":"2","key":"2375_CR67","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu L, Ouyang W, Wang X, Fieguth P, Chen J, Liu X, Pietikainen M (2020) Deep learning for generic object detection: a survey. IJCV 128(2):261\u2013318","journal-title":"IJCV"},{"key":"2375_CR68","unstructured":"Chen Y, Zhang P, Li Z, Li Y, Zhang X, Qi L, Sun J, Jia J (2020) Dynamic scale training for object detection. Journal Article"},{"key":"2375_CR69","doi-asserted-by":"crossref","unstructured":"Lin T-Y et al (2017) Focal loss for dense object detection. In: ICCV, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"2375_CR70","unstructured":"Ren S et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS, vol 28"},{"issue":"3","key":"2375_CR71","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1109\/LGRS.2020.2975541","volume":"18","author":"G Cheng","year":"2021","unstructured":"Cheng G, Si Y, Hong H, Yao X, Guo L (2021) Cross-scale feature fusion for object detection in optical remote sensing images. IEEE Geosci Remote Sens Lett 18(3):431\u2013435","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"2375_CR72","doi-asserted-by":"crossref","unstructured":"Shi X, Xia Z, Li Y, Wang X, Niu Y (2024) Fusing graph structural information with pre-trained generative model for knowledge graph-to-text generation. Knowl Inf Syst 1\u201322","DOI":"10.1007\/s10115-024-02235-y"},{"issue":"5","key":"2375_CR73","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2021","unstructured":"Cai Z, Vasconcelos N (2021) Cascade R-CNN: high quality object detection and instance segmentation. TPAMI 43(5):1483\u20131498","journal-title":"TPAMI"},{"key":"2375_CR74","doi-asserted-by":"crossref","unstructured":"Lin T, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL (2014) Microsoft COCO: common objects in context. In: ECCV, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"9","key":"2375_CR75","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, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. TPAMI 37(9):1904\u20131916","journal-title":"TPAMI"},{"issue":"2","key":"2375_CR76","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"T Lin","year":"2020","unstructured":"Lin T, Goyal P, Girshick R, He K, Dollar P (2020) Focal loss for dense object detection. TPAMI 42(2):318\u2013327","journal-title":"TPAMI"},{"key":"2375_CR77","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: CVPR, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"2375_CR78","doi-asserted-by":"crossref","unstructured":"Liu W et al SSD: single shot multibox detector. In: ECCV, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"issue":"4","key":"2375_CR79","first-page":"1922","volume":"44","author":"Z Tian","year":"2022","unstructured":"Tian Z, Shen C, Chen H, He T (2022) FCOS: a simple and strong anchor-free object detector. TPAMI 44(4):1922\u20131933","journal-title":"TPAMI"},{"key":"2375_CR80","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. arXiv preprint http:\/\/arxiv.org\/abs\/1904.07850"},{"key":"2375_CR81","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: ICCV, pp 6569\u20136578","DOI":"10.1109\/ICCV.2019.00667"},{"key":"2375_CR82","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: ECCV, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2375_CR83","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Presented at the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2375_CR84","doi-asserted-by":"crossref","unstructured":"Kim K, Lee HS (2020) Probabilistic anchor assignment with IoU prediction for object detection. In: ECCV, pp 355\u2013371","DOI":"10.1007\/978-3-030-58595-2_22"},{"key":"2375_CR85","doi-asserted-by":"crossref","unstructured":"Kisantal M, Wojna Z, Naruniec J, Murawski J, Cho K (2019) Augmentation for small object detection, arXiv preprint http:\/\/arxiv.org\/abs\/1902.07296","DOI":"10.5121\/csit.2019.91713"},{"issue":"19","key":"2375_CR86","doi-asserted-by":"publisher","first-page":"7663","DOI":"10.3390\/s22197663","volume":"22","author":"X Wang","year":"2022","unstructured":"Wang X, Zhu D, Yan Y (2022) Towards efficient detection for small objects via attention-guided detection network and data augmentation. Sensors 22(19):7663","journal-title":"Sensors"},{"key":"2375_CR87","doi-asserted-by":"publisher","first-page":"108998","DOI":"10.1016\/j.patcog.2022.108998","volume":"133","author":"B Bosquet","year":"2023","unstructured":"Bosquet B et al (2023) A full data augmentation pipeline for small object detection based on generative adversarial networks. Pattern Recogn 133:108998","journal-title":"Pattern Recogn"},{"key":"2375_CR88","doi-asserted-by":"crossref","unstructured":"Zhang S, Zhu X, Lei Z, Shi H, Wang X, Li SZ (2017) S3FD: single shot scale-invariant face detector. In: ICCV, pp 192\u2013201","DOI":"10.1109\/ICCV.2017.30"},{"key":"2375_CR89","doi-asserted-by":"crossref","unstructured":"Zhu C, Tao R, Luu K, Savvides M (2018) Seeing small faces from robust anchor\u2019s perspective. In: CVPR, pp 5127\u20135136","DOI":"10.1109\/CVPR.2018.00538"},{"key":"2375_CR90","doi-asserted-by":"crossref","unstructured":"Xu C, Wang J, Yang W, Yu L (2021) Dot distance for tiny object detection in aerial images. In: CVPRW, pp 1192\u20131201","DOI":"10.1109\/CVPRW53098.2021.00130"},{"key":"2375_CR91","doi-asserted-by":"crossref","unstructured":"Zhang H, Dana K, Shi J, Zhang Z, Wang X, Tyagi A, Agrawal A (2018) Context encoding for semantic segmentation. In: CVPR, pp 7151\u20137160","DOI":"10.1109\/CVPR.2018.00747"},{"key":"2375_CR92","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: ICCV, pp 8231\u20138240","DOI":"10.1109\/ICCV.2019.00832"},{"key":"2375_CR93","doi-asserted-by":"crossref","unstructured":"Wang X, Yang Z, Wu J, Zhao Y, Zhou Z (2021) EdgeDuet: tiling small object detection for edge-assisted autonomous mobile vision. In: INFOCOM, pp 1\u201310","DOI":"10.1109\/INFOCOM42981.2021.9488843"},{"key":"2375_CR94","doi-asserted-by":"crossref","unstructured":"Lu X, Ji J, Xing Z, Miao Q (2021) Attention and feature fusion SSD for remote sensing object detection. IEEE Trans Instrum Meas 1\u20139","DOI":"10.1109\/TIM.2021.3052575"},{"key":"2375_CR95","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2020.3011973","volume":"19","author":"M Hong","year":"2021","unstructured":"Hong M, Li S, Yang Y, Zhu F, Zhao Q, Lu L (2021) SSPNet: scale selection pyramid network for tiny person detection from UAV images. IEEE Geosci Remote Sens Lett 19:1\u20135","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"2375_CR96","doi-asserted-by":"crossref","unstructured":"Kim JU, Park S, Ro YM (2021) Robust small-scale pedestrian detection with cued recall via memory learning. In: ICCV, pp 3030\u20133039","DOI":"10.1109\/ICCV48922.2021.00304"},{"key":"2375_CR97","unstructured":"Goodfellow IJ et al (2014) Generative adversarial nets. In: NeurIPS, pp 2672\u20132680"},{"issue":"9","key":"2375_CR98","doi-asserted-by":"publisher","first-page":"1854","DOI":"10.3390\/rs13091854","volume":"13","author":"SA Bashir","year":"2021","unstructured":"Bashir SA, Wang Y (2021) Small object detection in remote sensing images with residual feature aggregation-based super-resolution and object detector network. Remote Sens 13(9):1854","journal-title":"Remote Sens"},{"key":"2375_CR99","doi-asserted-by":"crossref","unstructured":"Na B, Fox GC (2018) Object detection by a super-resolution method and a convolutional neural networks. In: BigData, pp 2263\u20132269","DOI":"10.1109\/BigData.2018.8622135"},{"key":"2375_CR100","doi-asserted-by":"crossref","unstructured":"Liu Z et al (2022) A convnet for the 2020s. In: CVPR, pp 11976\u201311986","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2375_CR101","doi-asserted-by":"crossref","unstructured":"Chen C, Liu M-Y, Tuzel O, Xiao J (2016) R-CNN for small object detection. In: ACCV, pp 214\u2013230","DOI":"10.1007\/978-3-319-54193-8_14"},{"key":"2375_CR102","doi-asserted-by":"crossref","unstructured":"Wu J, Zhou C, Zhang Q, Yang M, Yuan J (2020) Self-mimic learning for small-scale pedestrian detection. In: ACM MM, pp 2012\u20132020","DOI":"10.1145\/3394171.3413634"},{"issue":"2","key":"2375_CR103","first-page":"380","volume":"22","author":"S Zhang","year":"2020","unstructured":"Zhang S, Xie Y, Wan J, Xia H, Li SZ, Guo G (2020) WiderPerson: a diverse dataset for dense pedestrian detection in the wild. TMM 22(2):380\u2013393","journal-title":"TMM"},{"issue":"12","key":"2375_CR104","doi-asserted-by":"publisher","first-page":"10015","DOI":"10.1109\/TGRS.2019.2930982","volume":"57","author":"G Zhang","year":"2019","unstructured":"Zhang G, Lu S, Zhang W (2019) AD-Net: a context-aware detection network for objects in remote sensing imagery. IEEE Trans Geosci Remote Sens 57(12):10015\u201310024","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"2375_CR105","doi-asserted-by":"crossref","unstructured":"Duan C, Wei Z, Zhang C, Qu S, Wang H (2021) Coarse-grained density map guided object detection in aerial images. In: ICCVW, pp 2789\u20132798","DOI":"10.1109\/ICCVW54120.2021.00313"},{"key":"2375_CR106","doi-asserted-by":"publisher","first-page":"2148","DOI":"10.1109\/JSTARS.2020.3046482","volume":"14","author":"Y Li","year":"2021","unstructured":"Li Y, Huang Q, Pei X, Chen Y, Jiao L, Shang R (2021) Cross-layer attention network for small object detection in remote sensing imagery. IEEE J Sel Topics Appl Earth Observ 14:2148\u20132161","journal-title":"IEEE J Sel Topics Appl Earth Observ"},{"key":"2375_CR107","unstructured":"Wang J, Yuan Y, Yu G (2017) Face attention network: an effective face detector for the occluded faces. arXiv preprint http:\/\/arxiv.org\/abs\/1711.07246"},{"key":"2375_CR108","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. arXiv preprint http:\/\/arxiv.org\/abs\/1804.02767"},{"key":"2375_CR109","doi-asserted-by":"crossref","unstructured":"Yang F, Choi W, Lin Y (2016) Exploit all the layers: fast and accurate CNN object detector with scale-dependent pooling and cascaded rejection classifiers. In: CVPR, pp 2129\u20132137","DOI":"10.1109\/CVPR.2016.234"},{"issue":"4","key":"2375_CR110","first-page":"985","volume":"20","author":"J Li","year":"2017","unstructured":"Li J, Liang X, Shen S, Xu T, Feng J, Yan S (2017) Scale-aware Fast R-CNN for pedestrian detection. TMM 20(4):985\u2013996","journal-title":"TMM"},{"key":"2375_CR111","doi-asserted-by":"crossref","unstructured":"Zhou P, Ni B, Geng C, Hu J, Xu Y, (2018) Scale-transferrable object detection. In: CVPR, pp 528\u2013537","DOI":"10.1109\/CVPR.2018.00062"},{"issue":"2","key":"2375_CR112","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 CK, Winn J, Zisserman A (2010) The PASCAL Visual Object Classes (VOC) challenge. IJCV 88(2):303\u2013338","journal-title":"IJCV"},{"key":"2375_CR113","doi-asserted-by":"crossref","unstructured":"Gong Y, Yu X, Ding Y, Peng X, Zhao J, Han Z (2021) Effective fusion factor in FPN for tiny object detection. In: WACV, pp 1159\u20131167","DOI":"10.1109\/WACV48630.2021.00120"},{"issue":"6","key":"2375_CR114","first-page":"1758","volume":"30","author":"X Liang","year":"2020","unstructured":"Liang X, Zhang J, Zhuo L, Li Y, Tian Q (2020) Small object detection in unmanned aerial vehicle images using feature fusion and scaling-based single shot detector with spatial context analysis. TCSVT 30(6):1758\u20131770","journal-title":"TCSVT"},{"issue":"3","key":"2375_CR115","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1109\/TITS.2018.2838132","volume":"20","author":"X Hu","year":"2019","unstructured":"Hu X, Xu X, Xiao Y, Chen H, He S, Qin J, Heng P-A (2019) Sinet: A scale-insensitive convolutional neural network for fast vehicle detection. IEEE Trans Intell Transp Syst 20(3):1010\u20131019","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2375_CR116","doi-asserted-by":"crossref","unstructured":"Tang X, Du DK, He Z, Liu J (2018) PyramidBox: a context-assisted single shot face detector. In: ECCV, pp 812\u2013828","DOI":"10.1007\/978-3-030-01240-3_49"},{"key":"2375_CR117","doi-asserted-by":"crossref","unstructured":"Bell S, Zitnick CL, Bala K, Girshick R (2016) Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks. In: CVPR, pp 2874\u20132883","DOI":"10.1109\/CVPR.2016.314"},{"issue":"8","key":"2375_CR118","doi-asserted-by":"publisher","first-page":"1844","DOI":"10.1109\/TPAMI.2019.2897684","volume":"41","author":"M Braun","year":"2019","unstructured":"Braun M, Krebs S, Flohr F, Gavrila DM (2019) EuroCity persons: a novel benchmark for person detection in traffic scenes. TPAMI 41(8):1844\u20131861","journal-title":"TPAMI"},{"key":"2375_CR119","unstructured":"Zhou X, Wang D, Krahenbuhl P (2019) Objects as points, arXiv preprint http:\/\/arxiv.org\/abs\/1904.07850"},{"key":"2375_CR120","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"},{"key":"2375_CR121","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1023\/A:1023052124951","volume":"53","author":"A Torralba","year":"2003","unstructured":"Torralba A (2003) Contextual priming for object detection. Int J Comput Vis 53:169\u2013191","journal-title":"Int J Comput Vis"},{"key":"2375_CR122","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting 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":"2375_CR123","first-page":"13564","volume":"33","author":"C Chi","year":"2020","unstructured":"Chi C, Wei F, Hu H (2020) Relationnet++: bridging visual representations for object detection via transformer decoder. Adv Neural Inf Process Syst 33:13564\u201313574","journal-title":"Adv Neural Inf Process Syst"},{"key":"2375_CR124","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2022) CenterNet++ for object detection. arXiv preprint http:\/\/arxiv.org\/abs\/2204.08394"},{"key":"2375_CR125","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2021) Deformable DETR: deformable transformers for end-to-end object detection. In: ICLR"},{"key":"2375_CR126","unstructured":"Song H, Sun D, Chun S, Jampani V, Han D, Heo B, Kim W, Yang M-H (2022) ViDt: an efficient and effective fully transformer-based object detector. arXiv preprint http:\/\/arxiv.org\/abs\/2110.03921"},{"key":"2375_CR127","doi-asserted-by":"crossref","unstructured":"Dai X, Chen Y, Yang J, Zhang P, Yuan L, Zhang L (2021) Dynamic DETR: end-to-end object detection with dynamic attention. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2988\u20132997","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"2375_CR128","unstructured":"Ma T, Mao M, Zheng H, Gao P, Wang X, Han S, Ding E, Zhang B, Doermann D (2021) Oriented object detection with transformer. arXiv preprint http:\/\/arxiv.org\/abs\/2106.03146"},{"key":"2375_CR129","doi-asserted-by":"crossref","unstructured":"Wang Y, Zhang X, Yang T, Sun J (2022) Anchor DETR: query design for transformer-based object detection. In: AAAI","DOI":"10.1609\/aaai.v36i3.20158"},{"issue":"1","key":"2375_CR130","first-page":"185","volume":"36","author":"X Cao","year":"2022","unstructured":"Cao X, Yuan P, Feng B, Niu K (2022) CF-DETR: coarse-to-fine transformers for end-to-end object detection. Proc AAAI Conf Artif Intell 36(1):185\u2013193","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"18","key":"2375_CR131","doi-asserted-by":"publisher","first-page":"6993","DOI":"10.3390\/s22186993","volume":"22","author":"W Xu","year":"2022","unstructured":"Xu W, Zhang C, Wang Q, Dai P (2022) FEA-swin: foreground enhancement attention swin transformer network for accurate UAV-based dense object detection. Sensors 22(18):6993","journal-title":"Sensors"},{"key":"2375_CR132","doi-asserted-by":"crossref","unstructured":"Lin T-Y et al (2017) Focal loss for dense object detection. In: ICCV","DOI":"10.1109\/ICCV.2017.324"},{"key":"2375_CR133","unstructured":"Liang T et al (2021) Conformer: local features coupling global representations for visual recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision"},{"issue":"12","key":"2375_CR134","doi-asserted-by":"publisher","first-page":"2861","DOI":"10.3390\/rs14122861","volume":"14","author":"Z Peng","year":"2022","unstructured":"Peng Z et al (2022) Swin-transformer-enabled Yolov5 with attention mechanism for small object detection. Remote Sens 14(12):2861","journal-title":"Remote Sens"},{"key":"2375_CR135","doi-asserted-by":"crossref","unstructured":"Xue J et al (2022) Dual network structure with interweaved global-local feature hierarchy for transformer-based object detection. IEEE J Sel Top Appl Earth Observ Remote Sens","DOI":"10.1109\/JSTARS.2022.3198577"},{"key":"2375_CR136","unstructured":"Ma T et al (2021) Oriented object detection with transformer. arXiv preprint http:\/\/arxiv.org\/abs\/2106.03146"},{"key":"2375_CR137","unstructured":"Xu X et al (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"2375_CR138","unstructured":"Cai L et al (2023) NeXtFormer: enhanced transformer network for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (Continued in references for this section)"},{"key":"2375_CR139","unstructured":"Dai X et al (2021) MDef-DETR: multi-scale definable detection transformer. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"2375_CR140","doi-asserted-by":"crossref","unstructured":"Shen R et al (2023) Text-guided object detector for multi-modal video question answering. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision","DOI":"10.1109\/WACV56688.2023.00109"},{"key":"2375_CR141","unstructured":"Wang W et al (2022) CBNet V2-TTA: improved object detection framework. arXiv preprint http:\/\/arxiv.org\/abs\/2204.02976"},{"key":"2375_CR142","unstructured":"Cai L et al (2022) FP-DETR: efficient object detection with feature pyramid and deformable attention. In: Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"2375_CR143","unstructured":"Wang W et al (2022) T-TRD: transformer for real-time detection. In: International conference on learning representations"},{"key":"2375_CR144","unstructured":"Chen Q et al (2022) Group DETR v2: enhanced object detection with group-wise one-to-many assignment. arXiv preprint http:\/\/arxiv.org\/abs\/2211.03594"},{"key":"2375_CR145","unstructured":"Peng Z et al (2022) SPH-Yolov5: small object detection with swin transformer head. In: Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"2375_CR146","unstructured":"Cai L et al (2022) Multi-source aggregation transformer (MATR). In: Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"2375_CR147","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.neucom.2022.04.062","volume":"493","author":"K Zeng","year":"2022","unstructured":"Zeng K et al (2022) NLFFTNet: non-local feature fusion transformer network for multi-scale object detection. Neurocomputing 493:15\u201327","journal-title":"Neurocomputing"},{"key":"2375_CR148","unstructured":"Lu W et al (2022) CO-DETR: improved detection transformer with one-to-many label assignment. In: Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"2375_CR149","unstructured":"Zhang H et al (2022) DINO: Detr with improved denoising anchor boxes. arXiv preprint http:\/\/arxiv.org\/abs\/2203.03605"},{"key":"2375_CR150","doi-asserted-by":"crossref","unstructured":"Li F et al (2022) DN-DETR: accelerate DETR training by introducing query denoising. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"2375_CR151","unstructured":"Dai D et al (2021) AO2-DETR: arbitrary-oriented object detection with transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"2375_CR152","unstructured":"Zhu X et al (2021) DETR++: bi-directional feature pyramid layers for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"2375_CR153","unstructured":"Yang Z et al (2021) PointDet++: small object detection with human pose estimation. In Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"2375_CR154","unstructured":"Han H et al (2021) GhostNet: more efficient mobile neural networks via ghost module. IEEE Trans Pattern Anal Mach Intell"},{"key":"2375_CR155","unstructured":"Chen X et al (2022) MS transformer: medical image analysis with self-supervised learning. In: Proceedings of the international conference on medical imaging"},{"key":"2375_CR156","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","volume":"117","author":"G Cheng","year":"2016","unstructured":"Cheng G, Han J (2016) A survey on object detection in optical remote sensing images. ISPRS J Photogramm Remote Sens 117:11\u201328","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"2375_CR157","unstructured":"Luo W et al (2022) SOF-DETR: small object favoring detection transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision"},{"key":"2375_CR158","unstructured":"Zhang L et al (2022) HTDet: high-resolution transformer for small object detection. IEEE Trans Image Process"},{"key":"2375_CR159","doi-asserted-by":"crossref","unstructured":"Zhang D, Han J, Cheng G, Yang M-H (2021) Weakly supervised object localization and detection: a survey. In: TPAMI, p 1","DOI":"10.1109\/TPAMI.2021.3074313"},{"key":"2375_CR160","unstructured":"Li T et al (2002) MDCT: multi-kernel dilated convolution for small object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"2375_CR161","unstructured":"Song H et al (2023) RTD-Net: real-time detection of partially occluded small objects. IEEE Trans Image Process"},{"key":"2375_CR162","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115:211\u2013252","journal-title":"Int J Comput Vis"},{"key":"2375_CR163","doi-asserted-by":"crossref","unstructured":"Meinhardt T et al (2022) TrackFormer: multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"2375_CR164","unstructured":"Chen X et al (2021) TransT: transformer-based template tracking for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"2375_CR165","unstructured":"Liu Y et al (2021) Transformer-based small object detection in videos. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"2375_CR166","doi-asserted-by":"crossref","unstructured":"Zhou Q et al (2022) TransVOD: end-to-end video object detection with spatial-temporal transformers. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"2375_CR167","doi-asserted-by":"crossref","unstructured":"Wang H et al (2022) PTSEFormer: progressive temporal-spatial enhanced transformer for video object detection. In: Proceedings of the European conference on computer vision","DOI":"10.1007\/978-3-031-20074-8_42"},{"key":"2375_CR168","unstructured":"Li S et al (2022) Sparse VOD: sparse aggregation for video object detection. IEEE Access"},{"key":"2375_CR169","doi-asserted-by":"crossref","unstructured":"Roh S-D, Chung K-S (2022) DAFA: diversity-aware feature aggregation for attention-based video object detection. IEEE Access","DOI":"10.1109\/ACCESS.2022.3203399"},{"key":"2375_CR170","doi-asserted-by":"crossref","unstructured":"Kisantal M, Wojna Z, Murawski J, Naruniec J, Cho K (2019) Augmentation for small object detection, arXiv preprint http:\/\/arxiv.org\/abs\/1902.07296","DOI":"10.5121\/csit.2019.91713"},{"key":"2375_CR171","doi-asserted-by":"crossref","unstructured":"Chen C, Zhang Y, Lv Q, Wei S, Wang X, Sun X, Dong J (2019) RRNet: a hybrid detector for object detection in drone-captured images. In: ICCVW, pp 100\u2013108","DOI":"10.1109\/ICCVW.2019.00018"},{"key":"2375_CR172","doi-asserted-by":"crossref","unstructured":"Zhang X, Izquierdo E, Chandramouli K (2019) Dense and small object detection in UAV vision based on cascade network. In: ICCVW, pp 118\u2013126","DOI":"10.1109\/ICCVW.2019.00020"},{"key":"2375_CR173","doi-asserted-by":"crossref","unstructured":"Xu C, Wang J, Yang W, Yu H, Yu L, Xia G-S (2022) RFLA: Gaussian receptive based label assignment for tiny object detection. In: ECCV","DOI":"10.1007\/978-3-031-20077-9_31"},{"issue":"10","key":"2375_CR174","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1109\/TPAMI.2020.2981890","volume":"43","author":"K Oksuz","year":"2020","unstructured":"Oksuz K, Cam BC, Kalkan S, Akbas E (2020) Imbalance problems in object detection: a review. TPAMI 43(10):3388\u20133415","journal-title":"TPAMI"},{"key":"2375_CR175","unstructured":"Saboo A, Gyawali PK, Shukla A, Sharma M, Jain N, Wang L (2021) Latent-optimization based Disease-aware Image Editing for Medical Image Augmentation. In: BMVC, p 181"},{"issue":"6","key":"2375_CR176","first-page":"33","volume":"29","author":"EH Adelson","year":"1984","unstructured":"Adelson EH, Anderson CH, Bergen JR, Burt PJ, Ogden JM (1984) Pyramid methods in image processing. RCA Eng 29(6):33\u201341","journal-title":"RCA Eng"},{"key":"2375_CR177","doi-asserted-by":"crossref","unstructured":"Cai Z, Fan Q, Feris RS, Vasconcelos N (2016) A unified multi-scale deep convolutional neural network for fast object detection. In: ECCV, pp 354\u2013370","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"2375_CR178","unstructured":"Li J et al DSFD: dual shot face detector. In: CVPR, pp 5055\u20135064"},{"key":"2375_CR179","doi-asserted-by":"crossref","unstructured":"Qiao S, Chen L-C, Yuille A (2021) DetectoRS: detecting objects with recursive feature pyramid and switchable atrous convolution. In: CVPR, pp 10208\u201310219","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"2375_CR180","doi-asserted-by":"crossref","unstructured":"Lin T, Dollar P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: CVPR, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"2375_CR181","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin T-Y, Le QV (2019) NAS-FPN: learning scalable feature pyramid architecture for object detection. In: CVPR, pp 7029\u20137038","DOI":"10.1109\/CVPR.2019.00720"},{"key":"2375_CR182","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) EfficientDet: scalable and efficient object detection. In: CVPR, pp 10778\u201310787","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2375_CR183","doi-asserted-by":"crossref","unstructured":"Najibi M, Samangouei P, Chellappa R, Davis LS (2017) SSH: single stage headless face detector. In: ICCV, pp 4885\u20134894","DOI":"10.1109\/ICCV.2017.522"},{"key":"2375_CR184","doi-asserted-by":"crossref","unstructured":"Singh B, Davis LS (2018) An analysis of scale invariance in object detection-SNIP. In: CVPR, pp 3578\u20133587","DOI":"10.1109\/CVPR.2018.00377"},{"key":"2375_CR185","unstructured":"Singh B, Najibi M, Davis L (2018) SNIPER: efficient multi-scale training. In: NeurIPS, vol 31"},{"key":"2375_CR186","doi-asserted-by":"crossref","unstructured":"Najibi M, Singh B, Davis L (2019) AutoFocus: efficient multi-scale inference. IN: ICCV, pp 9745\u20139755","DOI":"10.1109\/ICCV.2019.00984"},{"key":"2375_CR187","doi-asserted-by":"crossref","unstructured":"Ma Y, Liu S, Li Z, Sun J (2021) IQDet: instance-wise quality distribution sampling for object detection. In: CVPR, pp 1717\u20131725","DOI":"10.1109\/CVPR46437.2021.00176"},{"key":"2375_CR188","unstructured":"Chen Y et al (2020) Dynamic scale training for object detection. arXiv preprint http:\/\/arxiv.org\/abs\/2004.12432"},{"key":"2375_CR189","doi-asserted-by":"crossref","unstructured":"Liu S, Huang D, Wang Y (2018) Path aggregation network for instance segmentation. In: CVPR, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"2375_CR190","doi-asserted-by":"crossref","unstructured":"Qin Z, Li Z, Zhang Z, Bao Y, Yu G, Peng Y, Sun J (2019) ThunderNet: towards real-time generic object detection on mobile devices. In: ICCV, pp 6717\u20136726","DOI":"10.1109\/ICCV.2019.00682"},{"key":"2375_CR191","unstructured":"Zhang X, Wan F, Liu C, Ji R, Ye Q (2019) FreeAnchor: learning to match anchors for visual object detection. In: NeurIPS, vol 32"},{"key":"2375_CR192","doi-asserted-by":"crossref","unstructured":"Woo S, Hwang S, Kweon IS (2018) StairNet: top-down semantic aggregation for accurate one shot detection. In: WACV, pp 1093\u20131102","DOI":"10.1109\/WACV.2018.00125"},{"key":"2375_CR193","first-page":"1968","volume":"24","author":"C Deng","year":"2021","unstructured":"Deng C, Wang M, Liu L, Liu Y, Jiang Y (2021) Extended feature pyramid network for small object detection. TMM 24:1968\u20131979","journal-title":"TMM"},{"key":"2375_CR194","first-page":"6745","volume":"29","author":"X Pan","year":"2020","unstructured":"Pan X et al (2020) Self-supervised feature augmentation for large image object detection. TIP 29:6745\u20136758","journal-title":"TIP"},{"key":"2375_CR195","doi-asserted-by":"crossref","unstructured":"Bai Y, Zhang Y, Ding M, Ghanem B (2018) SOD-MTGAN: small object detection via multi-task generative adversarial network. In: ECCV, pp 210\u2013226","DOI":"10.1007\/978-3-030-01261-8_13"},{"issue":"9","key":"2375_CR196","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.3390\/rs12091432","volume":"12","author":"J Rabbi","year":"2020","unstructured":"Rabbi J, Ray N, Schubert M, Chowdhury S, Chao D (2020) Small-object detection in remote sensing images with end-to-end edge-enhanced GAN and object detector network. Remote Sens 12(9):1432","journal-title":"Remote Sens"},{"key":"2375_CR197","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: ICCV, pp 9724\u20139733","DOI":"10.1109\/ICCV.2019.00982"},{"issue":"15","key":"2375_CR198","doi-asserted-by":"publisher","first-page":"2109","DOI":"10.1111\/mice.12970","volume":"38","author":"D Ma","year":"2023","unstructured":"Ma D, Fang H, Wang N, Lu H, Matthews J, Zhang C (2023) Transformer-optimized generation, detection, and tracking network for images with drainage pipeline defects. Comput Aid Civ Infrastruct Eng 38(15):2109\u20132127. https:\/\/doi.org\/10.1111\/mice.12970","journal-title":"Comput Aid Civ Infrastruct Eng"},{"key":"2375_CR199","doi-asserted-by":"crossref","unstructured":"Ozge Unel F, Ozkalayci BO, Cigla C (2019) The power of tiling for small object detection. In: CVPRW, pp 582\u2013591","DOI":"10.1109\/CVPRW.2019.00084"},{"key":"2375_CR200","doi-asserted-by":"crossref","unstructured":"Liu W et al (2016) SSD: single shot multibox detector. In: ECCV. Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2375_CR201","doi-asserted-by":"crossref","unstructured":"Liang T et al (2022) CBNet: composite backbone network architecture for object detection. IEEE Trans Image Process","DOI":"10.1109\/TIP.2022.3216771"},{"key":"2375_CR202","doi-asserted-by":"crossref","unstructured":"Fujitake M, Sugimoto A (2022) VSTAM: video sparse transformer with attention-guided memory for video object detection. IEEE Access","DOI":"10.1109\/ACCESS.2022.3184031"},{"key":"2375_CR203","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: Computer vision\u2014ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, proceedings, part I, vol 16. Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2375_CR204","doi-asserted-by":"publisher","first-page":"65886","DOI":"10.1109\/ACCESS.2022.3184031","volume":"10","author":"M Fujitake","year":"2022","unstructured":"Fujitake M, Sugimoto A (2022) Video sparse transformer with attention-guided memory for video object detection. IEEE Access 10:65886\u201365900","journal-title":"IEEE Access"},{"issue":"12","key":"2375_CR205","doi-asserted-by":"publisher","first-page":"9909","DOI":"10.1109\/TIE.2019.2893843","volume":"66","author":"T Liu","year":"2019","unstructured":"Liu T, Zhao Y, Wei Y, Zhao Y, Wei S (2019) Concealed object detection for activate millimeter wave image. IEEE Trans Ind Electron 66(12):9909\u20139917","journal-title":"IEEE Trans Ind Electron"},{"key":"2375_CR206","unstructured":"Hashmi KA, Stricker D, Afzal MZ (2022) Spatio-temporal learnable proposals for end-to-end video object detection. arXiv preprint http:\/\/arxiv.org\/abs\/2210.02368"},{"key":"2375_CR207","doi-asserted-by":"crossref","unstructured":"Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for UAV tracking. In: Computer vision\u2014ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, proceedings, part I, vol 14. Springer, pp 445\u2013461","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"2375_CR208","doi-asserted-by":"crossref","unstructured":"Goldman E, Herzig R, Eisenschtat A, Goldberger J, Hassner T (2019) Precise detection in densely packed scenes. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5227\u20135236","DOI":"10.1109\/CVPR.2019.00537"},{"issue":"3","key":"2375_CR209","doi-asserted-by":"publisher","first-page":"036501","DOI":"10.1117\/1.JMI.5.3.036501","volume":"5","author":"K Yan","year":"2018","unstructured":"Yan K, Wang X, Lu L, Summers RM (2018) Deeplesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. J Med Imaging 5(3):036501","journal-title":"J Med Imaging"},{"key":"2375_CR210","doi-asserted-by":"crossref","unstructured":"Cai L, Zhang Z, Zhu Y, Zhang L, Li M, Xue X (2022) Bigdetection: a large-scale benchmark for improved object detector pre-training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4777\u20134787","DOI":"10.1109\/CVPRW56347.2022.00524"},{"key":"2375_CR211","unstructured":"Udacity self-driving car driving data, 2017 transformer. https:\/\/github.com\/udacity\/selfdriving-car\/tree\/master\/annotations"},{"key":"2375_CR212","unstructured":"Hong J, Fulton M, Sattar J (2020) Trashcan: a semantically-segmented dataset towards visual detection of marine debris. arXiv preprint http:\/\/arxiv.org\/abs\/2007.08097"},{"key":"2375_CR213","doi-asserted-by":"crossref","unstructured":"Coluccia A, Fascista A, Schumann A, Sommer L, Dimou A, Zarpalas D, Akyon FC, Eryuksel O, Ozfuttu KA, Altinuc SO et al (2021) Drone-vs-bird detection challenge at IEEE AVSS2021. In: 2021 17th IEEE international conference on advanced video and signal based surveillance (AVSS). IEEE, pp 1\u20138","DOI":"10.1109\/AVSS52988.2021.9663844"},{"issue":"18","key":"2375_CR214","doi-asserted-by":"publisher","first-page":"6939","DOI":"10.3390\/s22186939","volume":"22","author":"S Li","year":"2022","unstructured":"Li S, Sultonov F, Tursunboev J, Park J-H, Yun S, Kang J-M (2022) Ghostformer: a ghostnet-based two-stage transformer for small object detection. Sensors 22(18):6939","journal-title":"Sensors"},{"key":"2375_CR215","first-page":"1","volume":"72","author":"T Ye","year":"2023","unstructured":"Ye T, Qin W, Zhao Z, Gao X, Deng X, Ouyang Y (2023) Real-time object detection network in UAV-vision based on CNN and transformer. IEEE Trans Instrum Meas 72:1\u201313","journal-title":"IEEE Trans Instrum Meas"},{"key":"2375_CR216","doi-asserted-by":"publisher","first-page":"6893","DOI":"10.1109\/TIP.2022.3216771","volume":"31","author":"T Liang","year":"2022","unstructured":"Liang T, Chu X, Liu Y, Wang Y, Tang Z, Chu W, Chen J, Ling H (2022) CBNet: a composite backbone network architecture for object detection. IEEE Trans Image Process 31:6893\u20136906","journal-title":"IEEE Trans Image Process"},{"key":"2375_CR217","unstructured":"Zhang H, Li F, Liu S, Zhang L, Su H, Zhu J, Ni LM, Shum H-Y (2022) Dino: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint http:\/\/arxiv.org\/abs\/2203.03605"},{"key":"2375_CR218","unstructured":"Jocher G et al (2020) \u201cyolov5\u201d, Code repository"},{"key":"2375_CR219","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2375_CR220","unstructured":"Wang J, Yang W, Guo H, Zhang R, Xia G-S (2020) Tiny object detection in aerial images. In: Presented at the international conference on pattern recognition, Milan, Italy"},{"key":"2375_CR221","doi-asserted-by":"crossref","unstructured":"Yu X, Gong Y, Jiang N, Ye Q, Han Z (2020) Scale match for tiny person detection. In: Presented at the IEEE winter conference on applications of computer vision, Snowmass Village, CO, USA","DOI":"10.1109\/WACV45572.2020.9093394"},{"key":"2375_CR222","doi-asserted-by":"crossref","unstructured":"Yang S, Luo P, Loy CC, Tang X (2016) WIDER FACE: a face detection benchmark. In: Presented at the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA","DOI":"10.1109\/CVPR.2016.596"},{"key":"2375_CR223","doi-asserted-by":"crossref","unstructured":"Chen C, Liu M-Y, Tuzel O, Xiao J (2016) R-CNN for small object detection. In: Presented at the Asian conference on computer vision, Taipei, Taiwan","DOI":"10.1007\/978-3-319-54193-8_14"},{"issue":"9","key":"2375_CR224","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.3390\/rs12091432","volume":"12","author":"J Rabbi","year":"2020","unstructured":"Rabbi J, Ray N, Schubert M, Chowdhury S, Chao D (2020) Small-object detection in remote sensing images with end-to-end edge-enhanced GAN and object detector network. Remote Sens 12(9):1432","journal-title":"Remote Sens"},{"key":"2375_CR225","unstructured":"Chen D, Miao D, Zhao X (2022) FP-DETR: efficient detection with transformers. In: ICLR"},{"key":"2375_CR226","doi-asserted-by":"crossref","unstructured":"Cui Y (2023) FAQ: feature aggregated queries for transformer-based video object detectors. arXiv preprint http:\/\/arxiv.org\/abs\/2303.08319","DOI":"10.1109\/CVPR52729.2023.00616"},{"key":"2375_CR227","doi-asserted-by":"crossref","unstructured":"Lin W-H, Zhong J-X, Liu S, Li T, Li G (2020) Roimix: proposal-fusion among multiple images for underwater object detection. In: ICASSP 2020\u20132020 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 2588\u20132592","DOI":"10.1109\/ICASSP40776.2020.9053829"},{"issue":"23","key":"2375_CR228","doi-asserted-by":"publisher","first-page":"4779","DOI":"10.3390\/rs13234779","volume":"13","author":"X Xu","year":"2021","unstructured":"Xu X, Feng Z, Cao C, Li M, Wu J, Wu Z, Shang Y, Ye S (2021) An improved swin transformer-based model for remote sensing object detection and instance segmentation. Remote Sens 13(23):4779","journal-title":"Remote Sens"},{"issue":"12","key":"2375_CR229","doi-asserted-by":"publisher","first-page":"2861","DOI":"10.3390\/rs14122861","volume":"14","author":"H Gong","year":"2022","unstructured":"Gong H, Mu T, Li Q, Dai H, Li C, He Z, Wang W, Han F, Tuniyazi A, Li H et al (2022) Swin-transformer-enabled yolov5 with attention mechanism for small object detection on satellite images. Remote Sens 14(12):2861","journal-title":"Remote Sens"},{"key":"2375_CR230","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"},{"issue":"14","key":"2375_CR231","doi-asserted-by":"publisher","first-page":"3246","DOI":"10.3390\/rs14143246","volume":"14","author":"Q Wu","year":"2022","unstructured":"Wu Q, Zhang B, Xu C, Zhang H, Wang C (2022) Dense oil tank detection and classification via YOLOX-TR network in large-scale SAR images. Remote Sens 14(14):3246","journal-title":"Remote Sens"},{"issue":"12","key":"2375_CR232","doi-asserted-by":"publisher","first-page":"7405","DOI":"10.1109\/TGRS.2016.2601622","volume":"54","author":"G Cheng","year":"2016","unstructured":"Cheng G, Zhou P, Han J (2016) Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Trans Geosci Remote Sens 54(12):7405\u20137415","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"2","key":"2375_CR233","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"key":"2375_CR234","doi-asserted-by":"crossref","unstructured":"Zhu Z, Liang D, Zhang S, Huang X, Li B, Hu S (2016) Traffic-sign detection and classification in the wild. In: Presented at the computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.232"},{"key":"2375_CR235","doi-asserted-by":"crossref","unstructured":"Lin TY et al (2014) Microsoft COCO: common objects in context. In: European conference on computer vision, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2375_CR236","doi-asserted-by":"crossref","unstructured":"Fang P, Shi Y (2018) Small object detection using context information fusion in faster R-CNN. In: Presented at the IEEE international conference on computer and communications, Chengdu, China","DOI":"10.1109\/CompComm.2018.8780579"},{"key":"2375_CR237","doi-asserted-by":"crossref","unstructured":"Du D et al (2018) The unmanned aerial vehicle benchmark: object detection and tracking. In: Presented at the European conference on computer vision, Munich, Germany","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"2375_CR238","doi-asserted-by":"crossref","unstructured":"Xia G-S et al (2018) DOTA: a large-scale dataset for object detection in aerial images. In: Presented at the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA","DOI":"10.1109\/CVPR.2018.00418"},{"key":"2375_CR239","unstructured":"Zhu P, Wen L, Du D, Bian X, Hu Q, Ling H (2020) Vision meets drones: past, present and future. http:\/\/arxiv.org\/abs\/2001.06303v2"},{"key":"2375_CR240","unstructured":"Li Z, Tang X, Han J, Liu J, He R (2019) PyramidBox++: high performance detector for finding tiny face. http:\/\/arxiv.org\/abs\/1904.00386v1"},{"key":"2375_CR241","doi-asserted-by":"publisher","first-page":"103615","DOI":"10.1016\/j.engappai.2020.103615","volume":"91","author":"B Bosquet","year":"2020","unstructured":"Bosquet B, Mucientes M, Brea VM (2020) STDnet: exploiting high resolution feature maps for small object detection. Eng Appl Artif Intell 91:103615","journal-title":"Eng Appl Artif Intell"},{"key":"2375_CR242","doi-asserted-by":"crossref","unstructured":"Chen P-Y, Hsieh J-W, Wang C-Y, Liao H-YM (2020) Recursive hybrid fusion pyramid network for real-time small object detection on embedded devices. Presented at the IEEE conference on computer vision and pattern recognition workshops, Seattle, WA, USA","DOI":"10.1109\/CVPRW50498.2020.00209"},{"key":"2375_CR243","unstructured":"Chen Y et al (2021) Dynamic scale training for object detection. http:\/\/arxiv.org\/abs\/2004.12432v2"},{"key":"2375_CR244","doi-asserted-by":"crossref","unstructured":"Jiang N, Yu X, Peng X, Gong Y, Han Z (2021) SM+: refined scale match for tiny person detection. In: Presented at the IEEE international conference on acoustics, speech and signal processing, Toronto, ON, Canada","DOI":"10.1109\/ICASSP39728.2021.9414162"},{"key":"2375_CR245","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade R-CNN: delving into high quality object detection. In: Presented at the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2375_CR246","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.neucom.2020.05.019","volume":"409","author":"S Zhang","year":"2020","unstructured":"Zhang S, Yang X, Liu Y, Xu C (2020) Asymmetric multi-stage CNNs for small-scale pedestrian detection. Neurocomputing 409:12\u201326","journal-title":"Neurocomputing"},{"key":"2375_CR247","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick RB, He K, Hariharan B, Belongie SJ (2017) Feature pyramid networks for object detection. In: Presented at the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA","DOI":"10.1109\/CVPR.2017.106"},{"key":"2375_CR248","unstructured":"Du D et al (2019) VisDrone-DET2019: the vision meets drone object detection in image challenge results. In: Presented at the IEEE international conference on computer vision workshops, Seoul, South Korea"},{"key":"2375_CR249","doi-asserted-by":"crossref","unstructured":"Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) Libra R-CNN: towards balanced learning for object detection. In: Presented at the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2019.00091"},{"issue":"3","key":"2375_CR250","doi-asserted-by":"publisher","first-page":"1921","DOI":"10.1007\/s11063-021-10493-y","volume":"53","author":"Z Yan","year":"2021","unstructured":"Yan Z, Zheng H, Li Y, Chen L (2021) Detection-oriented backbone trained from near scratch and local feature refinement for small object detection. Neural Process Lett 53(3):1921\u20131943","journal-title":"Neural Process Lett"},{"key":"2375_CR251","doi-asserted-by":"crossref","unstructured":"Behrendt K, Novak L, Botros R (2017) A deep learning approach to traffic lights: detection, tracking, and classification. In: Presented at the IEEE international conference on robotics and automation, Singapore","DOI":"10.1109\/ICRA.2017.7989163"},{"key":"2375_CR252","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.isprsjprs.2022.07.019","volume":"191","author":"Y Shen","year":"2022","unstructured":"Shen Y, Liu D, Zhang F, Zhang Q (2022) Fast and accurate multi-class geospatial object detection with large-size remote sensing imagery using CNN and Truncated NMS. ISPRS J Photogramm Remote Sens 191:235\u2013249","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"2375_CR253","doi-asserted-by":"crossref","unstructured":"Lim J-S, Astrid M, Yoon H-J, Lee S-I (2021) Small object detection using context and attention. In: Presented at the international conference on artificial intelligence in information and communication, Jeju Island, South Korea","DOI":"10.1109\/ICAIIC51459.2021.9415217"},{"key":"2375_CR254","doi-asserted-by":"crossref","unstructured":"Hong M, Li S, Yang Y, Zhu F, Zhao Q, Lu L (2021) SSPNet: scale selection pyramid network for tiny person detection from UAV images. http:\/\/arxiv.org\/abs\/2107.01548v1","DOI":"10.1109\/LGRS.2021.3103069"},{"key":"2375_CR255","unstructured":"Braun M, Krebs S, Flohr F, Gavrila DM (2018) The EuroCity persons dataset: a novel benchmark for object detection. http:\/\/arxiv.org\/abs\/1805.07193v2"},{"issue":"6","key":"2375_CR256","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.1109\/TCSVT.2019.2906246","volume":"30","author":"K Duan","year":"2020","unstructured":"Duan K, Du D, Qi H, Huang Q (2020) Detecting small objects using a channel-aware deconvolutional network. IEEE Trans Circuits Syst Video Technol 30(6):1639\u20131652","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2375_CR257","doi-asserted-by":"crossref","unstructured":"Yang X et al (2019) SCRDet: towards more robust detection for small, cluttered and rotated objects. In: Presented IEEE international conference on computer vision, Seoul, South Korea","DOI":"10.1109\/ICCV.2019.00832"},{"key":"2375_CR258","unstructured":"Ren S (2015) Faster R-CNN: towards real-time object detection with region proposal networks.\u00a0arXiv preprint http:\/\/arxiv.org\/abs\/1506.01497"},{"key":"2375_CR259","doi-asserted-by":"crossref","unstructured":"Iqra, Giri KJ, Javed M (2024) Small object detection in diverse application landscapes: a survey. Multimed Tools Appl 1\u201336","DOI":"10.1007\/s11042-024-18866-w"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-025-02375-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-025-02375-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-025-02375-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T01:04:37Z","timestamp":1744419877000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-025-02375-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,22]]},"references-count":259,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2375"],"URL":"https:\/\/doi.org\/10.1007\/s10115-025-02375-9","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,22]]},"assertion":[{"value":"7 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author declares that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}