{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T13:55:11Z","timestamp":1764424511868,"version":"3.46.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"34","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s00521-025-11687-4","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:23:44Z","timestamp":1761582224000},"page":"28803-28821","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A small object detection method based on CSF-YOLO for UAV images"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3761-381X","authenticated-orcid":false,"given":"Junwu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"11687_CR1","doi-asserted-by":"crossref","unstructured":"Caesar H, Uijlings J, Ferrari V Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1209\u20131218","DOI":"10.1109\/CVPR.2018.00132"},{"key":"11687_CR2","unstructured":"Woo S, Debnath S, Hu R et al Convnext v2: co-designing and scaling convnets with masked autoencoders. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16133\u201316142"},{"key":"11687_CR3","doi-asserted-by":"crossref","unstructured":"Jiang H, Learned-Miller E (2017) Face detection with the faster R-CNN. In: 12th IEEE international conference on automatic face & gesture recognition (FG 2017), IEEE, pp 650\u2013657","DOI":"10.1109\/FG.2017.82"},{"issue":"12","key":"11687_CR4","doi-asserted-by":"publisher","first-page":"7791","DOI":"10.1109\/TII.2020.2972918","volume":"16","author":"A Masood","year":"2020","unstructured":"Masood A, Sheng B, Yang P et al (2020) Automated decision support system for lung cancer detection and classification via enhanced RFCN with multilayer fusion RPN. IEEE Trans Ind Inf 16(12):7791\u20137801","journal-title":"IEEE Trans Ind Inf"},{"key":"11687_CR5","unstructured":"He K, Gkioxari G, Doll\u00e1r P et al Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969"},{"key":"11687_CR6","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R et al 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":"11687_CR7","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D et al (2016) Ssd: single shot multibox detector. Computer Vision\u2013ECCV 2016: 14th European conference, Proceedings, Part I 14. Springer, Amsterdam, The Netherlands, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"11687_CR8","unstructured":"Zhang S, Wen L, Bian X et al Single-shot refinement neural network for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4203\u20134212"},{"issue":"12","key":"11687_CR9","doi-asserted-by":"publisher","first-page":"25345","DOI":"10.1109\/TITS.2022.3158253","volume":"23","author":"S Liang","year":"2022","unstructured":"Liang S, Wu H, Zhen L et al (2022) Edge YOLO: real-time intelligent object detection system based on edge-cloud cooperation in autonomous vehicles. IEEE Trans Intell Transp Syst 23(12):25345\u201325360","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"11687_CR10","doi-asserted-by":"crossref","unstructured":"Zhu X, Lyu S, Wang X et al TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2778\u20132788","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"11687_CR11","unstructured":"Jocher G, Nishimura K, Mineeva T et al (2020) Yolov5 by ultralytics[J]. Dispon\u0131vel em: https:\/\/github.com\/ultralytics\/yolov5"},{"key":"11687_CR12","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y et al Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11687_CR13","unstructured":"Yang C, Huang Z, Wang N QueryDet: cascaded sparse query for accelerating high-resolution small object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13668\u201313677"},{"key":"11687_CR14","doi-asserted-by":"crossref","unstructured":"Zhang C, Liu T, Ju Y et al (2023) Pyramid masked image modeling for transformer-based aerial object detection. In: IEEE international conference on image processing (ICIP), IEEE, pp 1675\u20131679","DOI":"10.1109\/ICIP49359.2023.10223093"},{"key":"11687_CR15","doi-asserted-by":"crossref","unstructured":"Cao Y, He Z, Wang L et al 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":"11687_CR16","doi-asserted-by":"crossref","unstructured":"Kisantal M, Wojna Z, Murawski J et al (2019) Augmentation for small object detection[J]. arXiv preprint arXiv:190207296","DOI":"10.5121\/csit.2019.91713"},{"key":"11687_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108998","volume":"133","author":"B Bosquet","year":"2023","unstructured":"Bosquet B, Cores D, Seidenari L et al (2023) A full data augmentation pipeline for small object detection based on generative adversarial networks. Pattern Recognit 133:108998","journal-title":"Pattern Recognit"},{"key":"11687_CR18","unstructured":"Lin TY, Doll\u00e1r P, Girshick R et al Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125"},{"key":"11687_CR19","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H et al 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":"11687_CR20","unstructured":"Tan Z, Wang J, Sun X et al Giraffedet: a heavy-neck paradigm for object detection. In: International conference on learning representations"},{"key":"11687_CR21","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 et al (2021) Realize your surroundings: exploiting context information for small object detection[J]. Neurocomputing 433:287\u2013299","journal-title":"Neurocomputing"},{"key":"11687_CR22","doi-asserted-by":"crossref","unstructured":"Du B, Huang Y, Chen J et al (2023) adaptive sparse convolutional networks with global context enhancement for faster object detection on drone images[J]. arXiv preprint arXiv:230314488","DOI":"10.1109\/CVPR52729.2023.01291"},{"key":"11687_CR23","doi-asserted-by":"crossref","unstructured":"Singh B, Davis LS An analysis of scale invariance in object detection snip. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3578\u20133587","DOI":"10.1109\/CVPR.2018.00377"},{"key":"11687_CR24","unstructured":"Singh B, Najibi M, Davis LS (2018) Sniper: efficient multi-scale training[J]. Advances in neural information processing systems"},{"key":"11687_CR25","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.isprsjprs.2022.06.002","volume":"190","author":"C Xu","year":"2022","unstructured":"Xu C, Wang J, Yang W et al (2022) Detecting tiny objects in aerial images: a normalized Wasserstein distance and a new benchmark[J]. ISPRS J Photogramm Remote Sens 190:79\u201393","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"11687_CR26","unstructured":"Yang B, Bender G, Le QV et al CondConv: conditionally parameterized convolutions for efficient inference. In: Proceedings of the 33rd international conference on neural information processing systems. Curran Associates Inc, Article 117"},{"key":"11687_CR27","doi-asserted-by":"crossref","unstructured":"Chen Y, Dai X, Liu M et al (2020) Dynamic Convolution: Attention Over Convolution Kernels[J]. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), vol 2019. pp 11027-11036","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"11687_CR28","unstructured":"Li C, Zhou A, Yao A (2022) Omni-dimensional dynamic convolution[J]. arXiv preprint arXiv:220907947"},{"key":"11687_CR29","unstructured":"Fu CY, Liu W, Ranga A et al (2017) Dssd: deconvolutional single shot detector[J]. arXiv preprint arXiv:170106659"},{"key":"11687_CR30","unstructured":"Xu S, Wang X, Lv W et al (2022) PP-YOLOE: an evolved version of YOLO[J]. arXiv preprint arXiv:220316250"},{"key":"11687_CR31","doi-asserted-by":"crossref","unstructured":"Chen C, Liu MY, Tuzel O et al (2016) R-CNN for small object detection. Computer Vision\u2013ACCV 2016: 13th Asian Conference on Computer Vision, Revised Selected Papers, Part V 13. Springer, Taipei, Taiwan, pp 214\u2013230","DOI":"10.1007\/978-3-319-54193-8_14"},{"key":"11687_CR32","doi-asserted-by":"publisher","first-page":"106838","DOI":"10.1109\/ACCESS.2019.2932731","volume":"7","author":"C Cao","year":"2019","unstructured":"Cao C, Wang B, Zhang W et al (2019) An improved faster R-CNN for small object detection[J]. IEEE Access 7:106838\u2013106846","journal-title":"IEEE Access"},{"key":"11687_CR33","unstructured":"Redmon J, Farhadi A YOLO9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271"},{"key":"11687_CR34","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement[J]. arXiv preprint arXiv:180402767"},{"key":"11687_CR35","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection[J]. arXiv preprint arXiv:200410934"},{"key":"11687_CR36","unstructured":"Jocher G, Nishimura K, Mineeva T et al (2020) Yolov5 by ultralytics[J]"},{"key":"11687_CR37","unstructured":"Wang CY, Bochkovskiy A, Liao H-YM (2020) YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J]. arXiv preprint arXiv:220702696"},{"key":"11687_CR38","unstructured":"Ge Z, Liu S, Wang F et al (2021) Yolox: exceeding yolo series in 2021[J]. arXiv preprint arXiv:210708430"},{"key":"11687_CR39","unstructured":"Li C, Li L, Jiang H et al (2022) YOLOv6: a single-stage object detection framework for industrial applications[J]. arXiv preprint arXiv:220902976"},{"key":"11687_CR40","unstructured":"Jocher GaC, Ayush, Qiu, Jing (2023) YOLO by Ultralytics[J]"},{"key":"11687_CR41","unstructured":"Ding X, Zhang X, Ma N et al Repvgg: making vgg-style convnets great again. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13733\u201313742"},{"key":"11687_CR42","doi-asserted-by":"crossref","unstructured":"Chen J, Kao Sh, He H et al Run, don't walk: chasing higher flops for faster neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12021\u201312031","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"11687_CR43","doi-asserted-by":"crossref","unstructured":"Wang J, Chen K, Xu R et al Carafe: content-aware reassembly of features. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3007\u20133016","DOI":"10.1109\/ICCV.2019.00310"},{"key":"11687_CR44","unstructured":"Ren S, Zhou D, He S et al Shunted self-attention via multi-scale token aggregation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10853\u201310862"},{"key":"11687_CR45","doi-asserted-by":"crossref","unstructured":"Tang W, Sun J, Wang G (2021) Horizontal feature pyramid network for object detection in UAV images. China Automation Congress (CAC), IEEE, pp 7746\u20137750","DOI":"10.1109\/CAC53003.2021.9727887"},{"issue":"20","key":"11687_CR46","doi-asserted-by":"publisher","first-page":"12190","DOI":"10.1109\/JSEN.2020.3000249","volume":"20","author":"W Li","year":"2020","unstructured":"Li W, Zhang X, Peng Y et al (2020) DMnet: a network architecture using dilated convolution and multiscale mechanisms for spatiotemporal fusion of remote sensing images[J]. IEEE Sens J 20(20):12190\u201312202","journal-title":"IEEE Sens J"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11687-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11687-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11687-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T13:51:13Z","timestamp":1764424273000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11687-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":46,"journal-issue":{"issue":"34","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["11687"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11687-4","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"29 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 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 declared no conflict of interest and did not receive support from any organization for the submitted work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}