{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T09:20:29Z","timestamp":1769073629970,"version":"3.49.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T00:00:00Z","timestamp":1710201600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T00:00:00Z","timestamp":1710201600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61461053"],"award-info":[{"award-number":["61461053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61461053"],"award-info":[{"award-number":["61461053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the China Postgraduate Science Foundation of Yunnan University","award":["2020306"],"award-info":[{"award-number":["2020306"]}]},{"name":"the China Postgraduate Science Foundation of Yunnan University","award":["2020306"],"award-info":[{"award-number":["2020306"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Earth Sci Inform"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s12145-024-01265-y","type":"journal-article","created":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T21:22:41Z","timestamp":1710278561000},"page":"2085-2106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["MS-YOLO: integration-based multi-subnets neural network for object detection in aerial images"],"prefix":"10.1007","volume":"17","author":[{"given":"Xinyu","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minglei","family":"Duan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,12]]},"reference":[{"key":"1265_CR1","doi-asserted-by":"publisher","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv: 2004.10934. https:\/\/doi.org\/10.48550\/arXiv.2004.10934","DOI":"10.48550\/arXiv.2004.10934"},{"key":"1265_CR2","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 Recogn 133:108998. https:\/\/doi.org\/10.1016\/j.patcog.2022.108998","journal-title":"Pattern Recogn"},{"key":"1265_CR3","doi-asserted-by":"publisher","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 (CVPR). https:\/\/doi.org\/10.1109\/cvpr.2018.00644","DOI":"10.1109\/cvpr.2018.00644"},{"key":"1265_CR4","doi-asserted-by":"publisher","unstructured":"Cai Y, Zhou Y, Han Q et al (2022) Reversible column networks. arXiv preprint arXiv: 2212.11696. https:\/\/doi.org\/10.48550\/arXiv.2212.11696","DOI":"10.48550\/arXiv.2212.11696"},{"key":"1265_CR5","doi-asserted-by":"publisher","unstructured":"Du D, Zhu P, Wen L et al (2019) VisDrone-DET2019: the vision meets drone object detection in image challenge results. In: Proceedings of the IEEE\/CVF international conference on computer vision workshops (ICCVW). https:\/\/doi.org\/10.1109\/ICCVW.2019.00030","DOI":"10.1109\/ICCVW.2019.00030"},{"key":"1265_CR6","doi-asserted-by":"publisher","unstructured":"Duan K, Bai S, Xie L et al (2019) Centernet: Keypoint triplets for object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV). https:\/\/doi.org\/10.1109\/iccv.2019.00667","DOI":"10.1109\/iccv.2019.00667"},{"key":"1265_CR7","doi-asserted-by":"publisher","unstructured":"Ge Z, Liu S, Wang F et al (2021) Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv: 2107.08430. https:\/\/doi.org\/10.48550\/arXiv.2107.08430","DOI":"10.48550\/arXiv.2107.08430"},{"key":"1265_CR8","doi-asserted-by":"publisher","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision (ICCV).\u00a0https:\/\/doi.org\/10.1109\/iccv.2015.169","DOI":"10.1109\/iccv.2015.169"},{"key":"1265_CR9","doi-asserted-by":"publisher","unstructured":"Han K, Wang Y, Tian Q et al (2020) Ghostnet: more features from cheap operations. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.1911.11907","DOI":"10.48550\/arXiv.1911.11907"},{"key":"1265_CR10","doi-asserted-by":"publisher","unstructured":"He K, Gkioxari G, Doll\u00e1r P et al (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision (ICCV). https:\/\/doi.org\/10.48550\/arXiv.1703.06870","DOI":"10.48550\/arXiv.1703.06870"},{"key":"1265_CR11","doi-asserted-by":"publisher","unstructured":"Hinton G (2023) How to represent part-whole hierarchies in a neural network. Neural Comput 35(3):413\u2013452. https:\/\/doi.org\/10.48550\/arXiv.2102.12627","DOI":"10.48550\/arXiv.2102.12627"},{"key":"1265_CR12","doi-asserted-by":"publisher","unstructured":"Hou Q, Zhou D, Feng J (2021) Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr46437.2021.01350","DOI":"10.1109\/cvpr46437.2021.01350"},{"key":"1265_CR13","doi-asserted-by":"publisher","unstructured":"Howard A, Zhmoginov A, Chen LC et al (2018) Inverted residuals and linear bottlenecks: mobile networks for classification, detection and segmentation. https:\/\/doi.org\/10.48550\/arXiv.1801.04381","DOI":"10.48550\/arXiv.1801.04381"},{"key":"1265_CR14","unstructured":"Jocher G, Stoken A, Borovec J et al (2021) ultralytics\/yolov5: v5.0. [Online]. Available https:\/\/github.com\/ultralytics\/yolov5. Accessed 1 Jan 2023"},{"key":"1265_CR15","unstructured":"Jocher G, Chaurasia A, Qiu J (2023) YOLO by Ultralytics. 2023. Available https:\/\/github.com\/ultralytics\/ultralytics. Accessed 30 Feb 2023."},{"key":"1265_CR16","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 et al (2020) Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J Photogramm 159:296\u2013307. https:\/\/doi.org\/10.1016\/j.isprsjprs.2019.11.023","journal-title":"ISPRS J Photogramm"},{"key":"1265_CR17","doi-asserted-by":"publisher","unstructured":"Li C, Li L, Jiang H et al (2022) YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv: 2209.02976. https:\/\/doi.org\/10.48550\/arXiv.2209.02976","DOI":"10.48550\/arXiv.2209.02976"},{"key":"1265_CR18","doi-asserted-by":"publisher","unstructured":"Lin TY, Maire M, Belongie S et al (2014) Microsoft coco: Common objects in context. In: ECCV. https:\/\/doi.org\/10.48550\/arXiv.1405.0312","DOI":"10.48550\/arXiv.1405.0312"},{"key":"1265_CR19","doi-asserted-by":"publisher","unstructured":"Lin TY, Doll\u00e1r P, Girshick R et al (2017a) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.1612.03144","DOI":"10.48550\/arXiv.1612.03144"},{"key":"1265_CR20","doi-asserted-by":"publisher","unstructured":"Lin TY, Goyal P, Girshick R et al (2017b) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision (ICCV). https:\/\/doi.org\/10.1109\/iccv.2017.324","DOI":"10.1109\/iccv.2017.324"},{"key":"1265_CR21","doi-asserted-by":"publisher","unstructured":"Liu W, Anguelov D, Erhan D et al (2016) Ssd: single shot multibox detector. In: European conference on computer vision (ECCV). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1265_CR22","doi-asserted-by":"publisher","unstructured":"Liu S, Qi L, Qin H et al (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1265_CR23","doi-asserted-by":"publisher","unstructured":"Liu Y, Shao Z, Hoffmann N (2021) Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv: 2112.05561. https:\/\/doi.org\/10.48550\/arXiv.2112.05561","DOI":"10.48550\/arXiv.2112.05561"},{"key":"1265_CR24","doi-asserted-by":"publisher","unstructured":"Liu S, Zha J, Sun J et al (2023) EdgeYOLO: an edge-real-time object detector. arXiv preprint arXiv: 2302.07483. https:\/\/doi.org\/10.48550\/arXiv.2302.07483","DOI":"10.48550\/arXiv.2302.07483"},{"key":"1265_CR25","doi-asserted-by":"publisher","unstructured":"Lv W, Xu S, Zhao Y et al (2023) Detrs beat yolos on real-time object detection. arXiv preprint arXiv: 2304.08069. https:\/\/doi.org\/10.48550\/arXiv.2304.08069","DOI":"10.48550\/arXiv.2304.08069"},{"key":"1265_CR26","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.1612.08242","DOI":"10.48550\/arXiv.1612.08242"},{"key":"1265_CR27","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv: 1804.02767. https:\/\/doi.org\/10.48550\/arXiv.1804.02767","DOI":"10.48550\/arXiv.1804.02767"},{"key":"1265_CR28","doi-asserted-by":"publisher","unstructured":"Redmon J, Divvala S, Girshick R et al (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr.2016.91","DOI":"10.1109\/cvpr.2016.91"},{"issue":"10","key":"1265_CR29","doi-asserted-by":"publisher","first-page":"11725","DOI":"10.1007\/s10489-021-02955-6","volume":"52","author":"K Ren","year":"2022","unstructured":"Ren K, Gao Y, Wan M et al (2022) Infrared small target detection via region super resolution generative adversarial network. Appl Intell 52(10):11725\u201311737. https:\/\/doi.org\/10.1007\/s10489-021-02955-6","journal-title":"Appl Intell"},{"key":"1265_CR30","doi-asserted-by":"publisher","unstructured":"Tan M, Pang R, Le QV (2020a) Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr42600.2020.01079","DOI":"10.1109\/cvpr42600.2020.01079"},{"key":"1265_CR31","doi-asserted-by":"publisher","unstructured":"Tan M, Pang R, Le QV (2020b) Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.1911.09070","DOI":"10.48550\/arXiv.1911.09070"},{"key":"1265_CR32","doi-asserted-by":"publisher","unstructured":"Tian Z, Shen C, Chen H et al (2019) Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV). https:\/\/doi.org\/10.48550\/arXiv.1904.01355","DOI":"10.48550\/arXiv.1904.01355"},{"key":"1265_CR33","doi-asserted-by":"publisher","unstructured":"Tong Z, Chen Y, Xu Z et al (2023) Wise-IoU: bounding box regression loss with dynamic focusing mechanism. arXiv preprint arXiv: 2301.10051. https:\/\/doi.org\/10.48550\/arXiv.2301.10051","DOI":"10.48550\/arXiv.2301.10051"},{"issue":"1","key":"1265_CR34","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1049\/ipr2.12340","volume":"16","author":"G Wang","year":"2022","unstructured":"Wang G, Ding H, Li B et al (2022a) Trident-YOLO: improving the precision and speed of mobile device object detection. IET Image Process 16(1):145\u2013157. https:\/\/doi.org\/10.1049\/ipr2.12340","journal-title":"IET Image Process"},{"issue":"2","key":"1265_CR35","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1049\/cvi2.12072","volume":"16","author":"G Wang","year":"2022","unstructured":"Wang G, Ding H, Yang Z et al (2022b) TRC-YOLO: a real-time detection method for lightweight targets based on mobile devices. IET Comput vis 16(2):126\u2013142. https:\/\/doi.org\/10.1049\/cvi2.12072","journal-title":"IET Comput vis"},{"issue":"11","key":"1265_CR36","doi-asserted-by":"publisher","first-page":"12844","DOI":"10.1007\/s10489-021-03147-y","volume":"52","author":"J Wang","year":"2022","unstructured":"Wang J, Yu J, He Z (2022c) ARFP: a novel adaptive recursive feature pyramid for object detection in aerial images. Appl Intell 52(11):12844\u201312859. https:\/\/doi.org\/10.1007\/s10489-021-03147-y","journal-title":"Appl Intell"},{"key":"1265_CR37","doi-asserted-by":"publisher","unstructured":"Wang CY, Bochkovskiy A, Liao HYM (2023) YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr52729.2023.00721","DOI":"10.1109\/cvpr52729.2023.00721"},{"key":"1265_CR38","doi-asserted-by":"publisher","unstructured":"Woo S, Park J, Lee J Y et al (2018) Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV): 3\u201319. https:\/\/doi.org\/10.48550\/arXiv.1807.06521","DOI":"10.48550\/arXiv.1807.06521"},{"key":"1265_CR39","doi-asserted-by":"publisher","unstructured":"Xu C, Wang J, Yang W et al (2021) Dot distance for tiny object detection in aerial images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pat-tern Recognition (CVPR). https:\/\/doi.org\/10.1109\/cvprw53098.2021.00130","DOI":"10.1109\/cvprw53098.2021.00130"},{"key":"1265_CR40","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.isprsjprs.2022.02.001","volume":"186","author":"Q Yang","year":"2022","unstructured":"Yang Q, Ni Z, Ren P (2022) Meta captioning: a meta learning based remote sensing image captioning framework. ISPRS J Photogramm 186:190\u2013200. https:\/\/doi.org\/10.1016\/j.isprsjprs.2022.02.001","journal-title":"ISPRS J Photogramm"},{"key":"1265_CR41","doi-asserted-by":"publisher","unstructured":"Yang G, Lei J, Zhu Z et al (2023) AFPN: asymptotic feature pyramid network for object detection. arXiv preprint arXiv: 2306.15988. https:\/\/doi.org\/10.48550\/arXiv.2306.15988","DOI":"10.48550\/arXiv.2306.15988"},{"key":"1265_CR42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3306242","author":"L Zhang","year":"2023","unstructured":"Zhang L, Wang M, Jiang Y et al (2023) SSRDet: small object detection based on feature pyramid network. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2023.3306242","journal-title":"IEEE Access"},{"key":"1265_CR43","doi-asserted-by":"publisher","unstructured":"Zhang S, Chi C, Yao Y et al (2020) Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.1912.02424","DOI":"10.48550\/arXiv.1912.02424"},{"key":"1265_CR44","doi-asserted-by":"publisher","unstructured":"Zhu X, Hu H, Lin S et al (2019) Deformable convnets v2: More deformable, better results. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/cvpr.2019.00953","DOI":"10.1109\/cvpr.2019.00953"},{"key":"1265_CR45","doi-asserted-by":"publisher","unstructured":"Zhu X, Lyu S, Wang X et al (2021) 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 (ICCV). https:\/\/doi.org\/10.1109\/iccvw54120.2021.00312","DOI":"10.1109\/iccvw54120.2021.00312"},{"key":"1265_CR46","doi-asserted-by":"publisher","unstructured":"Zhu L, Wang X, Ke Z et al (2023) BiFormer: vision transformer with bi-level routing attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/doi.org\/10.48550\/arXiv.2303.08810","DOI":"10.48550\/arXiv.2303.08810"}],"container-title":["Earth Science Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-024-01265-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12145-024-01265-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12145-024-01265-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T09:22:22Z","timestamp":1717406542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12145-024-01265-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,12]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["1265"],"URL":"https:\/\/doi.org\/10.1007\/s12145-024-01265-y","relation":{},"ISSN":["1865-0473","1865-0481"],"issn-type":[{"value":"1865-0473","type":"print"},{"value":"1865-0481","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,12]]},"assertion":[{"value":"30 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2024","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 competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}