{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T09:06:32Z","timestamp":1779440792027,"version":"3.53.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62066018, No.62266020, No. 62361032, No.62261027, No. 62366017"],"award-info":[{"award-number":["No.62066018, No.62266020, No. 62361032, No.62261027, No. 62366017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-026-08602-6","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T08:30:32Z","timestamp":1779438632000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing small object detection via detail-injected dual-path FPN and large-kernel attention"],"prefix":"10.1007","volume":"82","author":[{"given":"Jun","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongqing","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miaomiao","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbing","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"8602_CR1","doi-asserted-by":"crossref","unstructured":"Caesar H, Bankiti V, Lang AH et al (2020) nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 11621\u201311631","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"8602_CR2","unstructured":"Zhu P, Wen L, Bian X et al (2018) Vision meets drones: a challenge. arXiv preprint arXiv:1804.07437"},{"key":"8602_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102907","volume":"193","author":"L Wen","year":"2020","unstructured":"Wen L, Du D, Cai Z et al (2020) UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. Comput Vis Image Underst 193:102907","journal-title":"Comput Vis Image Underst"},{"key":"8602_CR4","doi-asserted-by":"crossref","unstructured":"Lin T Y, Maire M, Belongie S et al (2014) Microsoft coco: common objects in context. In: European Conference on Computer Vision. Springer, Cham, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8602_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106442","volume":"123","author":"D Wan","year":"2023","unstructured":"Wan D, Lu R, Shen S et al (2023) Mixed local channel attention for object detection. Eng Appl Artif Intell 123:106442","journal-title":"Eng Appl Artif Intell"},{"key":"8602_CR6","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":"8602_CR7","doi-asserted-by":"crossref","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. pp 13713\u201313722","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"8602_CR8","doi-asserted-by":"crossref","unstructured":"Ulutan O, Iftekhar ASM, Manjunath BS (2020) Vsgnet: spatial attention network for detecting human object interactions using graph convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 13617\u201313626","DOI":"10.1109\/CVPR42600.2020.01363"},{"key":"8602_CR9","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R et al (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"8602_CR10","doi-asserted-by":"publisher","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 8759\u20138768, https:\/\/doi.org\/10.1109\/CVPR.2018.00913","DOI":"10.1109\/CVPR.2018.00913"},{"key":"8602_CR11","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"8602_CR12","doi-asserted-by":"publisher","unstructured":"Tang S, Zhang S, Fang Y (2024) HIC-YOLOv5: improved YOLOv5 for small object detection. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, pp 6614\u20136619, https:\/\/doi.org\/10.1109\/ICRA57147.2024.10610273","DOI":"10.1109\/ICRA57147.2024.10610273"},{"key":"8602_CR13","doi-asserted-by":"crossref","unstructured":"Zhu Y, Zhou Q, Liu N et al (2023) Scalekd: distilling scale-aware knowledge in small object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 19723\u201319733","DOI":"10.1109\/CVPR52729.2023.01889"},{"key":"8602_CR14","doi-asserted-by":"crossref","unstructured":"Wang J, Pu Y, Han Y et al (2024) Gra: detecting oriented objects through group-wise rotating and attention. In: European Conference on Computer Vision. Springer, Cham, pp 298\u2013315","DOI":"10.1007\/978-3-031-72643-9_18"},{"key":"8602_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2025.3572706","volume":"63","author":"Z Du","year":"2025","unstructured":"Du Z, Hu Z, Zhao G, Jin Y, Ma H (2025) Cross-layer feature pyramid transformer for small object detection in aerial images. IEEE Trans Geosci Remote Sens 63:1\u201314. https:\/\/doi.org\/10.1109\/TGRS.2025.3572706. (Art no. 5625714)","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"8602_CR16","doi-asserted-by":"crossref","unstructured":"Shi Z, Hu J, Ren J et al 2025 HS-FPN: high frequency and spatial perception FPN for tiny object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol 39(7), pp 6896\u20136904","DOI":"10.1609\/aaai.v39i7.32740"},{"key":"8602_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3396489","volume":"62","author":"H-I Liu","year":"2024","unstructured":"Liu H-I, Tseng Y-W, Chang K-C, Wang P-J, Shuai H-H, Cheng W-H (2024) A denoising FPN with Transformer R-CNN for tiny object detection. IEEE Trans Geosci Remote Sens 62:1\u201315. https:\/\/doi.org\/10.1109\/TGRS.2024.3396489. (Art no. 4704415)","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"8602_CR18","doi-asserted-by":"crossref","unstructured":"Li H, Zhang R, Pan Y et al (2024) LR-FPN: enhancing remote sensing object detection with location refined feature pyramid network. In: 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN60899.2024.10650583"},{"key":"8602_CR19","doi-asserted-by":"crossref","unstructured":"Li H (2024) Rethinking features-fused-pyramid-neck for object detection. In: European Conference on Computer Vision. Springer, Cham, pp 74\u201390","DOI":"10.1007\/978-3-031-72855-6_5"},{"issue":"17","key":"8602_CR20","doi-asserted-by":"publisher","first-page":"2989","DOI":"10.3390\/rs17172989","volume":"17","author":"X Zhao","year":"2025","unstructured":"Zhao X, Yang Z, Zhao H (2025) DCS-YOLOv8: a lightweight context-aware network for small object detection in UAV remote sensing imagery. Remote Sens 17(17):2989","journal-title":"Remote Sens"},{"key":"8602_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126141","volume":"267","author":"F Cai","year":"2025","unstructured":"Cai F, Qu Z, Xia S et al (2025) A method of object detection with attention mechanism and C2f_DCNv2 for complex traffic scenes. Expert Syst Appl 267:126141","journal-title":"Expert Syst Appl"},{"key":"8602_CR22","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-025-01731-7","volume":"31","author":"O Talha","year":"2025","unstructured":"Talha O, Zhou W, Yuan N et al (2025) Improved YOLOv8-C2fCA for embryonic cell detection and counting. Multimed Syst 31:177. https:\/\/doi.org\/10.1007\/s00530-025-01731-7","journal-title":"Multimed Syst"},{"key":"8602_CR23","doi-asserted-by":"crossref","unstructured":"Yang Z, Guan Q, Zhao K et al (2024) Multi-branch auxiliary fusion yolo with re-parameterization heterogeneous convolutional for accurate object detection. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, Singapore pp 492\u2013505","DOI":"10.1007\/978-981-97-8858-3_34"},{"key":"8602_CR24","doi-asserted-by":"publisher","unstructured":"Du D et al (2019) VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea (South), pp 213\u2013226, https:\/\/doi.org\/10.1109\/ICCVW.2019.00030","DOI":"10.1109\/ICCVW.2019.00030"},{"key":"8602_CR25","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 Remote Sens 159:296\u2013307","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"8602_CR26","doi-asserted-by":"publisher","first-page":"11632","DOI":"10.1109\/JSTARS.2024.3408154","volume":"17","author":"D Wang","year":"2024","unstructured":"Wang D, Zhang J, Xu M et al (2024) MTP: advancing remote sensing foundation model via multitask pretraining. IEEE J Sel Top Appl Earth Observ Remote Sens 17:11632\u201311654","journal-title":"IEEE J Sel Top Appl Earth Observ Remote Sens"},{"issue":"4","key":"8602_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11554-025-01719-6","volume":"22","author":"W Xu","year":"2025","unstructured":"Xu W, Wan Y, Zhao W (2025) ELA: efficient location attention for deep convolution neural networks. J Real-Time Image Process 22(4):1\u201314","journal-title":"J Real-Time Image Process"},{"key":"8602_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108784","volume":"178","author":"H Huang","year":"2024","unstructured":"Huang H, Chen Z, Zou Y et al (2024) Channel prior convolutional attention for medical image segmentation. Comput Biol Med 178:108784","journal-title":"Comput Biol Med"},{"key":"8602_CR29","doi-asserted-by":"publisher","unstructured":"Cao Y, Xu J, Lin S, Wei F, Hu H (2019) GCNet: non-local networks meet squeeze-excitation networks and beyond. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea (South), 2019, pp. 1971\u20131980, https:\/\/doi.org\/10.1109\/ICCVW.2019.00246","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"8602_CR30","first-page":"1140","volume":"35","author":"MH Guo","year":"2022","unstructured":"Guo MH, Lu CZ, Hou Q et al (2022) Segnext: rethinking convolutional attention design for semantic segmentation. Adv Neural Inf Process Syst 35:1140\u20131156","journal-title":"Adv Neural Inf Process Syst"},{"key":"8602_CR31","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee JY et al (2018) 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":"8602_CR32","unstructured":"Liu Y, Shao Z, Hoffmann N (2021) Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv:2112.05561"},{"key":"8602_CR33","doi-asserted-by":"crossref","unstructured":"Li Y, Hou Q, Zheng Z et al (2023) Large selective kernel network for remote sensing object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023, pp 16794\u201316805","DOI":"10.1109\/ICCV51070.2023.01540"},{"key":"8602_CR34","doi-asserted-by":"publisher","first-page":"129866","DOI":"10.1016\/j.neucom.2025.129866","volume":"634","author":"Y Si","year":"2025","unstructured":"Si Y, Xu H, Zhu X et al (2025) SCSA: Exploring the synergistic effects between spatial and channel attention. Neurocomputing 634:129866","journal-title":"Neurocomputing"},{"key":"8602_CR35","doi-asserted-by":"crossref","unstructured":"Ouyang D, He S, Zhang G et al (2023) Efficient multi-scale attention module with cross-spatial learning. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"8602_CR36","doi-asserted-by":"crossref","unstructured":"Zhao Y, Lv W, Xu S et al (2024) Detrs beat yolos on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 16965\u201316974","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"8602_CR37","doi-asserted-by":"publisher","first-page":"105057","DOI":"10.1016\/j.imavis.2024.105057","volume":"147","author":"M Kang","year":"2024","unstructured":"Kang M, Ting CM, Ting FF et al (2024) ASF-YOLO: A novel YOLO model with attentional scale sequence fusion for cell instance segmentation. Image Vis Comput 147:105057","journal-title":"Image Vis Comput"},{"key":"8602_CR38","unstructured":"Xu X, Jiang Y, Chen W et al (2022) Damo-yolo: a report on real-time object detection design. arXiv preprint arXiv:2211.15444"},{"key":"8602_CR39","doi-asserted-by":"publisher","unstructured":"Zhang Y, Ye M, Zhu G, Liu Y, Guo P, Yan J (2024) FFCA-YOLO for small object detection in remote sensing images. In: IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1\u201315, Art no. 5611215, https:\/\/doi.org\/10.1109\/TGRS.2024.3363057","DOI":"10.1109\/TGRS.2024.3363057"},{"key":"8602_CR40","doi-asserted-by":"crossref","unstructured":"Varghese R, Sambath M (2024) Yolov8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS). IEEE, pp 1\u20136","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"8602_CR41","doi-asserted-by":"crossref","unstructured":"Wang CY, Yeh I H, Mark Liao HY (2024) Yolov9: learning what you want to learn using programmable gradient information. In: European Conference on Computer Vision. Springer, Cham, pp 1\u201321","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"8602_CR42","first-page":"107984","volume":"37","author":"A Wang","year":"2024","unstructured":"Wang A, Chen H, Liu L et al (2024) Yolov10: real-time end-to-end object detection. Adv Neural Inf Process Syst 37:107984\u2013108011","journal-title":"Adv Neural Inf Process Syst"},{"key":"8602_CR43","unstructured":"Khanam R, Hussain M (2024) Yolov11: an overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725"},{"key":"8602_CR44","unstructured":"Tian Y, Ye Q, Doermann D. Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524, 2025."},{"issue":"14","key":"8602_CR45","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.3390\/rs17142421","volume":"17","author":"S Qu","year":"2025","unstructured":"Qu S, Dang C, Chen W et al (2025) SMA-YOLO: an improved YOLOv8 algorithm based on parameter-free attention mechanism and multi-scale feature fusion for small object detection in UAV images. Remote Sens 17(14):2421","journal-title":"Remote Sens"},{"key":"8602_CR46","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-025-07290-y","volume":"81","author":"H Liu","year":"2025","unstructured":"Liu H, Tan F, Jin Y (2025) Dual-YOLO: dual-path UAV aerial image target detection algorithm. J Supercomput 81:809. https:\/\/doi.org\/10.1007\/s11227-025-07290-y","journal-title":"J Supercomput"},{"key":"8602_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3576957","volume":"74","author":"J Xie","year":"2025","unstructured":"Xie J et al (2025) KL-YOLO: a lightweight adaptive global feature enhancement network for small-object detection in low-altitude remote sensing imagery. IEEE Trans Instrum Meas 74:1\u201313. https:\/\/doi.org\/10.1109\/TIM.2025.3576957","journal-title":"IEEE Trans Instrum Meas"},{"issue":"6","key":"8602_CR48","doi-asserted-by":"publisher","DOI":"10.3390\/drones9060429","volume":"9","author":"X Zhao","year":"2025","unstructured":"Zhao X, Zhang H, Zhang W et al (2025) MSUD-YOLO: a novel multiscale small object detection model for UAV aerial images. Drones 9(6):429","journal-title":"Drones"},{"key":"8602_CR49","doi-asserted-by":"publisher","first-page":"21783","DOI":"10.1109\/JSTARS.2025.3601579","volume":"18","author":"J Ou","year":"2025","unstructured":"Ou J, Shen Y, Du Y (2025) DHLNet: a dynamic hierarchical lightweight network for enhanced ship detection in remote sensing images. IEEE J Sel Top Appl Earth Obs Remote Sens 18:21783\u201321806. https:\/\/doi.org\/10.1109\/JSTARS.2025.3601579","journal-title":"IEEE J Sel Top Appl Earth Obs Remote Sens"},{"issue":"2","key":"8602_CR50","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.32604\/cmc.2025.061363","volume":"83","author":"H Wang","year":"2025","unstructured":"Wang H, Zhang Y, Zhu C (2025) DAFPN-YOLO: an improved UAV-based object detection algorithm based on YOLOv8s. Comput Mater Contin 83(2):1929\u20131949. https:\/\/doi.org\/10.32604\/cmc.2025.061363","journal-title":"Comput Mater Contin"},{"issue":"8","key":"8602_CR51","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging11080285","volume":"11","author":"L Yang","year":"2025","unstructured":"Yang L, Honarvar Shakibaei Asli B (2025) MSConv-YOLO: an improved small target detection algorithm based on YOLOv8. J Imaging 11(8):285","journal-title":"J Imaging"},{"issue":"12","key":"8602_CR52","doi-asserted-by":"publisher","first-page":"2099","DOI":"10.3390\/rs17122099","volume":"17","author":"B Yao","year":"2025","unstructured":"Yao B, Zhang C, Meng Q et al (2025) SRM-YOLO for small object detection in remote sensing images. Remote Sens 17(12):2099","journal-title":"Remote Sens"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08602-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-026-08602-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08602-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T08:30:47Z","timestamp":1779438647000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-026-08602-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":52,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["8602"],"URL":"https:\/\/doi.org\/10.1007\/s11227-026-08602-6","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]},"assertion":[{"value":"15 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"443"}}