{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:21:19Z","timestamp":1777886479878,"version":"3.51.4"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Digital Signal Processing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.dsp.2026.106037","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:57:10Z","timestamp":1772697430000},"page":"106037","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["AESOD: Towards accurate and efficient general-purpose small object detection"],"prefix":"10.1016","volume":"176","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7466-6715","authenticated-orcid":false,"given":"Jiayu","family":"Peng","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1698-7236","authenticated-orcid":false,"given":"Kai","family":"Lv","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7146-5342","authenticated-orcid":false,"given":"Dexian","family":"Lin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7068-8766","authenticated-orcid":false,"given":"Liang","family":"Yuan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.dsp.2026.106037_bib0001","doi-asserted-by":"crossref","first-page":"6551","DOI":"10.3934\/mbe.2023282","article-title":"Deep learning-based small object detection: a survey","volume":"20","author":"Feng","year":"2023","journal-title":"Math. Biosci. Eng."},{"issue":"11","key":"10.1016\/j.dsp.2026.106037_bib0002","first-page":"13467","article-title":"Towards large-scale small object detection: survey and benchmarks","volume":"45","author":"Cheng","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106037_bib0003","unstructured":"A.M. Rekavandi, S. Rashidi, F. Boussaid, S. Hoefs, E. Akbas, et al., Transformers in small object detection: a benchmark and survey of state-of-the-art, arXiv: 2309.04902(2023)."},{"issue":"3","key":"10.1016\/j.dsp.2026.106037_bib0004","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","article-title":"Object detection in 20 years: a survey","volume":"111","author":"Zou","year":"2023","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.dsp.2026.106037_bib0005","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"10.1016\/j.dsp.2026.106037_bib0006","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"issue":"6","key":"10.1016\/j.dsp.2026.106037_bib0007","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106037_bib0008","series-title":"European Conference on Computer Vision","first-page":"21","article-title":"SSD: single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.dsp.2026.106037_bib0009","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.dsp.2026.106037_bib0010","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.dsp.2026.106037_bib0011","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7263","article-title":"YOLO9000: Better, faster, stronger","author":"Redmon","year":"2017"},{"key":"10.1016\/j.dsp.2026.106037_bib0012","unstructured":"J. Redmon, A. Farhadi, YOLOv3: an incremental improvement, arXiv: 1804.02767(2018)."},{"key":"10.1016\/j.dsp.2026.106037_bib0013","unstructured":"A. Bochkovskiy, C.-Y. Wang, H.-Y. M. Liao, YOLOv4: optimal speed and accuracy of object detection, arXiv: 2004.10934(2020)."},{"key":"10.1016\/j.dsp.2026.106037_bib0014","unstructured":"G. Jocher, J. Qiu, A. Chaurasia, Ultralytics YOLO, 2023, https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"10.1016\/j.dsp.2026.106037_bib0015","unstructured":"M. Lei, S. Li, Y. Wu, H. Hu, Y. Zhou, X. Zheng, G. Ding, S. Du, Z. Wu, Y. Gao, YOLOv13: real-time object detection with hypergraph-enhanced adaptive visual perception, arXiv: 2506.17733(2025)."},{"key":"10.1016\/j.dsp.2026.106037_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9308","article-title":"Deformable convNets v2: more deformable, better results","author":"Zhu","year":"2019"},{"key":"10.1016\/j.dsp.2026.106037_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10781","article-title":"EfficientDet: scalable and efficient object detection","author":"Tan","year":"2020"},{"issue":"18","key":"10.1016\/j.dsp.2026.106037_bib0018","doi-asserted-by":"crossref","first-page":"4580","DOI":"10.3390\/rs15184580","article-title":"SMFF-YOLO: a scale-adaptive yolo algorithm with multi-level feature fusion for object detection in uav scenes","volume":"15","author":"Wang","year":"2023","journal-title":"Remote Sens."},{"issue":"8","key":"10.1016\/j.dsp.2026.106037_bib0019","doi-asserted-by":"crossref","first-page":"526","DOI":"10.3390\/drones7080526","article-title":"Drone-YOLO: an efficient neural network method for target detection in drone images","volume":"7","author":"Zhang","year":"2023","journal-title":"Drones"},{"key":"10.1016\/j.dsp.2026.106037_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13668","article-title":"QueryDet: cascaded sparse query for accelerating high-resolution small object detection","author":"Yang","year":"2022"},{"issue":"1","key":"10.1016\/j.dsp.2026.106037_bib0021","article-title":"FocuDet: an efficient object detector for small object","volume":"14","author":"Shi","year":"2024","journal-title":"Sci. Rep."},{"key":"10.1016\/j.dsp.2026.106037_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2023.103752","article-title":"FE-YOLOv5: feature enhancement network based on YOLOv5 for small object detection","volume":"90","author":"Wang","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.dsp.2026.106037_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112849","article-title":"Dual-domain attentions for unmanned aerial vehicle small object detection","volume":"163","author":"Wang","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.dsp.2026.106037_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107455","article-title":"Small object detection in unmanned aerial vehicle images using multi-scale hybrid attention","volume":"128","author":"Song","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.dsp.2026.106037_bib0025","unstructured":"G. Jocher, A. Chaurasia, A. Stoken, J. Borovec, Y. Kwon, K. Michael, J. Fang, Z. Yifu, C. Wong, D. Montes, et al., Ultralytics\/YOLOv5: v7. 0-YOLOv5 sota realtime instance segmentation, Zenodo (2022)."},{"key":"10.1016\/j.dsp.2026.106037_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.112775","article-title":"VSTDet: a lightweight small object detection network inspired by the ventral visual pathway","volume":"171","author":"Niu","year":"2025","journal-title":"Appl. Soft. Comput."},{"key":"10.1016\/j.dsp.2026.106037_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105232","article-title":"SDMNet: spatially dilated multi-scale network for object detection for drone aerial imagery","volume":"150","author":"Battish","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.dsp.2026.106037_bib0028","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2778","article-title":"TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios","author":"Zhu","year":"2021"},{"key":"10.1016\/j.dsp.2026.106037_bib0029","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.dsp.2026.106037_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119997","article-title":"ETAM: ensemble transformer with attention modules for detection of small objects","volume":"224","author":"Zhang","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.dsp.2026.106037_bib0031","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, Deformable DETR: deformable transformers for end-to-end object detection, arXiv: 2010.04159(2020)."},{"key":"10.1016\/j.dsp.2026.106037_bib0032","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.dsp.2026.106037_bib0033","series-title":"2024 IEEE International Conference on Robotics and Automation (ICRA)","first-page":"6614","article-title":"HIC-YOLOv5: improved YOLOv5 for small object detection","author":"Tang","year":"2024"},{"issue":"4","key":"10.1016\/j.dsp.2026.106037_bib0034","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s11554-024-01519-4","article-title":"YOLO-TLA: an efficient and lightweight small object detection model based on YOLOv5","volume":"21","author":"Ji","year":"2024","journal-title":"J. Real Time Image Process."},{"key":"10.1016\/j.dsp.2026.106037_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105052","article-title":"HV-YOLOv8 by HDPconv: better lightweight detectors for small object detection","volume":"147","author":"Wang","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.dsp.2026.106037_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1580","article-title":"GhostNet: more features from cheap operations","author":"Han","year":"2020"},{"key":"10.1016\/j.dsp.2026.106037_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15751","article-title":"ParameterNet: parameters are all you need for large-scale visual pretraining of mobile networks","author":"Han","year":"2024"},{"issue":"11","key":"10.1016\/j.dsp.2026.106037_bib0038","doi-asserted-by":"crossref","first-page":"9528","DOI":"10.1109\/TNNLS.2022.3151138","article-title":"DualConv: dual convolutional kernels for lightweight deep neural networks","volume":"34","author":"Zhong","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"11","key":"10.1016\/j.dsp.2026.106037_bib0039","doi-asserted-by":"crossref","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","article-title":"Detection and tracking meet drones challenge","volume":"44","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.dsp.2026.106037_bib0040","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2110","article-title":"Traffic-sign detection and classification in the wild","author":"Zhu","year":"2016"},{"key":"10.1016\/j.dsp.2026.106037_bib0041","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3974","article-title":"DOTA: a large-scale dataset for object detection in aerial images","author":"Xia","year":"2018"},{"key":"10.1016\/j.dsp.2026.106037_bib0042","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6154","article-title":"Cascade R-CNN: delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.dsp.2026.106037_bib0043","unstructured":"X. Zhou, D. Wang, P. Kr\u00e4henb\u00fchl, Objects as points, arXiv: 1904.07850(2019)."},{"issue":"12","key":"10.1016\/j.dsp.2026.106037_bib0044","article-title":"Object detection in UAV images based on multi-scale split attention","volume":"43","author":"Mao","year":"2022","journal-title":"Acta Aeronaut. Astronaut. Sin."},{"key":"10.1016\/j.dsp.2026.106037_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2024.104554","article-title":"GD-YOLO: an improved convolutional neural network architecture for real-time detection of smoking and phone use behaviors","volume":"151","author":"Fu","year":"2024","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.dsp.2026.106037_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126440","article-title":"Precision and speed: LSOD-YOLO for lightweight small object detection","volume":"269","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.dsp.2026.106037_bib0047","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7464","article-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"10.1016\/j.dsp.2026.106037_bib0048","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"YOLOv9: learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"key":"10.1016\/j.dsp.2026.106037_bib0049","first-page":"107984","article-title":"YOLOv10: real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.dsp.2026.106037_bib0050","unstructured":"G. Jocher, J. Qiu, Ultralytics yolo26, 2026, https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"10.1016\/j.dsp.2026.106037_bib0051","unstructured":"Y. Tian, Q. Ye, D. Doermann, YOLOv12: attention-centric real-time object detectors, arXiv: 2502.12524(2025)."}],"container-title":["Digital Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1051200426001569?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1051200426001569?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T03:39:50Z","timestamp":1777606790000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1051200426001569"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":51,"alternative-id":["S1051200426001569"],"URL":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106037","relation":{},"ISSN":["1051-2004"],"issn-type":[{"value":"1051-2004","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"AESOD: Towards accurate and efficient general-purpose small object detection","name":"articletitle","label":"Article Title"},{"value":"Digital Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.dsp.2026.106037","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106037"}}