{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T16:34:36Z","timestamp":1792254876618,"version":"4.4.0"},"reference-count":32,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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","award":["62105305"],"award-info":[{"award-number":["62105305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013318","name":"Shanxi Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["202404041101020"],"award-info":[{"award-number":["202404041101020"]}],"id":[{"id":"10.13039\/501100013318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009329","name":"Scientific Research and Technology Development Program of Guangxi Zhuang Autonomous Region","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.neunet.2026.108545","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:19:01Z","timestamp":1767658741000},"page":"108545","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":11,"special_numbering":"C","title":["AMSA-YOLO: Real-time object detection with adaptive multi-scale attention mechanism"],"prefix":"10.1016","volume":"197","author":[{"given":"Canjin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8691-2662","authenticated-orcid":false,"given":"Chunhui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglong","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1576-0793","authenticated-orcid":false,"given":"Rijun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108545_bib0008","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M. YOLOv4: optimal speed and accuracy of object detection. arXiv:2004.10934 [cs.CV]. 2020. Available from: https:\/\/arxiv.org\/abs\/2004.10934."},{"key":"10.1016\/j.neunet.2026.108545_bib0014","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020","journal-title":"Lecture Notes in Computer Science"},{"key":"10.1016\/j.neunet.2026.108545_bib0016","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A. Emerging properties in self-supervised vision transformers. arXiv:2104.14294 [cs.CV]. 2021. Available from: https:\/\/doi.org\/10.48550\/ARXIV.2104.14294.","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"2","key":"10.1016\/j.neunet.2026.108545_bib0030","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The PASCAL visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.108545_bib0027","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2918","article-title":"Simple copy-paste is a strong data augmentation method for instance segmentation","author":"Ghiasi","year":"2021"},{"key":"10.1016\/j.neunet.2026.108545_bib0001","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.neunet.2026.108545_bib0002","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"key":"10.1016\/j.neunet.2026.108545_bib0021","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.neunet.2026.108545_bib0009","article-title":"ultralytics\/yolov5: v7.0-YOLOv5 SOTA realtime instance segmentation","author":"Jocher","year":"2022","journal-title":"Zenodo."},{"key":"10.1016\/j.neunet.2026.108545_bib0013","article-title":"YOLO by ultralytics","author":"Jocher","year":"2023","journal-title":"GitHub Repository."},{"key":"10.1016\/j.neunet.2026.108545_bib0007","article-title":"YOLO11 by Ultralytics","author":"Jocher","year":"2024","journal-title":"GitHub Repository"},{"key":"10.1016\/j.neunet.2026.108545_bib0029","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2026.108545_bib0006","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.neunet.2026.108545_bib0023","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neunet.2026.108545_bib0005","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"21","article-title":"SSD: single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.neunet.2026.108545_bib0024","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"10.1016\/j.neunet.2026.108545_bib0004","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.neunet.2026.108545_bib0003","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108545_bib0028","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"658","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"10.1016\/j.neunet.2026.108545_bib0018","unstructured":"Sapkota, R., Cheppally, R.H., Sharda, A., Karkee, M. RF-DETR object detection vs YOLOv12: A study of transformer-based and CNN-based architectures for single-class and multi-class greenfruit detection in complex orchard environments under label ambiguity. arXiv:2504.13099 [cs.CV]. 2025. Available from: https:\/\/doi.org\/10.48550\/ARXIV.2504.13099."},{"key":"10.1016\/j.neunet.2026.108545_bib0032","unstructured":"Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., Sun, J. CrowdHuman: a benchmark for detecting human in a crowd. arXiv:1805.00123 [cs.CV]. 2018. Available from: https:\/\/arxiv.org\/abs\/1805.00123."},{"key":"10.1016\/j.neunet.2026.108545_bib0026","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3578","article-title":"An analysis of scale invariance in object detection SNIP","author":"Singh","year":"2018"},{"key":"10.1016\/j.neunet.2026.108545_bib0025","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"},{"key":"10.1016\/j.neunet.2026.108545_bib0019","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T. FCOS: Fully convolutional one-stage object detection. arXiv:1904.01355 [cs.CV]. 2019. Available from: https:\/\/doi.org\/10.48550\/ARXIV.1904.01355.","DOI":"10.1109\/ICCV.2019.00972"},{"key":"10.1016\/j.neunet.2026.108545_bib0010","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.neunet.2026.108545_bib0011","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., Liao, H.Y.M. YOLOv9: learning what you want to learn using programmable gradient information. arXiv:2402.13616 [cs.CV]. 2024. Available from: https:\/\/arxiv.org\/abs\/2402.13616.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"10.1016\/j.neunet.2026.108545_bib0012","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., Ding, G. YOLOv10: real-time end-to-end object detection. arXiv:2405.14458 [cs.CV]. 2024. Available from: https:\/\/arxiv.org\/abs\/2405.14458."},{"key":"10.1016\/j.neunet.2026.108545_bib0022","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.neunet.2026.108545_bib0020","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. arXiv:1912.02424 [cs.CV]. 2019. Available from: https:\/\/doi.org\/10.48550\/ARXIV.1912.02424.","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"10.1016\/j.neunet.2026.108545_bib0017","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., Chen, J. DETRs beat YOLOs on real-time object detection. arXiv:2304.08069 [cs.CV]. 2023. Available from: https:\/\/doi.org\/10.48550\/ARXIV.2304.08069.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"10.1016\/j.neunet.2026.108545_bib0015","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J. Deformable DETR: Deformable transformers for end-to-end object detection. arXiv:2010.04159 [cs.CV]. 2020. Available from: https:\/\/doi.org\/10.48550\/ARXIV.2010.04159."},{"issue":"11","key":"10.1016\/j.neunet.2026.108545_bib0031","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 Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026000080?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026000080?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:50:06Z","timestamp":1773967806000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026000080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":32,"alternative-id":["S0893608026000080"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108545","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"AMSA-YOLO: Real-time object detection with adaptive multi-scale attention mechanism","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108545","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108545"}}