{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T02:42:57Z","timestamp":1747190577680,"version":"3.40.5"},"reference-count":42,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T00:00:00Z","timestamp":1637884800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangdong Natural Science Foundation Project","award":["2021A1515011496","2020A1010020041"],"award-info":[{"award-number":["2021A1515011496","2020A1010020041"]}]},{"name":"Guangdong Province Science and Technology Projects","award":["2021A1515011496","2020A1010020041"],"award-info":[{"award-number":["2021A1515011496","2020A1010020041"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mobile Information Systems"],"published-print":{"date-parts":[[2021,11,26]]},"abstract":"<jats:p>Remote sensing images are often of low quality due to the limitations of the equipment, resulting in poor image accuracy, and it is extremely difficult to identify the target object when it is blurred or small. The main challenge is that objects in sensing images have very few pixels. Traditional convolutional networks are complicated to extract enough information through local convolution and are easily disturbed by noise points, so they are usually not ideal for classifying and diagnosing small targets. The current solution is to process the feature map information at multiple scales, but this method does not consider the supplementary effect of the context information of the feature map on the semantics. In this work, in order to enable CNNs to make full use of context information and improve its representation ability, we propose a residual attention function fusion method, which improves the representation ability of feature maps by fusing contextual feature map information of different scales, and then propose a spatial attention mechanism for global pixel point convolution response. This method compresses global pixels through convolution, weights the original feature map pixels, reduces noise interference, and improves the network\u2019s ability to grasp global critical pixel information. In experiments, the remote sensing ship image recognition experiments on remote sensing image data sets show that the network structure can improve the performance of small-target detection. The results on cifar10 and cifar100 prove that the attention mechanism is universal and practical.<\/jats:p>","DOI":"10.1155\/2021\/6466051","type":"journal-article","created":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T23:50:10Z","timestamp":1637970610000},"page":"1-12","source":"Crossref","is-referenced-by-count":2,"title":["Remote Sensing Data Detection Based on Multiscale Fusion and Attention Mechanism"],"prefix":"10.1155","volume":"2021","author":[{"given":"Min","family":"Huang","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, Guangdong 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9955-0832","authenticated-orcid":true,"given":"Cong","family":"Cheng","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, Guangdong 510000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0992-4213","authenticated-orcid":true,"given":"Gennaro","family":"De Luca","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Arizona State University, Tempe, AZ 85287-2180, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/6625184"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107343"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5574732"},{"key":"4","first-page":"10","article-title":"Human activity recognition and embedded application based on convolutional neural network","volume-title":"Journal of Artificial Intelligence Technology","author":"Y. Xu"},{"key":"5","article-title":"Tracking statistical learning online: word segmentation in a target detection task","volume":"215","author":"L. K. S\u00e1ra","year":"2021","journal-title":"Acta Psychologica"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.3390\/s21010144"},{"key":"7","first-page":"1","article-title":"Technologies supporting artificial intelligence and robotics application development","volume-title":"Journal of Artificial Intelligence and Technology","author":"Y. Chen"},{"key":"8","first-page":"180","article-title":"Development of a robot for in-service radiography inspection of subsea flexible risers","volume-title":"Journal of Artificial Intelligence and Technology","author":"A. P. Kaur"},{"issue":"1","key":"9","article-title":"Deep learning based target detection algorithm for motion capture applications","volume":"1682","author":"H. Wang","year":"2020","journal-title":"Journal of Physics: Conference Series"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1049\/trit.2019.0028"},{"issue":"1","key":"11","first-page":"13","article-title":"Deep learning\u2010based action recognition with 3D skeleton: a survey","volume":"6","author":"Y. Xing","year":"2016","journal-title":"Journal of Intelligent Technology"},{"issue":"22","key":"12","article-title":"Vehicle detection in overhead satellite images using a one-stage object detection model","volume":"20","author":"S. DeliaGeorgiana","year":"2020","journal-title":"Sensors"},{"issue":"4","key":"13","article-title":"Airborne infrared aircraft target detection algorithm based on YOLOv4-tiny","volume":"1865","author":"X. Hou","year":"2021","journal-title":"Journal of Physics: Conference Series"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"author":"S. Ren","key":"15","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks"},{"author":"T. Y. Lin","key":"16","article-title":"Feature pyramid networks for object detection"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.3390\/s21010136"},{"author":"Z. Cai","key":"18","article-title":"A unified multi-scale deep convolutional neural network for fast object detection"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"K. Simonyan","key":"19"},{"article-title":"HyperNet: towards accurate region proposal generation and joint object detection","author":"T. Kong","key":"20","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.98"},{"article-title":"DSSD: Deconvolutional Single Shot Detector","year":"2017","author":"C. Y. Fu","key":"21"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00745"},{"key":"24","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"A. Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.5244\/c.30.87"},{"article-title":"Aggregated Residual Transformations for Deep Neural Networks","year":"2016","author":"S. Xie","key":"28"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.243"},{"author":"S. Zagoruyko","key":"30","article-title":"Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer"},{"article-title":"Attention is all you need","year":"2017","author":"A. Vaswani","key":"31"},{"article-title":"Non-local neural networks","year":"2017","author":"X. Wang","key":"32"},{"article-title":"GCNet: Non-local networks meet squeeze-excitation networks and beyond","year":"2019","author":"Y. Cao","key":"33"},{"volume-title":"U-net: Convolutional Networks for Biomedical Image Segmentation","year":"2015","author":"O. Ronneberger","key":"34"},{"article-title":"YOLOv3: an incremental improvement","year":"2018","author":"J. Redmon","key":"35"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.324"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1673\/1\/012040"},{"article-title":"Training data-efficient image transformers & distillation through attention","year":"2020","author":"H. Touvron","key":"38"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","year":"2019","author":"M. Tan","key":"40"},{"article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"M. Sandler","key":"41","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00474"},{"author":"F. Yu","key":"42","article-title":"Deep layer aggregation"}],"container-title":["Mobile Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/misy\/2021\/6466051.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/misy\/2021\/6466051.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/misy\/2021\/6466051.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T23:50:23Z","timestamp":1637970623000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/misy\/2021\/6466051\/"}},"subtitle":[],"editor":[{"given":"Xingsi","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,11,26]]},"references-count":42,"alternative-id":["6466051","6466051"],"URL":"https:\/\/doi.org\/10.1155\/2021\/6466051","relation":{},"ISSN":["1875-905X","1574-017X"],"issn-type":[{"type":"electronic","value":"1875-905X"},{"type":"print","value":"1574-017X"}],"subject":[],"published":{"date-parts":[[2021,11,26]]}}}