期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
Pre-Locator Incorporating Swin-Transformer Refined Classifier for Traffic Sign Recognition
1
作者 Qiang Luo Wenbin Zheng 《Intelligent Automation & Soft Computing》 SCIE 2023年第8期2227-2246,共20页
In the field of traffic sign recognition,traffic signs usually occupy very small areas in the input image.Most object detection algorithms directly reduce the original image to a specific size for the input model duri... In the field of traffic sign recognition,traffic signs usually occupy very small areas in the input image.Most object detection algorithms directly reduce the original image to a specific size for the input model during the detection process,which leads to the loss of small object information.Addi-tionally,classification tasks are more sensitive to information loss than local-ization tasks.This paper proposes a novel traffic sign recognition approach,in which a lightweight pre-locator network and a refined classification network are incorporated.The pre-locator network locates the sub-regions of the traffic signs from the original image,and the refined classification network performs the refinement recognition task in the sub-regions.Moreover,an innovative module(named SPP-ST)is proposed,which combines the Spatial Pyramid Pool module(SPP)and the Swin-Transformer module as a new feature extractor to learn the special spatial information of traffic sign effec-tively.Experimental results show that the proposed method is superior to the state-of-the-art methods(82.1 mAP achieved on 218 categories in the TT100k dataset,an improvement of 19.7 percentage points compared to the previous method).Moreover,both the result analysis and the output visualizations further demonstrate the effectiveness of our proposed method.The source code and datasets of this work are available at https://github.com/DijiesitelaQ/TSOD. 展开更多
关键词 Traffic sign RECOGNITION swin-transformer YOLOX small object
下载PDF
Existence and Approximation of Statistical Solutions of the 3D MHD Equations
2
作者 ZHANG Yuanyuan CHEN Guanggan 《Journal of Partial Differential Equations》 2024年第3期326-354,共29页
This paper focuses on the statistical characteristics of the 3D MHD equations.We firstly establish an existence theorem of a Vishik-Fursikov measure of the 3D MHD equations by taking advantage of the Krein-Milman theo... This paper focuses on the statistical characteristics of the 3D MHD equations.We firstly establish an existence theorem of a Vishik-Fursikov measure of the 3D MHD equations by taking advantage of the Krein-Milman theorem along with some functional and measure theories.Then by applying the Topsoe lemma on the constructed trajectory space possessing some special topological properties,we show that the Vishik-Fursikov measure and the stationary Vishik-Fursikov statistical solution of the 3D MHD system are approximated by the counterparts of the 3D MHD-αsystem,respectively,as the parameterαdecreases to zero. 展开更多
关键词 3D MHD equations Vishik-Fursikov measures stationary statistical solutions convergence of measures.
原文传递
A GENERALIZED RESULT ON THE POLYNOMIAL-LIKE ITERATIVE EQUATION
3
作者 Pingping ZHANG Yingying ZENG 《Acta Mathematica Scientia》 SCIE CSCD 2021年第1期177-186,共10页
Most results on the polynomial-like iterative equation are given under the condition that the given function is monotone,while a work by L.Liu and X.Gong gets nonmonotone PM solutions with height 1 when the given func... Most results on the polynomial-like iterative equation are given under the condition that the given function is monotone,while a work by L.Liu and X.Gong gets nonmonotone PM solutions with height 1 when the given function is of the same case.Removing the condition on height for the given function,we first give a method to assert the nonexistence of C^(0)solutions,then present equivalent conditions for the existence of PM solutions with finite height.Finally,as an application of the equivalent conditions,we construct the PM solutions in the case that the given function has one fort. 展开更多
关键词 HEIGHT characteristic interval FORT PM function
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部