Results 41 to 50 of about 62,654 (265)
Traffic sign recognition algorithm based on improved convolution neural network
上海师范大学学报. 自然科学版, 2018 For the problem of low traffic sign recognition rate due to gradient diffusion in convolution neural network(CNN), an improved convolution neural network was proposed.
ZHU Yongjia, ZHANG Jing
doaj +1 more source
电力工程技术, 2022 Relay protection device is an important part to ensure the safe and stable operation of power system. With the rapid increase of the number of substations and relay protection devices,the daily inspection workload of the operation and maintenance ...
WANG Ye +4 more
doaj +1 more source
Doubly Convolutional Neural Networks
CoRR, 2016 Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural networks (DCNNs), which significantly improve the performance of CNNs by further exploring this idea.
Shuangfei Zhai +3 more
openaire +3 more sources
Factorial Convolution Neural Networks
CoRR, 2021 In recent years, GoogleNet has garnered substantial attention as one of the base convolutional neural networks (CNNs) to extract visual features for object detection. However, it experiences challenges of contaminated deep features when concatenating elements with different properties.
Jaemo Sung, Eun-Sung Jung
openaire +2 more sources
Object-Aware Adaptive Convolution Kernel Attention Mechanism in Siamese Network for Visual Tracking
Applied Sciences, 2022 As a classic framework for visual object tracking, the Siamese convolutional neural network has received widespread attention from the research community.
Dongliang Yuan +4 more
doaj +1 more source
Compressing Convolutional Neural Networks
CoRR, 2015 Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as model sizes increase, so do the storage and memory requirements of the classifiers.
Wenlin Chen +4 more
openaire +2 more sources
Pointwise Convolutional Neural Networks [PDF]
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018 10 pages, 6 figures, 10 tables.
Binh-Son Hua +2 more
openaire +2 more sources
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Background and Objectives Multiple sclerosis (MS) exhibits racially disparate rates of disease progression. Black people with MS (B‐PwMS) experience a more severe disease course than non‐Hispanic White people with MS (NHW‐PwMS). Here we investigated structural and functional connectivity as well as structure–function decoupling in the ...
Emilio Cipriano +11 more
wiley +1 more source
Normalized Convolutional Neural Network
CoRR, 2020 We introduce a Normalized Convolutional Neural Layer, a novel approach to normalization in convolutional networks. Unlike conventional methods, this layer normalizes the rows of the im2col matrix during convolution, making it inherently adaptive to sliced inputs and better aligned with kernel structures. This distinctive approach differentiates it from
Dongsuk Kim +4 more
openaire +2 more sources
Annals of Clinical and Translational Neurology, EarlyView.ABSTRACT Objective Cognitive decline is a disabling and variable feature of Parkinson disease (PD). While cholinergic system degeneration is linked to cognitive impairments in PD, most prior research reported cross‐sectional associations. We aimed to fill this gap by investigating whether baseline regional cerebral vesicular acetylcholine transporter ...
Taylor Brown +6 more
wiley +1 more source