Challenges and solutions for vision-based hand gesture interpretation: A review
Hand gesture is one of the most efficient and natural interfaces in current human–computer
interaction (HCI) systems. Despite the great progress achieved in hand gesture-based HCI …
interaction (HCI) systems. Despite the great progress achieved in hand gesture-based HCI …
An accelerating convolutional neural networks via a 2D entropy based-adaptive filter search method for image recognition
The success of CNNs for various vision tasks has been accompanied by a significant
increase in required FLOPs and parameter quantities, which has impeded the deployment of …
increase in required FLOPs and parameter quantities, which has impeded the deployment of …
Cross-layer importance evaluation for neural network pruning
Y Lian, P Peng, K Jiang, W Xu - Neural Networks, 2024 - Elsevier
Filter pruning has achieved remarkable success in reducing memory consumption and
speeding up inference for convolutional neural networks (CNNs). Some prior works, such as …
speeding up inference for convolutional neural networks (CNNs). Some prior works, such as …
Class-specific representation based distance metric learning for image set classification
Image set classification, which compares the similarity between image sets with variable
quantity, quality and unordered heterogeneous images, has drawn increased research …
quantity, quality and unordered heterogeneous images, has drawn increased research …
Spatial–contextual variational autoencoder with attention correction for anomaly detection in retinal OCT images
Anomaly detection refers to leveraging only normal data to train a model for identifying
unseen abnormal cases, which is extensively studied in various fields. Most previous …
unseen abnormal cases, which is extensively studied in various fields. Most previous …
Two-directional two-dimensional fractional-order embedding canonical correlation analysis for multi-view dimensionality reduction and set-based video recognition
Set-based video recognition is an important application in practice, and many specialized
approaches have been proposed. However, most of these methods either only use one kind …
approaches have been proposed. However, most of these methods either only use one kind …
Weakly supervised semantic segmentation via self-supervised destruction learning
Currently, weakly supervised semantic segmentation approaches adopt the Class Activation
Map (CAM) to generate the initial attention maps from the standard classification backbone …
Map (CAM) to generate the initial attention maps from the standard classification backbone …
TAILOR: InTer-feAture distinctIon fiLter fusiOn pRuning
Filter pruning is an effective method for reducing the size of convolutional neural networks
without sacrificing performance. Most filter pruning methods prioritize filters with high …
without sacrificing performance. Most filter pruning methods prioritize filters with high …
Attention-based adaptive structured continuous sparse network pruning
J Liu, W Liu, Y Li, J Hu, S Cheng, W Yang - Neurocomputing, 2024 - Elsevier
Deep neural network models, especially CNNs, have a wide range of applications in many
fields, but their high computational power requirements limit the deployment applications in …
fields, but their high computational power requirements limit the deployment applications in …
Compression of deep convolutional neural network using additional importance-weight-based filter pruning approach
SS Sawant, M Wiedmann, S Göb, N Holzer, EW Lang… - Applied Sciences, 2022 - mdpi.com
The success of the convolutional neural network (CNN) comes with a tremendous growth of
diverse CNN structures, making it hard to deploy on limited-resource platforms. These over …
diverse CNN structures, making it hard to deploy on limited-resource platforms. These over …