In recent years, two time series classification models, ROCKET and
MINIR...
We propose a high-rate scheme for discretely-modulated continuous-variab...
Advances in deep generative models shed light on de novo molecule genera...
A burst buffer is a common method to bridge the performance gap between ...
Whitening loss provides theoretical guarantee in avoiding feature collap...
Filter pruning has attracted increasing attention in recent years for it...
Image-text retrieval in remote sensing aims to provide flexible informat...
Domain generalization (DG) aims to learn a generalizable model from mult...
Filter pruning is a common method to achieve model compression and
accel...
Batch Normalization (BN) is a core and prevalent technique in accelerati...
A desirable objective in self-supervised learning (SSL) is to avoid feat...
Molecule generation, especially generating 3D molecular geometries from
...
This paper studies generalized truncated moment problems with unbounded ...
Embedding-based neural topic models could explicitly represent words and...
Energy-based latent variable models (EBLVMs) are more expressive than
co...
Batch normalization (BN) is a milestone technique in deep learning. It
n...
Edge computing has enabled a large set of emerging edge applications by
...
Knowledge graph embedding models learn the representations of entities a...
Deep convolutional neural networks (CNNs) with a large number of paramet...
Kronecker-factored Approximate Curvature (K-FAC) has recently been shown...
One-bit analog-to-digital converter (ADC), performing signal sampling as...
Chest X-rays are an important and accessible clinical imaging tool for t...
Previous studies dominantly target at self-supervised learning on real-v...
The rapid growth in literature accumulates diverse and yet comprehensive...
Generative adversarial networks (GANs) have achieved remarkable progress...
There is now extensive evidence demonstrating that deep neural networks ...
The nonlinearity of activation functions used in deep learning models ar...
Batch normalization (BN) is an important technique commonly incorporated...
Normalization techniques are essential for accelerating the training and...
Deep generative models have been successfully applied to Zero-Shot Learn...
Training neural networks with many processors can reduce time-to-solutio...
A massive amount of reviews are generated daily from various platforms. ...
Orthogonality is widely used for training deep neural networks (DNNs) du...
Capsule networks (CapsNets) are capable of modeling visual hierarchical
...
Batch Normalization (BN) is extensively employed in various network
arch...
There is a growing interest in creating tools to assist in clinical note...
Conditioning analysis uncovers the landscape of optimization objective b...
Extracting graph representation of visual scenes in image is a challengi...
We address the problem of spatio-temporal action detection in videos.
Ex...
Hash based nearest neighbor search has become attractive in many
applica...
Batch Normalization (BN) is ubiquitously employed for accelerating neura...
Content-based adult video detection plays an important role in preventin...
At present, the great achievements of convolutional neural network(CNN) ...
Emerging Deep Learning (DL) applications introduce heavy I/O workloads o...
Business Architecture (BA) plays a significant role in helping organizat...
Batch Normalization (BN) is capable of accelerating the training of deep...
Convolutional neural networks (CNNs) can be applied to graph similarity
...
Optimizing deep neural networks (DNNs) often suffers from the ill-condit...
Recent advances in imaging sensors and digital light projection technolo...