Recent breakthroughs in zero-shot voice synthesis have enabled imitating...
Real-world single image denoising is crucial and practical in computer
v...
We study robust reinforcement learning (RL) with the goal of determining...
An N-of-1 trial is a multiple crossover trial conducted in a single
indi...
Chemistry and materials science are complex. Recently, there have been g...
The quality of three-dimensional reconstruction is a key factor affectin...
Medical image segmentation methods normally perform poorly when there is...
It is often difficult to obtain sufficient training data for adaptive si...
With the development of deep learning processors and accelerators, deep
...
Supply chain management is aimed to keep going long-term performance of ...
Audio-driven talking face has attracted broad interest from academia and...
Drive-by sensing (i.e. vehicle-based mobile sensing) is an emerging data...
Pervasive and mobile sensing is an integral part of smart transport and ...
DER is the primary metric to evaluate diarization performance while faci...
Although residential crowding has many well-being implications, its
conn...
As a promising approach in model compression, knowledge distillation imp...
Federated learning (FL) is a distributed machine learning approach where...
We study policy optimization for Markov decision processes (MDPs) with
m...
We present Falconn++, a novel locality-sensitive filtering (LSF) approac...
As a single-track mobile platform, bikebot (i.e., bicycle-based robot) h...
Bikebot manipulation has advantages of the single-track robot mobility a...
As an important application in remote sensing, landcover classification
...
Energy harvesting technologies offer a promising solution to sustainably...
With the fast development of modern deep learning techniques, the study ...
We address the issue of safety in reinforcement learning. We pose the pr...
We present a fast block direct solver for the unified dynamic simulation...
Motivated by the problem of learning when the number of training samples...
Information flows are intrinsic properties of an multi-stage manufacturi...
Although the importance of using static analysis to detect taint-style
v...
It is widely believed that the perceptual system of an organism is optim...
Chronological age of healthy people is able to be predicted accurately u...
We address the issue of safety in reinforcement learning. We pose the pr...
Recently, satellites with high temporal resolution have fostered wide
at...
The rapid development of remote sensing techniques provides rich,
large-...
Lattice structures have been widely used in various applications of addi...
In the big data era, graph computing is widely used to exploit the hidde...
Pooled testing is widely used for screening for viral or bacterial infec...
The World Health Organization (WHO) guidelines for monitoring the
effect...
Multilayer perceptron (MLP) is a class of networks composed of multiple
...
The human brain works in an unsupervised way, and more than one brain re...
In recent years, IoT platforms and systems have been rapidly emerging.
A...
Cross-modal associations between voice and face from a person can be lea...
Existing works, including ELMO and BERT, have revealed the importance of...
The state-of-art DNN structures involve intensive computation and high m...
Emotion is well-recognized as a distinguished symbol of human beings, an...
Massive multi-threading in GPU imposes tremendous pressure on memory
sub...
Cloud based medical image analysis has become popular recently due to th...
Binary classification rules based on covariates typically depend on simp...
Novelty detection is the machine learning task to recognize data, which
...
Analogical reasoning is effective in capturing linguistic regularities. ...