Generating 3D faces from textual descriptions has a multitude of
applica...
Meta learning recently has been heavily researched and helped advance th...
Existing Optimal Transport (OT) methods mainly derive the optimal transp...
Robust loss minimization is an important strategy for handling robust
le...
Although current deep learning-based methods have gained promising
perfo...
Streaming data collection is essential to real-time data analytics in va...
Modern deep neural networks can easily overfit to biased training data
c...
It has been shown that equivariant convolution is very helpful for many ...
Cross-contrast image translation is an important task for completing mis...
Meta learning has attracted much attention recently in machine learning
...
In the setting of continual learning, a network is trained on a sequence...
Differential evolution is one of the most prestigious population-based
s...
This paper investigates robust recovery of an undamped or damped spectra...
Efficient exploration is one of the most important issues in deep
reinfo...
Current machine learning has made great progress on computer vision and ...
The learning rate (LR) is one of the most important hyper-parameters in
...
The recent advancement of deep learning techniques has made great progre...
In this paper, we first propose a graph neural network encoding method f...
The advancement of artificial intelligence has cast a new light on the
d...
This paper proposes the first-ever algorithmic framework for tuning
hype...
Tuning hyper-parameters for evolutionary algorithms is an important issu...
Robust loss minimization is an important strategy for handling robust
le...
Bayesian approach as a useful tool for quantifying uncertainties has bee...
While deep networks have strong fitting capability to complex input patt...
While deep networks have strong fitting capability to complex input patt...
Hyperspectral imaging can help better understand the characteristics of
...
Deep neural networks are traditionally trained using human-designed
stoc...
Intelligent communication is gradually considered as the mainstream dire...
The cycleGAN is becoming an influential method in medical image synthesi...
As a promising area in artificial intelligence, a new learning paradigm,...
Single image rain removal is a typical inverse problem in computer visio...
A large number of recent genome-wide association studies (GWASs) for com...
Supervised learning frequently boils down to determining hidden and brig...
Multi-atlas segmentation approach is one of the most widely-used image
s...
It is known that Boosting can be interpreted as a gradient descent techn...
Compressive sensing (CS) is an effective approach for fast Magnetic Reso...
Hyperspectral image (HSI) denoising has been attracting much research
at...
Many computer vision problems can be posed as learning a low-dimensional...
In this paper, we present a novel approach to automatic 3D Facial Expres...
Background subtraction has been a fundamental and widely studied task in...
In this paper, we address the problem of estimating and removing non-uni...
This paper presents a middle-level video representation named Video Prim...
In recent years, the nuclear norm minimization (NNM) problem has been
at...
Sparse clustering, which aims to find a proper partition of an extremely...
Regularization is a well recognized powerful strategy to improve the
per...
Multilook processing is a widely used speckle reduction approach in synt...
In this paper, a new method is proposed for sparse PCA based on the recu...