Multitask learning (MTL) leverages task-relatedness to enhance performan...
Regression analysis is a key area of interest in the field of data analy...
Transformer-based methods have exhibited remarkable potential in single ...
Binary feature descriptors have been widely used in various visual
measu...
Line segment detection plays a cornerstone role in computer vision tasks...
Multi-view subspace clustering methods have employed learned
self-repres...
Detection and description of line segments lay the basis for numerous vi...
Deep neural networks have achieved great success in many data processing...
Multitask learning (MTL) can utilize the relatedness between multiple ta...
Time series anomaly detection strives to uncover potential abnormal beha...
Ensemble learning serves as a straightforward way to improve the perform...
With powerful ability to exploit latent structure of self-representation...
The existing tensor networks adopt conventional matrix product for
conne...
Weakly-supervised anomaly detection aims at learning an anomaly detector...
Recently, adversarial attack methods have been developed to challenge th...
Single image super-resolution (SISR), which aims to reconstruct a
high-r...
Deep learning has been used to image compressive sensing (CS) for enhanc...
A single perturbation can pose the most natural images to be misclassifi...
Existing RGB-D salient object detection (SOD) models usually treat RGB a...
Multi-view clustering has attracted increasing attentions recently by
ut...
Low rank tensor ring model is powerful for image completion which recove...
Feature selection is a widely used dimension reduction technique to sele...
It is a recognized fact that the classification accuracy of unseen class...
Recent works in domain adaptation always learn domain invariant features...
Recurrent neural networks (RNNs) are widely used as a memory model for
s...
Recent works that utilized deep models have achieved superior results in...
Tensor completion can estimate missing values of a high-order data from ...
Most compressive sensing (CS) reconstruction methods can be divided into...
Robust tensor principal component analysis (RTPCA) can separate the low-...
Deep learning models are known to be vulnerable to adversarial examples....
Machine learning models are vulnerable to adversarial examples. For the
...
The coupled tensor decomposition aims to reveal the latent data structur...
While being the de facto standard coordinate representation in human pos...
Recurrent neural networks (RNNs) are known to be difficult to train due ...
Age estimation is a classic learning problem in computer vision. Many la...
Robust tensor completion recoveries the low-rank and sparse parts from i...
The recently prevalent tensor train (TT) and tensor ring (TR) decomposit...
Tensor completion aims to recover a multi-dimensional array from its
inc...
Tensor completion aims to recover a multi-dimensional array from its
inc...
Image ordinal classification refers to predicting a discrete target valu...
Tensor completion recovers missing entries of multiway data. Teh missing...
Recurrent neural networks (RNNs) have been widely used for processing
se...
Depth-image-based rendering (DIBR) oriented view synthesis has been wide...
Pooling is an important component in convolutional neural networks (CNNs...
Deep network pruning is an effective method to reduce the storage and
co...
Face photo synthesis from simple line drawing is a one-to-many task as s...
Tensor principal component analysis (TPCA) is a multi-linear extension o...
Many works have concentrated on visualizing and understanding the inner
...