Many of the existing machine learning algorithms, both supervised and unsupervised,
depend on the quality of the input characteristics to generate a good model. The amount of …

We propose a new algorithmic framework for learning autoencoders of data distributions. In
this framework, we minimize the discrepancy between the model distribution and the target …

Multi-modal clustering aims at finding a clustering structure shared by the data of different
modalities in an unsupervised way. Currently, solving this problem often relies on two …

Nondestructive testing (NDT) is an economical way of detecting subsurface defects in
composite products. Infrared thermography serves as a popular NDT method due to its high …

Traditional multi-view learning methods often rely on two assumptions:() the samples in
different views are well-aligned, and () their representations obey the same distribution in a …

This paper addresses unsupervised representation learning on tabular data containing
multiple views generated by distinct sources of measurement. Traditional methods, which …

In the field of multi-view learning (MVL), it is crucial to extract both common (consistent) and
unique (complementary) information across different views. While the focus has traditionally …

In plant breeding and genetics, predictive models traditionally rely on compact
representations of high-dimensional data, often using methods like Principal Component …

Although they have achieved great success in optical images, deep convolutional neural
networks underperform for ship detection in SAR images because of the lack of color and …

This paper describes the UM-pAligner for the parallel sentence identification shared task of
BUCC 2018. The proposed UM-pAligner system consists of two main components …