Semantic segmentation is a challenging task in computer vision. In recent years, the
performance of semantic segmentation has been greatly improved by using deep learning …

Big multimedia data is heterogeneous in essence, that is, the data may be a mixture of
video, audio, text, and images. This is due to the prevalence of novel applications in recent …

In this paper, we propose a simple unsupervised graph representation learning method to
conduct effective and efficient contrastive learning. Specifically, the proposed multiplet loss …

Abstract Multi-task learning (MTL), which optimizes multiple related learning tasks at the
same time, has been widely used in various applications, including natural language …

Previous multi-view spectral clustering methods are a two-step strategy, which first learns a
fixed common representation (or common affinity matrix) of all the views from original data …

Traditional graph clustering methods consist of two sequential steps, ie, constructing an
affinity matrix from the original data and then performing spectral clustering on the resulting …

This paper studies an example-driven k-parameter computation that identifies different k
values for different test samples in kNN prediction applications, such as classification …

Abstract KNN (K Nearest Neighbors) classification is one of top-10 data mining algorithms. It
is significant to extend KNN classifiers sensitive to costs for imbalanced data classification …

Aspect-based sentiment analysis technologies may be a very practical methodology for
securities trading, commodity sales, movie rating websites, etc. Most recent studies adopt …

This paper proposes a new unsupervised spectral feature selection method to preserve both
the local and global structure of the features as well as the samples. Specifically, our method …