Semi-supervised image classification aims to classify a large quantity of unlabeled images
by typically harnessing scarce labeled images. Existing semi-supervised methods often …

Graph Neural Networks (GNNs) have been shown to achieve competitive results to tackle
graph-related tasks, such as node and graph classification, link prediction and node and …

A novel sub-Markov random walk (subRW) algorithm with label prior is proposed for seeded
image segmentation, which can be interpreted as a traditional random walker on a graph …

In this paper, the problem of non-rigid shape recognition is studied from the perspective of
metric geometry. In particular, we explore the applicability of diffusion distances within the …

This article reviews and discusses a geometric perspective on the well-known fact in graph
theory that the effective resistance is a metric on the nodes of a graph. The classical proofs …

How to propagate label information from labeled examples to unlabeled examples over a
graph has been intensively studied for a long time. Existing graph-based propagation …

Measuring distances between pairs of points on a 3D surface is a fundamental problem in
computer graphics and geometric processing. For most applications, the important …

Complex networks, such as biological, social, and communication networks, often entail
uncertainty, and thus, can be modeled as probabilistic graphs. Similar to the problem of …

The ability of Graph Neural Networks (GNNs) to capture long-range and global topology
information is limited by the scope of conventional graph Laplacian, leading to unsatisfactory …

The last two decades have witnessed the explosive growth of image production from digital
photographs to the medical scans, satellite images, and video films. Consequently, the …