Computer vision is becoming an increasingly trendy word in the area of image processing.
With the emergence of computer vision applications, there is a significant demand to …

Graphs naturally appear in numerous application domains, ranging from social analysis,
bioinformatics to computer vision. The unique capability of graphs enables capturing the …

The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

The best performing learning algorithms devised for event cameras work by first converting
events into dense representations that are then processed using standard CNNs. However …

Point cloud registration is a key problem for computer vision applied to robotics, medical
imaging, and other applications. This problem involves finding a rigid transformation from …

Deep learning has revolutionized many machine learning tasks in recent years, ranging
from image classification and video processing to speech recognition and natural language …

Abstract We propose Graph-Coupled Oscillator Networks (GraphCON), a novel framework
for deep learning on graphs. It is based on discretizations of a second-order system of …

In recent years, graph neural networks (GNNs) have emerged as a powerful neural
architecture to learn vector representations of nodes and graphs in a supervised, end-to-end …

We propose octree-based transformers, named OctFormer, for 3D point cloud learning.
OctFormer can not only serve as a general and effective backbone for 3D point cloud …

We consider the problem of representation learning for graph data. Convolutional neural
networks can naturally operate on images, but have significant challenges in dealing with …