This study proposes a set of generic rules to revise existing neural networks for 3D point
cloud processing to rotation-equivariant quaternion neural networks (REQNNs), in order to …

Graph neural networks have been widely used to represent 3D molecules, which capture
molecular attributes and geometric information through various message-passing …

Geometric graph is a special kind of graph with geometric features, which is vital to model
many scientific problems. Unlike generic graphs, geometric graphs often exhibit physical …

Deep neural networks (DNNs) in 3D scenes show a strong capability of extracting high-level
semantic features and significantly promote research in the 3D field. 3D shapes and scenes …

Hypercomplex neural networks are gaining increasing interest in the deep learning
community. The attention directed towards hypercomplex models originates from several …

Hypercomplex algebras have recently been gaining prominence in the field of deep learning
owing to the advantages of their division algebras over real vector spaces and their superior …

In this paper, we propose novel quaternion activation functions where we modify either the
quaternion magnitude or the phase, as an alternative to the commonly used split activation …

Hypercomplex algebras have recently been gaining prominence in the field of deep learning
owing to the advantages of their division algebras over real vector spaces and their superior …

We propose a novel quaternionic time-series compression methodology where we divide a
long time-series into segments of data, extract the min, max, mean and standard deviation of …

Estimating the 3DoF rotation from a single RGB image is an important yet challenging
problem. As a popular approach, probabilistic rotation modeling additionally carries …