IEEE

Rotation- and Permutation-Equivariant Quantum Graph Neural Network for 3D Graph Data

Abstract: Equivariant quantum graph neural networks (EQGNNs) offer a potentially powerful method to process graph data. However, existing EQGNN models only consider the permutation symmetry of graphs, ...
IEEE

UniMotion: Bridging 2D and 3D Representations for Human Motion Prediction

Abstract: Human motion prediction (HMP) forecasts future human motion (pose sequences) based on previous motion data. While existing methods excel by learning motion dynamics from adjacent 3D skeleton ...