E2E-GNet: An End-to-End Skeleton-based Geometric Deep Neural Network for Human Motion Recognition

TL;DR

E2E-GNet is an innovative end-to-end geometric deep neural network that improves skeleton-based human motion recognition by incorporating geometric transformations and distortion-aware optimization, leading to superior performance across multiple datasets.

Contribution

The paper introduces a novel geometric transformation layer and a distortion-aware optimization layer in an end-to-end neural network for enhanced motion recognition.

Findings

Outperforms existing methods on five datasets

Achieves higher recognition accuracy with lower computational cost

Effectively retains geometric cues through novel layers

Abstract

Geometric deep learning has recently gained significant attention in the computer vision community for its ability to capture meaningful representations of data lying in a non-Euclidean space. To this end, we propose E2E-GNet, an end-to-end geometric deep neural network for skeleton-based human motion recognition. To enhance the discriminative power between different motions in the non-Euclidean space, E2E-GNet introduces a geometric transformation layer that jointly optimizes skeleton motion sequences on this space and applies a differentiable logarithm map activation to project them onto a linear space. Building on this, we further design a distortion-aware optimization layer that limits skeleton shape distortions caused by this projection, enabling the network to retain discriminative geometric cues and achieve a higher motion recognition rate. We demonstrate the impact of each layer through ablation studies and extensive experiments across five datasets spanning three domains show that E2E-GNet outperforms other methods with lower cost.