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.
@article{arxiv.2603.02477,
title = {E2E-GNet: An End-to-End Skeleton-based Geometric Deep Neural Network for Human Motion Recognition},
author = {Mubarak Olaoluwa and Hassen Drira},
journal= {arXiv preprint arXiv:2603.02477},
year = {2026}
}