mlsanityData to 7 Oct 2026

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

arXiv 2603.02477 ↗First posted 3 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 85 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

39 of 85 references.

References · 39

  1. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  2. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  3. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  4. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  5. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  6. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  7. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  8. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  9. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 317
  10. 2015Diffusion-Convolutional Neural Networkscited by 268
  11. 2016A Riemannian Network for SPD Matrix Learningcited by 162
  12. 2018Adaptive Graph Convolutional Neural Networkscited by 155
27 more
  1. 2020Skeleton-based Action Recognition via Spatial and Temporal Transformer Networkscited by 98
  2. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  3. 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
  4. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  5. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  6. 2023Learning Discriminative Representations for Skeleton Based Action Recognitioncited by 62
  7. 2016Building Deep Networks on Grassmann Manifoldscited by 58
  8. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  9. 2019A neural network based on SPD manifold learning for skeleton-based hand gesture recognitioncited by 46
  10. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 46
  11. 2022Generative Action Description Prompts for Skeleton-based Action Recognitioncited by 43
  12. 2016Deep Learning on Lie Groups for Skeleton-based Action Recognitioncited by 42
  13. 2023Masked Motion Predictors are Strong 3D Action Representation Learnerscited by 41
  14. 2017RGB-D-based Human Motion Recognition with Deep Learning: A Surveycited by 37
  15. 2022Hypergraph Transformer for Skeleton-based Action Recognitioncited by 36
  16. 2024Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognitioncited by 29
  17. 2021GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognitioncited by 27
  18. 2019A Deep Learning Framework for Assessing Physical Rehabilitation Exercisescited by 26
  19. 2020A Survey on Deep Geometry Learning: From a Representation Perspectivecited by 19
  20. 2022Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognitioncited by 18
  21. 2016Measuring the Quality of Exercisescited by 17
  22. 2023Graph Contrastive Learning for Skeleton-based Action Recognitioncited by 17
  23. 2024Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformercited by 15
  24. 2016RGB-D-based Action Recognition Datasets: A Surveycited by 14
  25. 2024Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connectionscited by 11
  26. 2023Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognitioncited by 4
  27. 2016A Study of Vision based Human Motion Recognition and Analysiscited by 1

Built on by

Not cited yet.