mlsanityData to 14 Oct 2026

Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition

arXiv 2308.10557 ↗First posted 21 Aug 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Hand action recognition is essential. Communication, human-robot interactions, and gesture control are dependent on it. Skeleton-based action recognition traditionally includes hands, which belong to the classes which remain challenging to correctly recognize to date. We propose a method specifically designed for hand action recognition which uses relative angular embeddings and local Spherical Harmonics to create novel hand representations. The use of Spherical Harmonics creates rotation-invariant representations which make hand action recognition even more robust against inter-subject differences and viewpoint changes. We conduct extensive experiments on the hand joints in the First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations, and on the NTU RGB+D 120 dataset, demonstrating the benefit of using Local Spherical Harmonics Representations. Our code is available at https://github.com/KathPra/LSHR_LSHT.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 55 references that are in the map. First posted on arXiv 21 Aug 2023.

Builds on

30 of 55 references.

References · 30

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  4. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  5. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  6. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  7. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  8. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  9. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  10. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 248
  11. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  12. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 230
18 more
  1. 2016A Riemannian Network for SPD Matrix Learningcited by 162
  2. 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
  3. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 126
  4. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  5. 2017Interpretable 3D Human Action Analysis with Temporal Convolutional Networkscited by 89
  6. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  7. 2020Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognitioncited by 82
  8. 2016Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networkscited by 63
  9. 2019Effective Rotation-invariant Point CNN with Spherical Harmonics kernelscited by 57
  10. 2018Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learningcited by 47
  11. 2022TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Countingcited by 44
  12. 2016Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methodscited by 29
  13. 2021Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognitioncited by 29
  14. 2020Learning to Orient Surfaces by Self-supervised Spherical CNNscited by 26
  15. 2021Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognitioncited by 22
  16. 2021AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognitioncited by 21
  17. 2016Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detectioncited by 18
  18. 2021NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actionscited by 11

Built on by

Not cited yet.