mlsanityData to 14 Oct 2026

Spatio-Temporal Graph Complementary Scattering Networks

arXiv 2110.12150 ↗First posted 23 Oct 2021cs.CV eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

Spatio-temporal graph signal analysis has a significant impact on a wide range of applications, including hand/body pose action recognition. To achieve effective analysis, spatio-temporal graph convolutional networks (ST-GCN) leverage the powerful learning ability to achieve great empirical successes; however, those methods need a huge amount of high-quality training data and lack theoretical interpretation. To address this issue, the spatio-temporal graph scattering transform (ST-GST) was proposed to put forth a theoretically interpretable framework; however, the empirical performance of this approach is constrainted by the fully mathematical design. To benefit from both sides, this work proposes a novel complementary mechanism to organically combine the spatio-temporal graph scattering transform and neural networks, resulting in the proposed spatio-temporal graph complementary scattering networks (ST-GCSN). The essence is to leverage the mathematically designed graph wavelets with pruning techniques to cover major information and use trainable networks to capture complementary information. The empirical experiments on hand pose action recognition show that the proposed ST-GCSN outperforms both ST-GCN and ST-GST.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 19 references that are in the map. First posted on arXiv 23 Oct 2021.

Builds on

16 of 19 references.

References · 16

  1. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  2. 2019Learning Trajectory Dependencies for Human Motion Predictioncited by 246
  3. 2017First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotationscited by 230
  4. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  5. 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
  6. 2016A Riemannian Network for SPD Matrix Learningcited by 162
  7. 2020Collaborative Motion Prediction via Neural Motion Message Passingcited by 55
  8. 2021Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Networkcited by 52
  9. 2019Symbiotic Graph Neural Networks for 3D Skeleton-based Human Action Recognition and Motion Predictioncited by 50
  10. 2018Geometric Scattering for Graph Data Analysiscited by 49
  11. 2018Diffusion Scattering Transforms on Graphscited by 44
  12. 2021Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Predictioncited by 37
4 more
  1. 2020Spatio-Temporal Graph Scattering Transformcited by 19
  2. 2016Transition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detectioncited by 18
  3. 2019Incorporating dynamicity of transportation network with multi-weight traffic graph convolutional network for traffic forecastingcited by 11
  4. 2020Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognitioncited by 9

Built on by

Not cited yet.