G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition
Not on the map. Why?
Abstract (arXiv)
Graph Convolutional Networks (GCNs) have proven to be highly effective for skeleton-based action recognition, primarily due to their ability to leverage graph topology for feature aggregation, a key factor in extracting meaningful representations. However, despite their success, GCNs often struggle to effectively distinguish between ambiguous actions, revealing limitations in the representation of learned topological and spatial features. To address this challenge, we propose a novel approach, Gaussian Topology Refinement Gated Graph Convolution (G3CN), to address the challenge of distinguishing ambiguous actions in skeleton-based action recognition. G3CN incorporates a Gaussian filter to refine the skeleton topology graph, improving the representation of ambiguous actions. Additionally, Gated Recurrent Units (GRUs) are integrated into the GCN framework to enhance information propagation between skeleton points. Our method shows strong generalization across various GCN backbones. Extensive experiments on NTU RGB+D, NTU RGB+D 120, and NW-UCLA benchmarks demonstrate that G3CN effectively improves action recognition, particularly for ambiguous samples.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 9 Sep 2025.
Builds on
26 of 39 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
- 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
- 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
- 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
- 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
- 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
- 2021Revisiting Skeleton-based Action Recognitioncited by 257
- 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
- 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
14 more
- 2019Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognitioncited by 135
- 2014Cross-view Action Modeling, Learning and Recognitioncited by 134
- 2021Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognitioncited by 90
- 2022Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 85
- 2020Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognitioncited by 82
- 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
- 2023Learning Discriminative Representations for Skeleton Based Action Recognitioncited by 62
- 2017Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gatescited by 54
- 2022IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognitioncited by 31
- 2018Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognitioncited by 28
- 2020Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 18
- 2023Graph Contrastive Learning for Skeleton-based Action Recognitioncited by 17
- 2022Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognitioncited by 13
- 2022Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognitioncited by 4
Built on by
Not cited yet.