# Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition

arXiv: https://arxiv.org/abs/1912.09745 · HTML: https://mlsanity.com/paper/1912.09745/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks](https://mlsanity.com/paper/2109.12946/) (2021)
- [Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2112.10570/) (2021)
- [Real-World Graph Convolution Networks (RW-GCNs) for Action Recognition in Smart Video Surveillance](https://mlsanity.com/paper/2201.05739/) (2022)
- [Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains](https://mlsanity.com/paper/2301.04494/) (2023)
- [AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement](https://mlsanity.com/paper/2208.03444/) (2022)
- [Transformers in Action Recognition: A Review on Temporal Modeling](https://mlsanity.com/paper/2302.01921/) (2022)
- [Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Identification/Recognition](https://mlsanity.com/paper/2104.09145/) (2021)
- [Domain Adaptation for Multi-label Image Classification: a Discriminator-free Approach](https://mlsanity.com/paper/2505.14333/) (2025)

## Abstract (arXiv)

This paper extends the Spatial-Temporal Graph Convolutional Network (ST-GCN) for skeleton-based action recognition by introducing two novel modules, namely, the Graph Vertex Feature Encoder (GVFE) and the Dilated Hierarchical Temporal Convolutional Network (DH-TCN). On the one hand, the GVFE module learns appropriate vertex features for action recognition by encoding raw skeleton data into a new feature space. On the other hand, the DH-TCN module is capable of capturing both short-term and long-term temporal dependencies using a hierarchical dilated convolutional network. Experiments have been conducted on the challenging NTU RGB-D-60 and NTU RGB-D 120 datasets. The obtained results show that our method competes with state-of-the-art approaches while using a smaller number of layers and parameters; thus reducing the required training time and memory.