# A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition

arXiv: https://arxiv.org/abs/2111.06995 · HTML: https://mlsanity.com/paper/2111.06995/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 13 Nov 2021.

## Builds on (most cited first, 20 of 20)

- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1703.08274/) (2017)
- [NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing](https://mlsanity.com/paper/2011.02062/) (2020)
- [Interpretable 3D Human Action Analysis with Temporal Convolutional Networks](https://mlsanity.com/paper/1704.04516/) (2017)
- [Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning](https://mlsanity.com/paper/1805.02335/) (2018)
- [Dual-Cross Central Difference Network for Face Anti-Spoofing](https://mlsanity.com/paper/2105.01290/) (2021)
- [AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching](https://mlsanity.com/paper/2004.12292/) (2020)
- [RGB-D-based Human Motion Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/1711.08362/) (2017)
- [Multi-Modal Face Anti-Spoofing Based on Central Difference Networks](https://mlsanity.com/paper/2004.08388/) (2020)
- [Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition](https://mlsanity.com/paper/2008.03791/) (2020)
- [Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition](https://mlsanity.com/paper/2008.09412/) (2020)
- [Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks](https://mlsanity.com/paper/1611.02447/) (2016)
- [Skeleton-Based Online Action Prediction Using Scale Selection Network](https://mlsanity.com/paper/1902.03084/) (2019)
- [RGB-D-based Action Recognition Datasets: A Survey](https://mlsanity.com/paper/1601.05511/) (2016)
- [Skeleton-based Action Recognition Using LSTM and CNN](https://mlsanity.com/paper/1707.02356/) (2017)
- [SAR-NAS: Skeleton-based Action Recognition via Neural Architecture Searching](https://mlsanity.com/paper/2010.15336/) (2020)

## Built on by (most cited first, 6 of 6)

- [Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment](https://mlsanity.com/paper/2409.14336/) (2024)
- [MoFM: A Large-Scale Human Motion Foundation Model](https://mlsanity.com/paper/2502.05432/) (2025)
- [Joint Temporal Pooling for Improving Skeleton-based Action Recognition](https://mlsanity.com/paper/2408.09356/) (2024)
- [From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2303.08414/) (2023)
- [SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition](https://mlsanity.com/paper/2308.16018/) (2023)
- [HFGCN:Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2501.11007/) (2025)

## Abstract (arXiv)

This paper proposes a new graph convolutional operator called central difference graph convolution (CDGC) for skeleton based action recognition. It is not only able to aggregate node information like a vanilla graph convolutional operation but also gradient information. Without introducing any additional parameters, CDGC can replace vanilla graph convolution in any existing Graph Convolutional Networks (GCNs). In addition, an accelerated version of the CDGC is developed which greatly improves the speed of training. Experiments on two popular large-scale datasets NTU RGB+D 60 & 120 have demonstrated the efficacy of the proposed CDGC. Code is available at https://github.com/iesymiao/CD-GCN.