# Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition

arXiv: https://arxiv.org/abs/2011.13322 · HTML: https://mlsanity.com/paper/2011.13322/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2020.

## Built on by (most cited first, 18 of 18)

- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Skeleton-Contrastive 3D Action Representation Learning](https://mlsanity.com/paper/2108.03656/) (2021)
- [Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition](https://mlsanity.com/paper/2108.04536/) (2021)
- [Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition](https://mlsanity.com/paper/2210.02693/) (2022)
- [D-STGCNT: A Dense Spatio-Temporal Graph Conv-GRU Network based on transformer for assessment of patient physical rehabilitation](https://mlsanity.com/paper/2401.06150/) (2023)
- [TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential](https://mlsanity.com/paper/2304.11631/) (2023)
- [Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition](https://mlsanity.com/paper/2402.02431/) (2024)
- [Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2202.02314/) (2022)
- [Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2208.08599/) (2022)
- [Causal Spatio-Temporal Prediction: An Effective and Efficient Multi-Modal Approach](https://mlsanity.com/paper/2505.17637/) (2025)
- [Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs](https://mlsanity.com/paper/2109.10257/) (2021)
- [Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting](https://mlsanity.com/paper/2311.12630/) (2023)
- [Action Recognition in Real-World Ambient Assisted Living Environment](https://mlsanity.com/paper/2503.23214/) (2025)
- [A Variational Graph Autoencoder for Manipulation Action Recognition and Prediction](https://mlsanity.com/paper/2110.13280/) (2021)
- [SiT-MLP: A Simple MLP with Point-wise Topology Feature Learning for Skeleton-based Action Recognition](https://mlsanity.com/paper/2308.16018/) (2023)
- [G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2509.07335/) (2025)
- [A Study on Real-time Object Detection using Deep Learning](https://mlsanity.com/paper/2602.15926/) (2026)
- [NeuroPath: Brain-Inspired Dual-Pathway Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2608.17487/) (2026)

## Abstract (arXiv)

Skeleton-based human action recognition has attracted much attention with the prevalence of accessible depth sensors. Recently, graph convolutional networks (GCNs) have been widely used for this task due to their powerful capability to model graph data. The topology of the adjacency graph is a key factor for modeling the correlations of the input skeletons. Thus, previous methods mainly focus on the design/learning of the graph topology. But once the topology is learned, only a single-scale feature and one transformation exist in each layer of the networks. Many insights, such as multi-scale information and multiple sets of transformations, that have been proven to be very effective in convolutional neural networks (CNNs), have not been investigated in GCNs. The reason is that, due to the gap between graph-structured skeleton data and conventional image/video data, it is very challenging to embed these insights into GCNs. To overcome this gap, we reinvent the split-transform-merge strategy in GCNs for skeleton sequence processing. Specifically, we design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths. Extensive experiments demonstrate that our network outperforms state-of-the-art methods by a significant margin with only 1/5 of the parameters and 1/10 of the FLOPs. Code is available at https://github.com/yellowtownhz/STIGCN.