# Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition

arXiv: https://arxiv.org/abs/2007.14690 · HTML: https://mlsanity.com/paper/2007.14690/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2020.

## Built on by (most cited first, 30 of 82)

- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [PYSKL: Towards Good Practices for Skeleton Action Recognition](https://mlsanity.com/paper/2205.09443/) (2022)
- [Skeleton-Contrastive 3D Action Representation Learning](https://mlsanity.com/paper/2108.03656/) (2021)
- [Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation](https://mlsanity.com/paper/2108.07181/) (2021)
- [Learning Discriminative Representations for Skeleton Based Action Recognition](https://mlsanity.com/paper/2303.03729/) (2023)
- [SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition](https://mlsanity.com/paper/2403.09508/) (2024)
- [Generative Action Description Prompts for Skeleton-based Action Recognition](https://mlsanity.com/paper/2208.05318/) (2022)
- [Hypergraph Transformer for Skeleton-based Action Recognition](https://mlsanity.com/paper/2211.09590/) (2022)
- [Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition](https://mlsanity.com/paper/2112.04178/) (2021)
- [Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2305.12398/) (2023)
- [DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition](https://mlsanity.com/paper/2210.05895/) (2022)
- [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)
- [IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2110.13385/) (2021)
- [Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2201.02849/) (2022)
- [Graph Contrastive Learning for Skeleton-based Action Recognition](https://mlsanity.com/paper/2301.10900/) (2023)
- [Navigating Open Set Scenarios for Skeleton-based Action Recognition](https://mlsanity.com/paper/2312.06330/) (2023)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)
- [Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos](https://mlsanity.com/paper/2404.07645/) (2024)
- [Hierarchical Graph Convolutional Skeleton Transformer for Action Recognition](https://mlsanity.com/paper/2109.02860/) (2021)
- [Skeleton-based Action Recognition via Adaptive Cross-Form Learning](https://mlsanity.com/paper/2206.15085/) (2022)
- [Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition](https://mlsanity.com/paper/2407.15706/) (2024)
- [Learning Human Motion Prediction via Stochastic Differential Equations](https://mlsanity.com/paper/2112.11124/) (2021)
- [InfoGCN++: Learning Representation by Predicting the Future for Online Human Skeleton-based Action Recognition](https://mlsanity.com/paper/2310.10547/) (2023)
- [ERA: Expert Retrieval and Assembly for Early Action Prediction](https://mlsanity.com/paper/2207.09675/) (2022)
- [Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness](https://mlsanity.com/paper/2305.11468/) (2023)
- [Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition](https://mlsanity.com/paper/2308.06707/) (2023)
- [Explore Human Parsing Modality for Action Recognition](https://mlsanity.com/paper/2401.02138/) (2024)
- [Skeleton-Based Human Action Recognition with Noisy Labels](https://mlsanity.com/paper/2403.09975/) (2024)

## Abstract (arXiv)

Graph Convolutional Networks (GCNs) have attracted increasing interests for the task of skeleton-based action recognition. The key lies in the design of the graph structure, which encodes skeleton topology information. In this paper, we propose Dynamic GCN, in which a novel convolutional neural network named Contextencoding Network (CeN) is introduced to learn skeleton topology automatically. In particular, when learning the dependency between two joints, contextual features from the rest joints are incorporated in a global manner. CeN is extremely lightweight yet effective, and can be embedded into a graph convolutional layer. By stacking multiple CeN-enabled graph convolutional layers, we build Dynamic GCN. Notably, as a merit of CeN, dynamic graph topologies are constructed for different input samples as well as graph convolutional layers of various depths. Besides, three alternative context modeling architectures are well explored, which may serve as a guideline for future research on graph topology learning. CeN brings only ~7% extra FLOPs for the baseline model, and Dynamic GCN achieves better performance with 2×~4× fewer FLOPs than existing methods. By further combining static physical body connections and motion modalities, we achieve state-of-the-art performance on three large-scale benchmarks, namely NTU-RGB+D, NTU-RGB+D 120 and Skeleton-Kinetics.