# Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition

arXiv: https://arxiv.org/abs/1805.06184 · HTML: https://mlsanity.com/paper/1805.06184/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2018.

## Built on by (most cited first, 28 of 28)

- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Learning Discriminative Representations for Skeleton Based Action Recognition](https://mlsanity.com/paper/2303.03729/) (2023)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction](https://mlsanity.com/paper/2108.11244/) (2021)
- [Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction](https://mlsanity.com/paper/2208.00368/) (2022)
- [Hierarchical Prototype Networks for Continual Graph Representation Learning](https://mlsanity.com/paper/2111.15422/) (2021)
- [Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition](https://mlsanity.com/paper/2202.04075/) (2022)
- [On the Utility of 3D Hand Poses for Action Recognition](https://mlsanity.com/paper/2403.09805/) (2024)
- [NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification](https://mlsanity.com/paper/2103.03939/) (2021)
- [Topology-aware Embedding Memory for Continual Learning on Expanding Networks](https://mlsanity.com/paper/2401.13200/) (2024)
- [TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction](https://mlsanity.com/paper/2109.00953/) (2021)
- [Gegenbauer Graph Neural Networks for Time-varying Signal Reconstruction](https://mlsanity.com/paper/2403.19800/) (2024)
- [A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation](https://mlsanity.com/paper/2312.05830/) (2023)
- [LVDiffusor: Distilling Functional Rearrangement Priors from Large Models into Diffusor](https://mlsanity.com/paper/2312.01474/) (2023)
- [GLAN: A Graph-based Linear Assignment Network](https://mlsanity.com/paper/2201.02057/) (2022)
- [Double-chain Constraints for 3D Human Pose Estimation in Images and Videos](https://mlsanity.com/paper/2308.05298/) (2023)
- [Multimodal Contrastive Learning with Hard Negative Sampling for Human Activity Recognition](https://mlsanity.com/paper/2309.01262/) (2023)
- [Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint](https://mlsanity.com/paper/2304.12616/) (2023)
- [Learning Resource Allocation Policy: Vertex-GNN or Edge-GNN?](https://mlsanity.com/paper/2307.12480/) (2023)
- [Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance](https://mlsanity.com/paper/2410.16935/) (2024)
- [Seeing All From a Few: Nodes Selection Using Graph Pooling for Graph Clustering](https://mlsanity.com/paper/2105.05320/) (2021)
- [Learning System Dynamics without Forgetting](https://mlsanity.com/paper/2407.00717/) (2024)
- [Structural Connectome Harmonization Using Deep Learning: The Strength of Graph Neural Networks](https://mlsanity.com/paper/2507.13992/) (2025)
- [Koopman pose predictions for temporally consistent human walking estimations](https://mlsanity.com/paper/2205.02737/) (2022)
- [A multimodal gesture recognition dataset for desktop human-computer interaction](https://mlsanity.com/paper/2401.03828/) (2024)
- [G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2509.07335/) (2025)
- [Message Passing on the Edge: Towards Scalable and Expressive GNNs](https://mlsanity.com/paper/2510.13615/) (2025)
- [A non-invasive video-based method for individual identification of wildlife using gait dynamics](https://mlsanity.com/paper/2607.04518/) (2026)

## Abstract (arXiv)

This paper investigates body bones from skeleton data for skeleton based action recognition. Body joints, as the direct result of mature pose estimation technologies, are always the key concerns of traditional action recognition methods. However, instead of joints, we humans naturally identify how the human body moves according to shapes, lengths and places of bones, which are more obvious and stable for observation. Hence given graphs generated from skeleton data, we propose to develop convolutions over graph edges that correspond to bones in human skeleton. We describe an edge by integrating its spatial neighboring edges to explore the cooperation between different bones, as well as its temporal neighboring edges to address the consistency of movements in an action. A graph edge convolutional neural network is then designed for skeleton based action recognition. Considering the complementarity between graph node convolution and graph edge convolution, we additionally construct two hybrid neural networks to combine graph node convolutional neural network and graph edge convolutional neural network using shared intermediate layers. Experimental results on Kinetics and NTU-RGB+D datasets demonstrate that our graph edge convolution is effective to capture characteristic of actions and our graph edge convolutional neural network significantly outperforms existing state-of-art skeleton based action recognition methods. Additionally, more performance improvements can be achieved by the hybrid networks.