Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Explore this paper's citation graph
Summary
A novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data.
- Type
- preprint
- Published
- 2018-01-23
- Cited by
- 5,443
- References
- 32
- Access
- Open access
- OpenAlex
- https://openalex.org/W2784435047
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:19167105
Keywords
Computer science, Tree traversal, Generalization, Action recognition, Graph
References
- Deep Convolutional Networks on Graph-Structured Data
- Differential Recurrent Neural Networks for Action Recognition
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Spectral Networks and Locally Connected Networks on Graphs
- Modeling video evolution for action recognition
- Action recognition with trajectory-pooled deep-convolutional descriptors
- Hierarchical recurrent neural network for skeleton based action recognition
- Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group
- Real-time human pose recognition in parts from single depth images
- Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
- Two-Stream Convolutional Networks for Action Recognition in Videos
- ImageNet classification with deep convolutional neural networks
- Pixel Recurrent Neural Networks
- Learning Convolutional Neural Networks for Graphs
- Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
- Deformable Convolutional Networks
- A New Representation of Skeleton Sequences for 3D Action Recognition
- On Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks
- Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
- The Kinetics Human Action Video Dataset
Cited by
- Adaptive Detrending to Accelerate Convolutional Gated Recurrent Unit Training for Contextual Video Recognition
- Action Recognition With Spatio–Temporal Visual Attention on Skeleton Image Sequences
- Through-Wall Human Pose Estimation Using Radio Signals
- Recognize Actions by Disentangling Components of Dynamics
- Skeleton-Based Relational Modeling for Action Recognition
- Adaptive Spectral Graph Convolutional Networks for Skeleton-Based Action Recognition
- Graph Edge Convolutional Neural Networks for Skeleton-Based Action Recognition
- A unified model for human activity recognition using spatial distribution of gradients and difference of Gaussian kernel
- Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition
- Human Action Recognition and Prediction: A Survey
- ARBEE: Towards Automated Recognition of Bodily Expression of Emotion in the Wild
- Skeleton Feature Fusion Based on Multi-Stream LSTM for Action Recognition
- Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds
- Higher-order Graph Convolutional Networks
- Part-based Graph Convolutional Network for Action Recognition
- Spectral–Spatial Graph Convolutional Networks for Semisupervised Hyperspectral Image Classification
- Improving Human Action Recognition through Hierarchical Neural Network Classifiers
- A Large-scale RGB-D Database for Arbitrary-view Human Action Recognition
- DA-Net: Learning the Fine-Grained Density Distribution With Deformation Aggregation Network
- ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
Related papers
- Exploring graph traversal algorithms in graph-based molecular generation
- Exploring graph traversal algorithms in graph-based molecular generation
- Discovery of Frequent Traversal Patterns from Weighted Traversals and Performance Enhancement by Traversal Split
- Exploring Graph Traversal Algorithms in Graph-Based Molecular Generation
- An efficient approach for the maintenance of path traversal patterns