Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition

@article{Li2019ActionalStructuralGC,
  title={Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition},
  author={Maosen Li and Siheng Chen and Xu Chen and Ya Zhang and Yanfeng Wang and Qi Tian},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={3590-3598}
}
  • Maosen Li, Siheng Chen, Qi Tian
  • Published 26 April 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Action recognition with skeleton data has recently attracted much attention in computer vision. [] Key Method We also extend the existing skeleton graphs to represent higher-order dependencies, i.e. structural links.
Attention-Based Generative Graph Convolutional Network for Skeleton-Based Human Action Recognition
TLDR
This work proposes an end-to-end generative graph convolution network to learn the joints graph connection patterns directly from data and uses self attention to construct the spatial adjacency matrix of each skeleton frame.
Feedback Graph Convolutional Network for Skeleton-Based Action Recognition
TLDR
This is the first work that introduces a feedback mechanism into GCNs for action recognition, and the proposed FGCN achieves the state-of-the-art performance on all three datasets.
Shallow Graph Convolutional Network for Skeleton-Based Action Recognition
TLDR
A plug-and-play channel adaptive merging module (CAMM) specific for the human skeleton graph is proposed, which can merge the vertices from the same part of the skeleton graph adaptively and efficiently and builds a novel shallow graph convolutional network (SGCN) based on the module.
Temporal-Aware Graph Convolution Network for Skeleton-based Action Recognition
TLDR
A novel Temporal-Aware Graph Convolution Network that can model the sequential nature of human actions by designing a causal temporal convolution layer and presenting a novel cross-spatial-temporal graph convolution (3D-GCN) layer that extends an adaptive graph from the spatial to the temporal domain to capture local cross- Spatial-Temporal dependencies among joints.
Spatial Temporal Attention Graph Convolutional Networks with Mechanics-Stream for Skeleton-Based Action Recognition
TLDR
SPatialtemporal attention graph convolutional networks (STA-GCN) is the first method to consider joint importance and relationship at the same time and shows the potential that the attention edge and node can be easily applied to existing methods and improve the performance.
GCsT: Graph Convolutional Skeleton Transformer for Action Recognition
TLDR
This paper presents a novel architecture, named Graph Convolutional skeleton Transformer (GCsT), which can flexibly capture local-global contexts and has an effective combination of desirable properties, namely, dynamical attention and global context in Transformer, as well as hierarchy and local topology structure in GCNs.
A Novel Graph Representation for Skeleton-based Action Recognition
TLDR
A generic representation of skeleton sequences for action recognition is designed and a novel model called Temporal Graph Networks (TGN), which can obtain spatiotemporal features simultaneously is proposed, which outperforms other state-of-the-art methods.
Dual-Stream Structured Graph Convolution Network for Skeleton-Based Action Recognition
TLDR
This work proposes a dual-stream structured graph convolution network (DS-SGCN) to solve the skeleton-based action recognition problem and fuse two streams ofgraph convolution responses in order to predict the category information of human action in an end-to-end fashion.
Multi-Scale Adaptive Aggregate Graph Convolutional Network for Skeleton-Based Action Recognition
TLDR
A multi-scale adaptive aggregate graph convolution network (MSAAGCN) to aggregate the remote and multi-order semantic information of the skeleton data and comprehensively model the internal relations of the human body for feature learning is proposed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 35 REFERENCES
Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
TLDR
A novel model with spatial reasoning and temporal stack learning (SR-TSL) for skeleton-based action recognition, which consists of a spatial reasoning network (SRN) and a temporal stacklearning network (TSLN).
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation
TLDR
This paper introduces a global spatial aggregation scheme, which is able to learn superior joint co-occurrence features over local aggregation, and consistently outperforms other state-of-the-arts on action recognition and detection benchmarks like NTU RGB+D, SBU Kinect Interaction and PKU-MMD.
Hierarchical recurrent neural network for skeleton based action recognition
  • Yong Du, Wei Wang, Liang Wang
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
TLDR
This paper proposes an end-to-end hierarchical RNN for skeleton based action recognition, and demonstrates that the model achieves the state-of-the-art performance with high computational efficiency.
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
TLDR
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.
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
TLDR
This work proposes an end-to-end spatial and temporal attention model for human action recognition from skeleton data on top of the Recurrent Neural Networks with Long Short-Term Memory (LSTM), which learns to selectively focus on discriminative joints of skeleton within each frame of the inputs and pays different levels of attention to the outputs of different frames.
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
TLDR
This paper introduces new gating mechanism within LSTM to learn the reliability of the sequential input data and accordingly adjust its effect on updating the long-term context information stored in the memory cell, and proposes a more powerful tree-structure based traversal method.
Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition
TLDR
A deep progressive reinforcement learning (DPRL) method for action recognition in skeleton-based videos, which aims to distil the most informative frames and discard ambiguous frames in sequences for recognizing actions.
Enhanced skeleton visualization for view invariant human action recognition
A New Representation of Skeleton Sequences for 3D Action Recognition
TLDR
Deep convolutional neural networks are proposed to be used to learn long-term temporal information of the skeleton sequence from the frames of the generated clips, and a Multi-Task Learning Network (MTLN) is proposed to jointly process all Frames of the clips in parallel to incorporate spatial structural information for action recognition.
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
  • Tae Soo Kim, A. Reiter
  • Computer Science
    2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2017
TLDR
This work proposes to use a new class of models known as Temporal Convolutional Neural Networks (TCN) for 3D human action recognition, and aims to take a step towards a spatio-temporal model that is easier to understand, explain and interpret.
...
1
2
3
4
...