Skeleton-Based Action Recognition Using Multi-Scale and Multi-Stream Improved Graph Convolutional Network

Skeleton-Based Action Recognition Using Multi-Scale and Multi-Stream Improved Graph Convolutional Network

Graph convolutional networks (GCNs) have achieved outstanding performances on skeleton-based action recognition. However, several problems remain in existing GCN-based methods, and the spatial-temporal features are not discriminative enough. Temporal convolution with one fixed kernel cannot obtain m...

Full description

Bibliographic Details
Main Authors: Wang Li, Xu Liu, Zheng Liu, Feixiang Du, Qiang Zou
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Skeleton-based action recognition
graph convolutional network
multi-scale
multi-stream
attention mechanism
improved spatial-temporal
Online Access:https://ieeexplore.ieee.org/document/9159664/

Internet

https://ieeexplore.ieee.org/document/9159664/

Similar Items