scholar.google.com › citations
Feb 5, 2024 · To solve these problems, an improved algorithm based on ST-GCN is proposed in this paper. Firstly, the direct relation of each node is ...
To solve these problems, an improved algorithm based on ST-GCN is proposed in this paper. Firstly, the direct relation of each node is determined in the spatial ...
The results demonstrate that the algorithm has achieved an increase of approximately 5% in recognition accuracy compared to its pre-improvement state, placing ...
5 days ago · ST-GCN is the first GCN algorithm working on 3D skeleton data, it utilizes spatio-temporal graph convolution kernels for down-sampling in order ...
This paper presents a novel framework for skeleton-based Hu- man Action Recognition (HAR) based on Graph Convolution. Networks (GCNs).
Missing: behavior | Show results with:behavior
Human recognition models based on spatial-temporal graph convolutional neural networks have been gradually developed, and we present an improved ...
May 7, 2024 · This study aims to enhance supervised human activity recognition based on spatiotemporal graph convolutional neural networks by addressing ...
Human Behavior Recognition Algorithm Based on OpenPose ...
www.researchgate.net › publication › 37...
Apr 21, 2024 · This paper extends the Spatial-Temporal Graph Convolutional Network (ST-GCN) for skeleton-based action recognition by introducing two novel ...
Mar 30, 2024 · This method improves the efficiency of human pose estimation models based on GCN. •. This method solves the problems of low accuracy in action ...
An improved ST-GCN model combined with the Alphapose posture estimation algorithm was proposed to intelligently monitor and identify the abnormal behavior of ...