Spatial Temporal Graph Convolutional Networks for Action Recognition
Spatial Temporal Graph Convolutional Networks for Action Recognition
Created using ChatSlide
An overview of Spatial Temporal Graph Convolutional Networks (ST-GCN) focusing on dynamics of skeleton poses, methodology for processing spatial-temporal graphs, and implementation for action recognition. It highlights evaluation results on key datasets, comparative performance metrics, and insights from analyses. The study also discusses ST-GCN's contributions, advancements in action recognition, and future research directions.