Abstract: A novel method for skeleton-based action recognition by fusing multi-level spatial features and multi-level temporal features is proposed in this article. Recently, Graph Convolutional ...
The hand is composed of many different bones, muscles, and ligaments that allow for a large amount of movement and dexterity. There are three major types of bones in the hand itself: Phalanges. These ...
Abstract: Graph convolutional networks (GCN) have recently been studied to exploit the graph topology of the human body for skeleton-based action recognition. However, most of these methods ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback