Hand Activity Recognition From Automatic Estimated Egocentric Skeletons Combining Slow Fast and Graphical Neural Networks

In this paper, we present an unified framework for understanding hand action from the first-person video. The proposed framework composes two main components. The first component estimates three-dimensional (3D) hand joints from RGB images. Two network structures derived from the baseline HopeNet ne...

Descrición completa

Detalles Bibliográficos

Principais autores:	Viet-Duc Le, Van-Nam Hoang, Tien-Thanh Nguyen, Van-Hung Le, Thanh-Hai Tran, Hai Vu, Thi-Lan Le
Formato:	Artigo
Idioma:	Inglês
Publicado:	World Scientific Publishing 2023-02-01
Series:	Vietnam Journal of Computer Science
Assuntos:	2D/3D hand pose estimation egocentric vision GCN DDNet hand action recognition
Acceso en liña:	https://www.worldscientific.com/doi/10.1142/S219688882250035X
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!