Skeleton-based action recognition using spatio-temporal lstm network with trust gates

• Main Authors: Liu, Jun, Shahroudy, Amir, Xu, Dong, Kot, Alex Chichung, Wang, Gang
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2020
• Subjects: Engineering::Electrical and electronic engineering; Action Recognition; Recurrent Neural Networks
• Online Access: https://hdl.handle.net/10356/136885
• Institution: Nanyang Technological University

Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activ...