Semi-CNN architecture for effective spatio-temporal learning in action recognition

• Main Authors: Leong, Mei Chee, Prasad, Dilip K., Lee, Yong Tsui, Lin, Feng
• Other Authors: School of Mechanical and Aerospace Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Mechanical engineering; Action Recognition; Spatio-temporal Features
• Online Access: https://hdl.handle.net/10356/146192
• Institution: Nanyang Technological University

This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D convolutional neural networks (CNNs), 3D CNNs can be applied directly on consecutive frames to extract spatio-temporal features. The aim of this work is...