3D-CNN-Based Fused Feature Maps with LSTM Applied to Action Recognition

3D-CNN-Based Fused Feature Maps with LSTM Applied to Action Recognition

Human activity recognition is an active field of research in computer vision with numerous applications. Recently, deep convolutional networks and recurrent neural networks (RNN) have received increasing attention in multimedia studies, and have yielded state-of-the-art results. In this research wor...

Full description

Bibliographic Details
Main Authors: Sheeraz Arif, Jing Wang, Tehseen Ul Hassan, Zesong Fei
Format: Article
Language:English
Published: MDPI AG 2019-02-01
Series:Future Internet
Subjects:
action recognition
fused features
3D convolution neural network
motion map
long short-term-memory
Online Access:https://www.mdpi.com/1999-5903/11/2/42

Internet

https://www.mdpi.com/1999-5903/11/2/42

Similar Items