Spatio–Temporal Image Representation of 3D Skeletal Movements for View-Invariant Action Recognition with Deep Convolutional Neural Networks
Designing motion representations for 3D human action recognition from skeleton sequences is an important yet challenging task. An effective representation should be robust to noise, invariant to viewpoint changes and result in a good performance with low-computational demand. Two main challenges in...
Main Authors: | Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio A. Velastin |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/8/1932 |
Similar Items
-
Performance Comparison of Association Rule Algorithms with SPMF on Automotive Industry Data
by: Melih Nair, et al.
Published: (2019-07-01) -
Data Mining Application using Association Rule Mining ECLAT Algorithm Based on SPMF
by: Reynaldo Jason, et al.
Published: (2018-01-01) -
Learning to recognise 3D human action from a new skeleton‐based representation using deep convolutional neural networks
by: Huy‐Hieu Pham, et al.
Published: (2019-04-01) -
A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera
by: Huy Hieu Pham, et al.
Published: (2020-03-01) -
Multiple Feature Reweight DenseNet for Image Classification
by: Ke Zhang, et al.
Published: (2019-01-01)