Predictively encoded graph convolutional network for noise-robust skeleton-based action recognition

In skeleton-based action recognition, graph convolutional networks (GCNs), which model human body skeletons using graphical components such as nodes and connections, have recently achieved remarkable performance. While the current state-of-the-art methods for skeleton-based action recognition usuall...

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Netherlands), 2022-02, Vol.52 (3), p.2317-2331
Main Authors: Yoon, Yongsang, Yu, Jongmin, Jeon, Moongu
Format: Article
Language:English
Subjects:
Activity recognition
Artificial Intelligence
Artificial neural networks
Computer engineering
Computer Science
Datasets
Electrical engineering
Experiments
Learning
Machines
Manufacturing
Mechanical Engineering
Methods
Neural networks
Noise
Processes
Robustness
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In skeleton-based action recognition, graph convolutional networks (GCNs), which model human body skeletons using graphical components such as nodes and connections, have recently achieved remarkable performance. While the current state-of-the-art methods for skeleton-based action recognition usually assume that completely observed skeletons will be provided, it is problematic to realize this assumption in real-world scenarios since the captured skeletons may be incomplete or noisy. In this work, we propose a skeleton-based action recognition method that is robust to noise interference for the given skeleton features. The key insight of our approach is to train a model by maximizing the mutual information between normal and noisy skeletons using predictive coding in the latent space. We conducted comprehensive skeleton-based action recognition experiments with defective skeletons using the NTU-RGB+D and Kinetics-Skeleton datasets. The experimental results demonstrate that when the skeleton samples are noisy, our approach achieves outstanding performances compared with the existing state-of-the-art methods.
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-021-02487-z