Deep metric learning autoencoder for nonlinear temporal alignment of human motion

Temporal alignment is an important preprocessing procedure for human action recognition. The challenge of temporal alignment problem is the temporal scale difference between human actions as well as the variability of each subject. Metric learning is the central problem of temporal alignment. This p...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE International Conference on Robotics and Automation (ICRA) pp. 2160 - 2166
Main Authors Xiaochuan Yin, Qijun Chen
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2016
Subjects
Correlation
Feature extraction
Learning systems
Linear programming
Measurement
Neural networks
Time series analysis
Online AccessGet full text
DOI10.1109/ICRA.2016.7487366

Cover

More Information
Summary:Temporal alignment is an important preprocessing procedure for human action recognition. The challenge of temporal alignment problem is the temporal scale difference between human actions as well as the variability of each subject. Metric learning is the central problem of temporal alignment. This paper presents a nonlinear time alignment method with deep autoencoder. The spatio-temporal features obtained from the neural network contain the metric information for feature comparison. The effectiveness of our method is verified with k-nearest neighbor (k-NN) classifier on MSR-Action 3D and MSR-Daily Activity 3D datasets. Experimental results illustrate that the proposed method achieves superior performance to other metric based techniques.
DOI:10.1109/ICRA.2016.7487366