Common and Discriminative Subspace Kernel-Based Multiblock Tensor Partial Least Squares Regression

Authors

  • Ming Hou Laval University
  • Qibin Zhao RIKEN Brain Science Institute and Shanghai Jiao Tong University
  • Brahim Chaib-draa Laval University
  • Andrzej Cichocki RIKEN Brain Science Institute

DOI:

https://doi.org/10.1609/aaai.v30i1.10214

Keywords:

tensor regression models, kernel methods, multiblock regression models, multiblock partial least squares, human pose estimation, motion trajectory

Abstract

In this work, we introduce a new generalized nonlinear tensor regression framework called kernel-based multiblock tensor partial least squares (KMTPLS) for predicting a set of dependent tensor blocks from a set of independent tensor blocks through the extraction of a small number of common and discriminative latent components. By considering both common and discriminative features, KMTPLS effectively fuses the information from multiple tensorial data sources and unifies the single and multiblock tensor regression scenarios into one general model. Moreover, in contrast to multilinear model, KMTPLS successfully addresses the nonlinear dependencies between multiple response and predictor tensor blocks by combining kernel machines with joint Tucker decomposition, resulting in a significant performance gain in terms of predictability. An efficient learning algorithm for KMTPLS based on sequentially extracting common and discriminative latent vectors is also presented. Finally, to show the effectiveness and advantages of our approach, we test it on the real-life regression task in computer vision, i.e., reconstruction of human pose from multiview video sequences.

Downloads

Published

2016-02-21

How to Cite

Hou, M., Zhao, Q., Chaib-draa, B., & Cichocki, A. (2016). Common and Discriminative Subspace Kernel-Based Multiblock Tensor Partial Least Squares Regression. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). https://doi.org/10.1609/aaai.v30i1.10214

Issue

Section

Technical Papers: Machine Learning Methods