Tensor Learning for Regression
- 18 August 2011
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 21 (2) , 816-827
Abstract
In this paper, we exploit the advantages of tensorial representations and propose several tensor learning models for regression. The model is based on the canonical/parallel-factor decomposition of tensors of multiple modes and allows the simultaneous projections of an input tensor to more than one direction along each mode. Two empirical risk functions are studied, namely, the square loss and ε-insensitive loss functions. The former leads to higher rank tensor ridge regression (TRR), and the latter leads to higher rank support tensor regression (STR), both formulated using the Frobenius norm for regularization. We also use the group-sparsity norm for regularization, favoring in that way the low rank decomposition of the tensorial weight. In that way, we achieve the automatic selection of the rank during the learning process and obtain the optimal-rank TRR and STR. Experiments conducted for the problems of head-pose, human-age, and 3-D body-pose estimations using real data from publicly available databases, verified not only the superiority of tensors over their vector counterparts but also the efficiency of the proposed algorithms.Keywords
This publication has 19 references indexed in Scilit:
- Surveying and comparing simultaneous sparse approximation (or group-lasso) algorithmsSignal Processing, 2011
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human MotionInternational Journal of Computer Vision, 2009
- Tensor Decompositions and ApplicationsSIAM Review, 2009
- Classifying matrices with a spectral regularization2007
- Modeling Appearances with Low-Rank SVM2007
- Supervised tensor learningKnowledge and Information Systems, 2007
- Linear image coding for regression and classification using the tensor-rank principle2005
- Sparse image coding using a 3D non-negative tensor factorization2005
- Non-negative tensor factorization with applications to statistics and computer vision2005
- Fast, reliable head tracking under varying illumination: an approach based on registration of texture-mapped 3D modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000