Application of reductive decomposition method for multilinear arrays (RDMMA) to animations

Authors:
Emre Demiralp
Affiliations:
Department of Psychology, University of Michigan, MI
Venue:
MMACTEE'09 Proceedings of the 11th WSEAS international conference on Mathematical methods and computational techniques in electrical engineering
Year:
2009

Citing 13
Cited 3

The truncated SVD as a method for regularization

BIT
Kronecker products, unitary matrices, and signal processing applications

SIAM Review
Accurate singular values of bidiagonal matrices

SIAM Journal on Scientific and Statistical Computing
Tensor rank is NP-complete

Journal of Algorithms
Multiway data analysis

Multiway data analysis
Rank, decomposition, and uniqueness for 3-way and n-way arrays

Multiway data analysis
On the early history of the singular value decomposition

SIAM Review
A decomposition for three-way arrays

SIAM Journal on Matrix Analysis and Applications
Bibliography on higher-order statistics

Signal Processing
A Multilinear Singular Value Decomposition

SIAM Journal on Matrix Analysis and Applications
A Link between the Canonical Decomposition in Multilinear Algebra and Simultaneous Matrix Diagonalization

SIAM Journal on Matrix Analysis and Applications
Decompositions of a Higher-Order Tensor in Block Terms—Part III: Alternating Least Squares Algorithms

SIAM Journal on Matrix Analysis and Applications
Applications of high dimensionalmodel representations to computer vision

WSEAS Transactions on Mathematics

High dimensional model representation (HDMR) based folded vector decomposition

AICT'11 Proceedings of the 2nd international conference on Applied informatics and computing theory
Weighted singular value decomposition for folded matrices

AICT'11 Proceedings of the 2nd international conference on Applied informatics and computing theory
Array flattening based univariate high dimensional model representation (AFBUHDMR)

AICT'11 Proceedings of the 2nd international conference on Applied informatics and computing theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

We have recently developed a dimension reductive method for the multilinear array decomposition such that the multilinear array under consideration is expressed as a linear combination of the two factor outer products scaled by an unknown value. Each outer product contains two arrays one of which is a single index vector while the other contains one less index than the original array. The unknown scalar, vector, and one less index containing array are determined in such a way that the Euclidean distance between the original array and this three factor term becomes minimum. This work aims to seek practical utilization of this method by experimenting with various multilinear data. To this end animations which are three index entities are attempted to be approximated. Results are promising and motivating for further development of this method in a domain general fashion.