Research Article

Tensorial Kernel Principal Component Analysis for Action Recognition

Table 2

List of important notations.

Notation Description

The th input tensor sample,
The projection of on
The projection on eigenvector
The mode- matricization of
The mode- matricization of th tensor sample
The vectorization of
The th projection matrix
The orthonormal base matrix of
The Gram or Kernel Matrix
The number of training samples
The order of a tensor object, the number of indices/modes
The -mode dimensionality in the projected space or the number of dominant eigenvectors
The number of most discriminative components of
The map from vector to RKHS
The map from tensor to HSF