ML Anthology

Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation

Lior Wolf, Amnon Shashua
CVPR 2003 pp. 635-642
doi:10.1109/CVPR.2003.1211413 /cvpr/2003/wolf2003cvpr-kernel/

Abstract

We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f(A, B) defined over pairs of matrices A, B based on the concept of principal angles between two linear subspaces. We show that the principal angles can be recovered using only inner-products between pairs of column vectors of the input matrices thereby allowing the original column vectors of A, B to be mapped onto arbitrarily high-dimensional feature spaces. We apply this technique to inference over image sequences applications of face recognition and irregular motion trajectory detection.

CVPR Semantic Scholar

Cite

Text

Wolf and Shashua. "Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211413

Markdown

[Wolf and Shashua. "Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/wolf2003cvpr-kernel/) doi:10.1109/CVPR.2003.1211413

BibTeX

@inproceedings{wolf2003cvpr-kernel,
  title     = {{Kernel Principal Angles for Classification Machines with Applications to Image Sequence Interpretation}},
  author    = {Wolf, Lior and Shashua, Amnon},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {635-642},
  doi       = {10.1109/CVPR.2003.1211413},
  url       = {https://mlanthology.org/cvpr/2003/wolf2003cvpr-kernel/}
}