Non-Linear Stationary Subspace Analysis with Application to Video Classification

Abstract

Low-dimensional representations are key to the success of many video classification algorithms. However, the commonly-used dimensionality reduction techniques fail to account for the fact that only part of the signal is shared across all the videos in one class. As a consequence, the resulting representations contain instance-specific information, which introduces noise in the classification process. In this paper, we introduce Non-Linear Stationary Subspace Analysis: A method that overcomes this issue by explicitly separating the stationary parts of the video signal (i.e., the parts shared across all videos in one class), from its non-stationary parts (i.e., specific to individual videos). We demonstrate the effectiveness of our approach on action recognition, dynamic texture classification and scene recognition.

Cite

Text

Baktashmotlagh et al. "Non-Linear Stationary Subspace Analysis with Application to Video Classification." International Conference on Machine Learning, 2013.

Markdown

[Baktashmotlagh et al. "Non-Linear Stationary Subspace Analysis with Application to Video Classification." International Conference on Machine Learning, 2013.](https://mlanthology.org/icml/2013/baktashmotlagh2013icml-nonlinear/)

BibTeX

@inproceedings{baktashmotlagh2013icml-nonlinear,
  title     = {{Non-Linear Stationary Subspace Analysis with Application to Video Classification}},
  author    = {Baktashmotlagh, Mahsa and Harandi, Mehrtash and Bigdeli, Abbas and Lovell, Brian and Salzmann, Mathieu},
  booktitle = {International Conference on Machine Learning},
  year      = {2013},
  pages     = {450-458},
  volume    = {28},
  url       = {https://mlanthology.org/icml/2013/baktashmotlagh2013icml-nonlinear/}
}