Discriminative non-linear stationary subspace analysis for video classification

Mahsa Baktashmotlagh, Mehrtash Harandi, Brian C. Lovell, Mathieu Salzmann

Research output: Contribution to journalArticleResearchpeer-review

26 Citations (Scopus)

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., the parts specific to individual videos). Our method also encourages the new representation to be discriminative, thus accounting for the underlying classification problem. We demonstrate the effectiveness of our approach on dynamic texture recognition, scene classification and action recognition.

Original languageEnglish
Article number6857376
Pages (from-to)2353-2366
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume36
Issue number12
DOIs
Publication statusPublished - 1 Dec 2014
Externally publishedYes

Keywords

  • kernel methods
  • stationarity
  • subspace analysis
  • Video classification

Cite this