Distance-based Human Action Recognition using optimized class representations

Ioannis Pitas, Alexandros Iosifidis, Anastasios Tefas

Research output: Contribution to journalArticle (Academic Journal)peer-review

3 Citations (Scopus)
231 Downloads (Pure)

Abstract

We study distance-based classification of human actions and introduce a new metric learning approach based on logistic discrimination for the determination of a low-dimensional feature space of increased discrimination power. We argue that for effective distance-based classification, both the optimal projection space and the optimal class representation should be determined. We qualitatively and quantitatively illustrate the superiority of the proposed approach to metric learning approaches employing the class mean for class representation. We also introduce extensions of the proposed metric learning approach to allow for richer class representations and to operate in arbitrary-dimensional Hilbert spaces for non-linear feature extraction and classification. Experimental results denote that the performance of the proposed distance-based classification schemes is comparable (or even better) to that of Support Vector Machine classifier (in both the linear and kernel cases) which is currently the standard choice for human action recognition.
Original languageEnglish
Pages (from-to)47-55
Number of pages9
JournalNeurocomputing
Volume161
Early online date16 Mar 2015
DOIs
Publication statusPublished - 5 Aug 2015

Keywords

  • Distance-based classification
  • Optimized class representations

Fingerprint Dive into the research topics of 'Distance-based Human Action Recognition using optimized class representations'. Together they form a unique fingerprint.

Cite this