Discriminant Bag of Words based Representation for Human Action Recognition

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas

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

60 Citations (Scopus)
272 Downloads (Pure)


In this paper we propose a novel framework for human action recognition based on Bag of Words (BoWs) action representation, that unifies discriminative codebook generation and discriminant subspace learning. The proposed framework is able to, naturally, incorporate several (linear or non-linear) discrimination criteria for discriminant BoWs-based action representation. An iterative optimization scheme is proposed for sequential discriminant BoWs-based action representation and codebook adaptation based on action discrimination in a reduced dimensionality feature space where action classes are better discriminated. Experiments on five publicly available data sets aiming at different application scenarios demonstrate that the proposed unified approach increases the codebook discriminative ability providing enhanced action classification performance.
Original languageEnglish
Pages (from-to)185-192
Number of pages8
JournalPattern Recognition Letters
Early online date30 Jul 2014
Publication statusPublished - 1 Nov 2014


  • Bag of Words
  • Discriminant Learning
  • Codebook Learning


Dive into the research topics of 'Discriminant Bag of Words based Representation for Human Action Recognition'. Together they form a unique fingerprint.

Cite this