Regularized Extreme Learning Machine for Multi-view Semi-supervised Action Recognition

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas

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

49 Citations (Scopus)
349 Downloads (Pure)

Abstract

In this paper, three novel classification algorithms aiming at (semi-)supervised action classification are proposed. Inspired by the effectiveness of discriminant subspace learning techniques and the fast and efficient Extreme Learning Machine (ELM) algorithm for Single-hidden Layer Feedforward Neural networks training, the ELM algorithm is extended by incorporating discrimination criteria in its optimization process, in order to enhance its classification performance. The proposed Discriminant ELM algorithm is extended, by incorporating proper regularization in its optimization process, in order to exploit information appearing in both labeled and unlabeled action instances. An iterative optimization scheme is proposed in order to address multi-view action classification. The proposed classification algorithms are evaluated on three publicly available action recognition databases providing state-of-the-art performance in all the cases.
Original languageEnglish
Pages (from-to)250-262
Number of pages13
JournalNeurocomputing
Volume145
Early online date12 May 2014
DOIs
Publication statusPublished - 5 Dec 2014

Keywords

  • Extreme Learning Machine
  • Semi-supervised Learning
  • Multi-view Learning

Fingerprint

Dive into the research topics of 'Regularized Extreme Learning Machine for Multi-view Semi-supervised Action Recognition'. Together they form a unique fingerprint.

Cite this