Multi-view Regularized Extreme Learning Machine for Human Action Recognition

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

5 Citations (Scopus)
318 Downloads (Pure)


In this paper, we propose an extension of the ELM algorithm that is able to exploit multiple action representations. This is achieved by incorporating proper regularization terms in the ELM optimization problem. In order to determine both optimized network weights and action representation combination weights, we propose an iterative optimization process. The proposed algorithm has been evaluated by using the state-of-the-art action video representation on three publicly available action recognition databases, where its performance has been compared with that of two commonly used video representation combination approaches, i.e., the vector concatenation before learning and the combination of classification outcomes based on learning on each view independently.
Original languageEnglish
Title of host publicationArtificial Intelligence: Methods and Applications
Subtitle of host publication8th Hellenic Conference on AI, SETN 2014, Ioannina, Greece, May 15-17, 2014. Proceedings
Number of pages11
ISBN (Electronic)9783319070643
Publication statusPublished - 2014
EventConference on Artificial Intelligence (SETN): Methods and Applications - Ioannina, Greece
Duration: 15 May 201417 May 2014

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743


ConferenceConference on Artificial Intelligence (SETN): Methods and Applications


  • Extreme Learning Machine
  • Multi-view Learning
  • Single-hidden Layer Feedforward networks
  • Human Action Recognition


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

Cite this