Semi-supervised classification of human actions based on Neural Networks

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas

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

10 Citations (Scopus)
218 Downloads (Pure)

Abstract

In this paper, we propose a novel algorithm for Single-hidden Layer Feedforward Neural networks training which is able to exploit information coming from both labeled and unlabeled data for semi-supervised action classification. We extend
the Extreme Learning Machine algorithm by incorporating appropriate regularization terms describing geometric properties and discrimination criteria of the training data representation in the ELM space to this end. The proposed algorithm is evaluated on human action recognition, where its performance is compared with that of other (semi-)supervised classification schemes. Experimental results on two publicly available action recognition databases denote its effectiveness.
Original languageEnglish
Title of host publication2014 22nd International Conference on Pattern Recognition (ICPR 2014)
Subtitle of host publicationProceedings of a meeting held 24-28 August 2014, Stockholm, Sweden
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1336-1341
Number of pages6
ISBN (Print)9781479952106
DOIs
Publication statusPublished - Jan 2015
EventIEEE International Conference on Pattern Recognition (ICPR) - Stockholm, Sweden
Duration: 24 Aug 201428 Aug 2014

Publication series

NameProceedings of the International Conference on Pattern Recognition (ICPR)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)1051-4651

Conference

ConferenceIEEE International Conference on Pattern Recognition (ICPR)
CountrySweden
CityStockholm
Period24/08/1428/08/14

Fingerprint

Dive into the research topics of 'Semi-supervised classification of human actions based on Neural Networks'. Together they form a unique fingerprint.

Cite this