Tampere University of Technology

TUTCRIS Research Portal

Semi-supervised classification of human actions based on neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
PublisherThe Institute of Electrical and Electronics Engineers, Inc.
Number of pages6
ISBN (Print)9781479952083
Publication statusPublished - 4 Dec 2014
Publication typeA4 Article in a conference publication
Event22nd International Conference on Pattern Recognition, ICPR 2014 - Stockholm, Sweden
Duration: 24 Aug 201428 Aug 2014


Conference22nd International Conference on Pattern Recognition, ICPR 2014


In this paper, we propose a novel algorithm for Single-hidden Layer Feed forward 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.