Laplacian one class extreme learning machines for human action recognition

Vasileios Mygdalis, Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas

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

2 Citations (Scopus)
245 Downloads (Pure)

Abstract

A novel OCC method for human action recognition namely the Laplacian One Class Extreme Learning Machines is presented. The proposed method exploits local geometric data information within the OC-ELM optimization process. It is shown that emphasizing on preserving the local geometry of the data leads to a regularized solution, which models the target class more efficiently than the standard OC-ELM algorithm. The proposed method is extended to operate in feature spaces determined by the network hidden layer outputs, as well as in ELM spaces of arbitrary dimensions. Its superior performance against other OCC options is consistent among five publicly available human action recognition datasets.
Original languageEnglish
Title of host publication2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP 2016)
Subtitle of host publicationProceedings of a meeting held 21-23 September 2016, Montreal, QC, Canada
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages298-302
Number of pages5
ISBN (Electronic)9781509037247
ISBN (Print)9781509037254
DOIs
Publication statusPublished - Feb 2017
Event 18th International Workshop on Multimedia Signal Processing: MMSP2016 - Montreal, Canada
Duration: 21 Sep 201623 Sep 2016

Publication series

NameProceedings of the International Workshop on Multimedia Signal Processing (MMSP)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)2163-3517
ISSN (Electronic)2473-3628

Conference

Conference 18th International Workshop on Multimedia Signal Processing
CountryCanada
CityMontreal
Period21/09/1623/09/16

Fingerprint Dive into the research topics of 'Laplacian one class extreme learning machines for human action recognition'. Together they form a unique fingerprint.

Cite this