Stacked denoising autoencoder for feature representation learning in pose-based action recognition

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

13 Citations (Scopus)

Abstract

In this paper, we studied Stacked Denoising Autoencoder(SDA) model for Human pose-based action recognition. We used public dataset Chalearn 2013 which contains Italian body language actions from 27 persons. We studied two model of SDA for pose clustering: 1) Traditional SDA with epoch and Neural Network supervised classifier and 2) Marginalized SDA which faster and ELM supervised classifier. We used supervised classifier by using initial cluster data from K-means. We deployed global tuning that updating the weight during iterative learning.

Original languageEnglish
Title of host publication2014 IEEE 3rd Global Conference on Consumer Electronics, GCCE 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages684-688
Number of pages5
ISBN (Electronic)9781479951451
DOIs
Publication statusPublished - 3 Feb 2014
Event2014 IEEE 3rd Global Conference on Consumer Electronics, GCCE 2014 - Tokyo, Japan
Duration: 7 Oct 201410 Oct 2014

Publication series

Name2014 IEEE 3rd Global Conference on Consumer Electronics, GCCE 2014

Conference

Conference2014 IEEE 3rd Global Conference on Consumer Electronics, GCCE 2014
Country/TerritoryJapan
CityTokyo
Period7/10/1410/10/14

Fingerprint

Dive into the research topics of 'Stacked denoising autoencoder for feature representation learning in pose-based action recognition'. Together they form a unique fingerprint.

Cite this