Stacked Denoising Autoencoder for feature representation learning in pose-based action recognition | IEEE Conference Publication | IEEE Xplore

Stacked Denoising Autoencoder for feature representation learning in pose-based action recognition


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 bo...Show More

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.
Date of Conference: 07-10 October 2014
Date Added to IEEE Xplore: 05 February 2015
Electronic ISBN:978-1-4799-5145-1
Print ISSN: 2378-8143
Conference Location: Tokyo, Japan

Contact IEEE to Subscribe

References

References is not available for this document.