License: Creative Commons Attribution 3.0 Unported license (CC BY 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.TIME.2018.21
URN: urn:nbn:de:0030-drops-97865
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2018/9786/
Go to the corresponding LIPIcs Volume Portal

Tanisaro, Pattreeya ; Heidemann, Gunther

An Empirical Study on Bidirectional Recurrent Neural Networks for Human Motion Recognition

pdf-format:
LIPIcs-TIME-2018-21.pdf (4 MB)

Abstract

The deep recurrent neural networks (RNNs) and their associated gated neurons, such as Long Short-Term Memory (LSTM) have demonstrated a continued and growing success rates with researches in various sequential data processing applications, especially when applied to speech recognition and language modeling. Despite this, amongst current researches, there are limited studies on the deep RNNs architectures and their effects being applied to other application domains. In this paper, we evaluated the different strategies available to construct bidirectional recurrent neural networks (BRNNs) applying Gated Recurrent Units (GRUs), as well as investigating a reservoir computing RNNs, i.e., Echo state networks (ESN) and a few other conventional machine learning techniques for skeleton-based human motion recognition. The evaluation of tasks focuses on the generalization of different approaches by employing arbitrary untrained viewpoints, combined together with previously unseen subjects. Moreover, we extended the test by lowering the subsampling frame rates to examine the robustness of the algorithms being employed against the varying of movement speed.

BibTeX - Entry

@InProceedings{tanisaro_et_al:LIPIcs:2018:9786,
  author =	{Pattreeya Tanisaro and Gunther Heidemann},
  title =	{{An Empirical Study on Bidirectional Recurrent Neural Networks for Human Motion Recognition}},
  booktitle =	{25th International Symposium on Temporal Representation  and Reasoning (TIME 2018)},
  pages =	{21:1--21:19},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-089-7},
  ISSN =	{1868-8969},
  year =	{2018},
  volume =	{120},
  editor =	{Natasha Alechina and Kjetil N{\o}rv{\aa}g and Wojciech Penczek},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2018/9786},
  URN =		{urn:nbn:de:0030-drops-97865},
  doi =		{10.4230/LIPIcs.TIME.2018.21},
  annote =	{Keywords: Recurrent Neural Networks, Human Motion Classification, Echo State Networks, Motion Capture, Bidirectional Recurrent Neural Networks}
}

Keywords: Recurrent Neural Networks, Human Motion Classification, Echo State Networks, Motion Capture, Bidirectional Recurrent Neural Networks
Collection: 25th International Symposium on Temporal Representation and Reasoning (TIME 2018)
Issue Date: 2018
Date of publication: 08.10.2018

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI