Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition

Valsamis Ntouskos, Panagiotis Papadakis, Fiora Pirri

2013

Abstract

In this paper we address the problem of human action recognition within Motion Capture sequences. We introduce a method based on Gaussian Process Latent Variable Models and Alignment Kernels. We build a new discriminative latent variable model with back-constraints induced by the similarity of the original sequences. We compare the proposed method with a standard sequence classification method based on Dynamic Time Warping and with the recently introduced V-GPDS model which is able to model highly dimensional dynamical systems. The proposed methodology exhibits high performance even for datasets that have not been manually preprocessed while it further allows fast inference by exploiting the back constraints.

Download


Paper Citation


in Harvard Style

Ntouskos V., Papadakis P. and Pirri F. (2013). Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 87-96. DOI: 10.5220/0004268600870096

in Bibtex Style

@conference{icpram13,
author={Valsamis Ntouskos and Panagiotis Papadakis and Fiora Pirri},
title={Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={87-96},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004268600870096},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition
SN - 978-989-8565-41-9
AU - Ntouskos V.
AU - Papadakis P.
AU - Pirri F.
PY - 2013
SP - 87
EP - 96
DO - 10.5220/0004268600870096