Activity recognition with echo state networks using 3D body joints and objects category - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Activity recognition with echo state networks using 3D body joints and objects category

Abstract

In this paper we present our experiments with an echo state network (ESN) for the task of classifying high-level human activities from video data. ESNs are recurrent neural networks which are biologically plausible, fast to train and they perform well in processing arbitrary sequential data. We focus on the integration of body motion with the information on objects manipulated during the activity, in order to overcome the visual ambiguities introduced by the processing of articulated body motion. We investigate the outputs learned and the accuracy of classification obtained with ESNs by using a challenging dataset of long high-level activities. We finally report the results achieved on this dataset.
Fichier principal
Vignette du fichier
Mici_ESANN_2016.pdf (1.74 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01417710 , version 1 (16-12-2016)

Identifiers

  • HAL Id : hal-01417710 , version 1

Cite

Luiza Mici, Xavier Hinaut, Stefan Wermter. Activity recognition with echo state networks using 3D body joints and objects category. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), Apr 2016, Bruges, Belgium. pp.465 - 470. ⟨hal-01417710⟩

Collections

CNRS INRIA INRIA2
311 View
161 Download

Share

Gmail Facebook X LinkedIn More