1KT - Knowledge Technology group [Hamburg] (University of Hamburg
Department of Informatics
Knowledge Technology, WTM
Vogt-Kölln-Straße 30
D - 22527 Hamburg - Allemagne)
Department of Informatics [Hamburg] (Head of Knowledge Technology
University of Hamburg
Faculty of Mathematics, Informatics and Natural Sciences
Department of Informatics, Knowledge Technology, WTM, Haus F
Vogt Koelln Str. 30
22527 Hamburg - Allemagne)
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.
https://hal.inria.fr/hal-01417710
Contributeur : Xavier Hinaut
<>
Soumis le : vendredi 16 décembre 2016 - 09:48:17
Dernière modification le : vendredi 11 janvier 2019 - 15:48:03
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, 2016, 〈https://www.elen.ucl.ac.be/esann/index.php?pg=esann16_programme〉. 〈hal-01417710〉
