Convolutional Neural Networks for Multivariate Time Series Classification using both Inter- and Intra- Channel Parallel Convolutions

Abstract : In this paper, we study a convolutional neural network we recently introduced in [9], intended to recognize 3D hand gestures via multivariate time series classification. The Convolutional Neural Network (CNN) we proposed processes sequences of hand-skeletal joints' positions using parallel convolutions. We justify the model's architecture and investigate its performance on hand gesture sequence classification tasks. Our model only uses hand-skeletal data and no depth image. Experimental results show that our approach achieves a state-of-the-art performance on a challenging dataset (DHG dataset from the SHREC 2017 3D Shape Retrieval Contest).Our model achieves a 91.28% classification accuracy for the 14 gesture classes case and an 84.35% classification accuracy for the 28 gesture classes case.
Type de document :
Communication dans un congrès
Reconnaissance des Formes, Image, Apprentissage et Perception (RFIAP'2018), Jun 2018, Marne la Vallée, France
Liste complète des métadonnées

https://hal-mines-paristech.archives-ouvertes.fr/hal-01888862
Contributeur : Fabien Moutarde <>
Soumis le : vendredi 5 octobre 2018 - 13:53:42
Dernière modification le : lundi 12 novembre 2018 - 10:55:37

Fichier

deepConvol-MultivariateTimeSer...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01888862, version 1

Collections

Citation

Guillaume Devineau, Wang Xi, Fabien Moutarde, Jie Yang. Convolutional Neural Networks for Multivariate Time Series Classification using both Inter- and Intra- Channel Parallel Convolutions. Reconnaissance des Formes, Image, Apprentissage et Perception (RFIAP'2018), Jun 2018, Marne la Vallée, France. 〈hal-01888862〉

Partager

Métriques

Consultations de la notice

41

Téléchargements de fichiers

17