Learning Recurrent High-order Statistics for Skeleton-based Hand Gesture Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Learning Recurrent High-order Statistics for Skeleton-based Hand Gesture Recognition

Résumé

High-order statistics have been proven useful in the framework of Convolutional Neural Networks (CNN) for a variety of computer vision tasks. In this paper, we propose to exploit high-order statistics in the framework of Recurrent Neural Networks (RNN) for skeleton-based hand gesture recognition. Our method is based on the Statistical Recurrent Units (SRU), an un-gated architecture that has been introduced as an alternative model for Long-Short Term Memory (LSTM) and Gate Recurrent Unit (GRU). The SRU captures sequential information by generating recurrent statistics that depend on a context of previously seen data and by computing moving averages at different scales. The integration of high-order statistics in the SRU significantly improves the performance of the original one, resulting in a model that is competitive to state-of-the-art methods on the Dynamic Hand Gesture (DHG) dataset, and outperforms them on the First-Person Hand Action (FPHA) dataset.
Fichier principal
Vignette du fichier
ICPR20__home_papercept_iapr.papercept.net_www_conferences_conferences_ICPR20_submissions_0443_FI.pdf (173.62 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03107675 , version 1 (12-01-2021)

Identifiants

  • HAL Id : hal-03107675 , version 1

Citer

Xuan Son Nguyen, Luc Brun, Olivier Lézoray, Sébastien Bougleux. Learning Recurrent High-order Statistics for Skeleton-based Hand Gesture Recognition. International Conference on Pattern Recognition (ICPR - IEEE), 2021, Milan (virtual), Italy. ⟨hal-03107675⟩
132 Consultations
196 Téléchargements

Partager

Gmail Facebook X LinkedIn More