TITLE = {{Learning Recurrent High-order Statistics for Skeleton-based Hand Gesture Recognition}}, AUTHOR = {Nguyen, Xuan Son and Brun, Luc and L{'e}zoray, Olivier and Bougleux, S{'e}bastien}, BOOKTITLE = {{International Conference on Pattern Recognition (ICPR - IEEE)}}, ADDRESS = {Milan (virtual), Italy}, YEAR = {2021}, url = {HAL:= https://hal.archives-ouvertes.fr/hal-03107675, pdf:=https://hal.archives-ouvertes.fr/hal-03107675/file/ICPR20__home_papercept_iapr.papercept.net_www_conferences_conferences_ICPR20_submissions_0443_FI.pdf}, HAL_ID = {hal-03107675}, HAL_VERSION = {v1}, theme="pattern", abstract="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. "