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

Guillaume Devineau (1) , Wang Xi (2) , Fabien Moutarde (1) , Jie Yang (2)

1 CAOR - Centre de Robotique
2 Shanghai Jiao Tong University [Shanghai]

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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Intelligence artificielle [cs.AI]; Traitement du signal et de l'image [eess.SP]; Apprentissage [cs.LG]; Réseau de neurones [cs.NE]

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⟩