University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Using Convolutional 3D Neural Networks for User-Independent Continuous Gesture Recognition

Camgoz, NC, Hadfield, SJ, Koller, O and Bowden, R (2016) Using Convolutional 3D Neural Networks for User-Independent Continuous Gesture Recognition In: Proceedings IEEE International Conference of Pattern Recognition (ICPR), ChaLearn Workshop, 2016-12-04 - 2016-12-08, Cancun, Mexico.

[img]
Preview
Text
camgoz2016icprw.pdf - Author's Original
Available under License : See the attached licence file.

Download (387kB) | Preview
[img]
Preview
Text (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

In this paper, we propose using 3D Convolutional Neural Networks for large scale user-independent continuous gesture recognition. We have trained an end-to-end deep network for continuous gesture recognition (jointly learning both the feature representation and the classifier). The network performs three-dimensional (i.e. space-time) convolutions to extract features related to both the appearance and motion from volumes of color frames. Space-time invariance of the extracted features is encoded via pooling layers. The earlier stages of the network are partially initialized using the work of Tran et al. before being adapted to the task of gesture recognition. An earlier version of the proposed method, which was trained for 11,250 iterations, was submitted to ChaLearn 2016 Continuous Gesture Recognition Challenge and ranked 2nd with the Mean Jaccard Index Score of 0.269235. When the proposed method was further trained for 28,750 iterations, it achieved state-of-the-art performance on the same dataset, yielding a 0.314779 Mean Jaccard Index Score.

Item Type: Conference or Workshop Item (Conference Paper)
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Camgoz, NCUNSPECIFIEDUNSPECIFIED
Hadfield, SJUNSPECIFIEDUNSPECIFIED
Koller, OUNSPECIFIEDUNSPECIFIED
Bowden, RUNSPECIFIEDUNSPECIFIED
Date : 4 December 2016
Copyright Disclaimer : Copyright 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 20 Dec 2016 10:38
Last Modified : 31 Oct 2017 18:59
URI: http://epubs.surrey.ac.uk/id/eprint/813060

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800