University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Deep Sign: Hybrid CNN-HMM for Continuous Sign Language Recognition

Koller, O, Zargaran, O, Ney, H and Bowden, R (2016) Deep Sign: Hybrid CNN-HMM for Continuous Sign Language Recognition In: The British Machine Vision Conference (BMVC) 2016, 2016-09-19 - 2016-09-22, York.

[img]
Preview
Text
Koller_BMVC2016.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (3MB) | Preview
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

This paper introduces the end-to-end embedding of a CNN into a HMM, while interpreting the outputs of the CNN in a Bayesian fashion. The hybrid CNN-HMM combines the strong discriminative abilities of CNNs with the sequence modelling capabilities of HMMs. Most current approaches in the field of gesture and sign language recognition disregard the necessity of dealing with sequence data both for training and evaluation. With our presented end-to-end embedding we are able to improve over the state-of-the-art on three challenging benchmark continuous sign language recognition tasks by between 15% and 38% relative and up to 13.3% absolute.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
AuthorsEmailORCID
Koller, OUNSPECIFIEDUNSPECIFIED
Zargaran, OUNSPECIFIEDUNSPECIFIED
Ney, HUNSPECIFIEDUNSPECIFIED
Bowden, RUNSPECIFIEDUNSPECIFIED
Date : September 2016
Copyright Disclaimer : Note that copyright in BMVC papers is held by the authors in every instance. The BMVA, as publisher of the proceedings, holds copyright over the collection, but the authors may make any use of papers they have authored including making an exact copy available on their own or other websites.
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 03 Oct 2016 09:31
Last Modified : 03 Oct 2016 09:31
URI: http://epubs.surrey.ac.uk/id/eprint/812319

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