UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Emotional expression classification using time-series kernels

Lőrincz, A; Jeni, L; Szabo, Z; Cohn, J; Kanade, T; (2013) Emotional expression classification using time-series kernels. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). (pp. 889 - 895). IEEE Green open access

[thumbnail of lorincz13emotional.pdf]
Preview
PDF
lorincz13emotional.pdf
Available under License : See the attached licence file.

Download (770kB)

Abstract

Recent advances in kernel methods are very promising for improving the estimation, clustering and classification of spatio-temporal processes. Facial expression estimation can take advantage of such methods if one considers marker positions and their motion in 3D space. We applied support vector classification with kernels derived from dynamic time-warping similarity measures. We achieved excellent results using only the 'motion pattern' of the PCA compressed representation of the marker point vector, the socalled shape parameters. Beyond the classification of full motion patterns, the classification of the initial phase of an emotion (i) is competitive with methods relying on textural information and (ii) has complementary advantages to texture based algorithms reinforcing the need for mixed approaches.

Type: Proceedings paper
Title: Emotional expression classification using time-series kernels
Event: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW): IEEE International Workshop on Analysis and Modeling of Faces and Gestures AMFG)
Location: Portland, Oregon
Dates: 2013-06-23 - 2013-06-28
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/CVPRW.2013.131
Publisher version: http://dx.doi.org/10.1109/CVPRW.2013.131
Language: English
Additional information: This is the authors' accepted version of this published article. © 2013 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.
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit
URI: https://discovery.ucl.ac.uk/id/eprint/1433104
Downloads since deposit
56Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item