Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

11-2014

Abstract

In this paper, we present the method for our submission to the Emotion Recognition in the Wild Challenge (EmotiW 2014). The challenge is to automatically classify the emotions acted by human subjects in video clips under realworld environment. In our method, each video clip can be represented by three types of image set models (i.e. linear subspace, covariance matrix, and Gaussian distribution) respectively, which can all be viewed as points residing on some Riemannian manifolds. Then different Riemannian kernels are employed on these set models correspondingly for similarity/distance measurement. For classification, three types of classifiers, i.e. kernel SVM, logistic regression, and partial least squares, are investigated for comparisons. Finally, an optimal fusion of classifiers learned from different kernels and different modalities (video and audio) is conducted at the decision level for further boosting the performance. We perform an extensive evaluation on the challenge data (including validation set and blind test set), and evaluate the effects of different strategies in our pipeline. The final recognition accuracy achieved 50.4% on test set, with a significant gain of 16.7% above the challenge baseline 33.7%.

Keywords

Emotion recognition; EmotiW 2014 challenge; Multiple kernels; Riemannian manifold

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Proceedings of the 16th ACM International Conference on Multimodal Interaction, Istanbul, Turkey, 2014 Nov 12-16

First Page

494

Last Page

501

ISBN

9781450328852

Identifier

10.1145/2663204.2666274

Publisher

Association for Computing Machinery, Inc

City or Country

New York

Share

COinS