Please use this identifier to cite or link to this item:
Title: Multi-score Learning for Affect Recognition: the Case of Body Postures
Authors: Meng, H
Kleinsmith, A
Bianchi-Berthouze, N
Keywords: Automatic emotion recognition;Observer variability;Affective computing;Affective posture;Pattern recognition;Multi-labeling;Multi-score learning
Issue Date: 2011
Publisher: Springer
Citation: LNCS, 2011, 6974 pp. 225 - 234
Abstract: An important challenge in building automatic affective state recognition systems is establishing the ground truth. When the groundtruth is not available, observers are often used to label training and testing sets. Unfortunately, inter-rater reliability between observers tends to vary from fair to moderate when dealing with naturalistic expressions. Nevertheless, the most common approach used is to label each expression with the most frequent label assigned by the observers to that expression. In this paper, we propose a general pattern recognition framework that takes into account the variability between observers for automatic affect recognition. This leads to what we term a multi-score learning problem in which a single expression is associated with multiple values representing the scores of each available emotion label. We also propose several performance measurements and pattern recognition methods for this framework, and report the experimental results obtained when testing and comparing these methods on two affective posture datasets.
Appears in Collections:Dept of Computer Science Research Papers

Files in This Item:
File Description SizeFormat 
Fulltext.pdf278.95 kBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.