We present a framework for combination aware AUintensity recognition. It includes a feature extraction approachthat can handle small head movements which does not requireface alignment. A three layered structure is used for the AUclassification. The first layer is dedicated to independent AU recognition, and the second layer incorporates AU combinationknowledge. At a third layer, AU dynamics are handled based onvariable duration semi-Markov model. The first two layers aremodeled using extreme learning machines (ELMs). ELMs haveequal performance to support vector machines but are computationallymore efficient, and can handle multi-class classificationdirectly. Moreover, they include feature selection via manifoldregularization. We show that the proposed layered classificationscheme can improve results by considering AU combinations aswell as intensity recognition.
Gonzalez, I, Oveneke, MC, Jiang, D, Verhelst, W & Sahli, H 2015, Framework for Combination Aware AU Intensity Recognition. in IEEE 6th International Conference on Affective Computing and Intelligent Interaction (ACII2015)., 10.1109/ACII.2015.7344631, pp. 602, IEEE 6th International Conference on Affective Computing and Intelligent Interaction, Xi'an , China, 21/09/15.
Gonzalez, I., Oveneke, M. C., Jiang, D., Verhelst, W., & Sahli, H. (2015). Framework for Combination Aware AU Intensity Recognition. In IEEE 6th International Conference on Affective Computing and Intelligent Interaction (ACII2015) (pp. 602). Article 10.1109/ACII.2015.7344631
@inproceedings{680918d6c6804f26a2bd9d04894f1dc3,
title = "Framework for Combination Aware AU Intensity Recognition",
abstract = "We present a framework for combination aware AUintensity recognition. It includes a feature extraction approachthat can handle small head movements which does not requireface alignment. A three layered structure is used for the AUclassification. The first layer is dedicated to independent AU recognition, and the second layer incorporates AU combinationknowledge. At a third layer, AU dynamics are handled based onvariable duration semi-Markov model. The first two layers aremodeled using extreme learning machines (ELMs). ELMs haveequal performance to support vector machines but are computationallymore efficient, and can handle multi-class classificationdirectly. Moreover, they include feature selection via manifoldregularization. We show that the proposed layered classificationscheme can improve results by considering AU combinations aswell as intensity recognition.",
keywords = "FACS, ELM, AU combination aware hierarchical classification, VDHMM",
author = "Isabel Gonzalez and Oveneke, {Meshia C{\'e}dric} and Dongmei Jiang and Werner Verhelst and Hichem Sahli",
year = "2015",
language = "English",
pages = "602",
booktitle = "IEEE 6th International Conference on Affective Computing and Intelligent Interaction (ACII2015)",
note = "IEEE 6th International Conference on Affective Computing and Intelligent Interaction ; Conference date: 21-09-2015 Through 24-09-2015",
}