Framework for Combination Aware AU Intensity Recognition

Isabel Gonzalez, Meshia Cédric Oveneke, Dongmei Jiang, Werner Verhelst, Hichem Sahli

Research output: Chapter in Book/Report/Conference proceedingConference paper

2 Citations (Scopus)

Abstract

We present a framework for combination aware AU
intensity recognition. It includes a feature extraction approach
that can handle small head movements which does not require
face alignment. A three layered structure is used for the AU
classification. The first layer is dedicated to independent AU
recognition, and the second layer incorporates AU combination
knowledge. At a third layer, AU dynamics are handled based on
variable duration semi-Markov model. The first two layers are
modeled using extreme learning machines (ELMs). ELMs have
equal performance to support vector machines but are computationally
more efficient, and can handle multi-class classification
directly. Moreover, they include feature selection via manifold
regularization. We show that the proposed layered classification
scheme can improve results by considering AU combinations as
well as intensity recognition.
Original languageEnglish
Title of host publicationIEEE 6th International Conference on Affective Computing and Intelligent Interaction (ACII2015)
Pages602
Number of pages608
Publication statusPublished - 2015
EventIEEE 6th International Conference on Affective Computing and Intelligent Interaction - China, Xi'an , China
Duration: 21 Sep 201524 Sep 2015

Conference

ConferenceIEEE 6th International Conference on Affective Computing and Intelligent Interaction
CountryChina
CityXi'an
Period21/09/1524/09/15

Keywords

  • FACS
  • ELM
  • AU combination aware hierarchical classification
  • VDHMM

Fingerprint

Dive into the research topics of 'Framework for Combination Aware AU Intensity Recognition'. Together they form a unique fingerprint.

Cite this