Exploiting privileged information for facial expression recognition

Michalis Vrigkas, Christophoros Nikou, Ioannis A. Kakadiaris

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

5 Scopus citations


Most of the facial expression recognition methods consider that both training and testing data are equally distributed. As facial image sequences may contain information for heterogeneous sources, facial data may be asymmetrically distributed between training and testing, as it may be difficult to maintain the same quality and quantity of information. In this work, we present a novel classification method based on the learning using privileged information (LUPI) paradigm to address the problem of facial expression recognition. We introduce a probabilistic classification approach based on conditional random fields (CRFs) to indirectly propagate knowledge from privileged to regular feature space. Each feature space owns specific parameter settings, which are combined together through a Gaussian prior, to train the proposed t-CRF+ model and allow the different tasks to share parameters and improve classification performance. The proposed method is validated on two challenging and publicly available benchmarks on facial expression recognition and improved the state-of-the-art methods in the LUPI framework.

Original languageEnglish (US)
Title of host publication2016 International Conference on Biometrics, ICB 2016
EditorsFernando Alonso-Fernandez, Arun Ross, Raymond Veldhuis, Julian Fierrez, Stan Z. Li, Josef Bigun
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509018697
StatePublished - Aug 23 2016
Event9th IAPR International Conference on Biometrics, ICB 2016 - Halmstad, Sweden
Duration: Jun 13 2016Jun 16 2016

Publication series

Name2016 International Conference on Biometrics, ICB 2016


Conference9th IAPR International Conference on Biometrics, ICB 2016

ASJC Scopus subject areas

  • Instrumentation
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering


Dive into the research topics of 'Exploiting privileged information for facial expression recognition'. Together they form a unique fingerprint.

Cite this