A survey on modelling of facial affect using Gaussian process domain expert

  Jamsheela M K

Automated analysis of facial expressions has been gaining significant attention over the past years. Most of existing models for facial behavior analysis rely on generic classifiers, which fail to generalize well to previously unseen data. This is because of inherent differences in source (training) and target (test) data, mainly caused by variation in subjects’ facial morphology, camera views, etc. Driven by the necessity for efficient and accurate inference mechanisms explore probabilistic framework of Gaussian processes (GPs). The main goal in our approach to automated analysis of facial expressions is to learn high dimensional mappings between the corresponding facial features and the associated output labels. The model adaptation is facilitated in a probabilistic fashion, by conditioning the target expert on the predictions from multiple source experts. Further exploit the predictive variance of each expert to define an optimal weighting during inference.

Keywords- Gaussian processes, multi-view facial expression recognition, domain adaptation, GP adaptation.

Unique Identification Number - IJEDR1801036
Page Number(s) - 215-217
Pubished in - Volume 6 | Issue 1 | January 2018
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Jamsheela M K,   "A survey on modelling of facial affect using Gaussian process domain expert", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.6, Issue 1, pp.215-217, January 2018, Available at :http://www.ijedr.org/papers/IJEDR1801036.pdf