Gaussian process domain experts for modeling of facial affect

File Description SizeFormat 
gpde-2017.pdfAccepted version8.73 MBAdobe PDFView/Open
Title: Gaussian process domain experts for modeling of facial affect
Authors: Eleftheriadis, S
Rudovic, O
Deisenroth, MP
Pantic, M
Item Type: Journal Article
Abstract: 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, and so on. All of these account for different contexts in which target and source data are recorded, and thus, may adversely affect the performance of the models learned solely from source data. In this paper, we exploit the notion of domain adaptation and propose a data efficient approach to adapt already learned classifiers to new unseen contexts. Specifically, we build upon the probabilistic framework of Gaussian processes (GPs), and introduce domain-specific GP experts (e.g., for each subject). The model adaptation is facilitated in a probabilistic fashion, by conditioning the target expert on the predictions from multiple source experts. We further exploit the predictive variance of each expert to define an optimal weighting during inference. We evaluate the proposed model on three publicly available data sets for multi-class (MultiPIE) and multi-label (DISFA, FERA2015) facial expression analysis by performing adaptation of two contextual factors: “where” (view) and “who” (subject). In our experiments, the proposed approach consistently outperforms: 1) both source and target classifiers, while using a small number of target examples during the adaptation and 2) related state-of-the-art approaches for supervised domain adaptation.
Issue Date: 28-Jun-2017
Date of Acceptance: 12-Jun-2017
URI: http://hdl.handle.net/10044/1/49121
DOI: https://dx.doi.org/10.1109/TIP.2017.2721114
ISSN: 1941-0042
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Start Page: 4697
End Page: 4711
Journal / Book Title: IEEE Transactions on Image Processing
Volume: 26
Issue: 10
Copyright Statement: © 2017 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
Keywords: Artificial Intelligence & Image Processing
0801 Artificial Intelligence And Image Processing
0906 Electrical And Electronic Engineering
1702 Cognitive Science
Publication Status: Published
Appears in Collections:Faculty of Engineering
Computing



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

Creative Commons