The face-space duality hypothesis: a computational model

Author(s)
Vitale, Jonathan
Williams, Mary-Anne
Johnston, Benjamin
Publication Date
2016
Abstract
<p>Valentine's face-space suggests that faces are represented in a psychological multidimensional space according to their perceived properties. However, the proposed framework was initially designed as an account of invariant facial features only, and explanations for dynamic features representation were neglected. In this paper we propose, develop and evaluate a computational model for a twofold structure of the face-space, able to unify both identity and expression representations in a single implemented model. To capture both invariant and dynamic facial features we introduce the <i>face-space duality hypothesis</i> and subsequently validate it through a mathematical presentation using a general approach to dimensionality reduction. Two experiments with real facial images show that the proposed face-space: (1) supports both identity and expression recognition, and (2) has a twofold structure anticipated by our formal argument.</p>
Citation
Proceedings of the 38th Annual Conference of the Cognitive Science Society, 38(0), p. 514-519
Link
Publisher
Cognitive Science Society
Title
The face-space duality hypothesis: a computational model
Type of document
Conference Publication
Entity Type
Publication

Files:

NameSizeformatDescriptionLink
closedpublished/ThefaceVitale2016ConferencePublication.pdf 371.05 KB application/pdf Conference publication View document