Learning Facial Motion Representation with a Lightweight Encoder for Identity Verification

Categorizing identity from facial motion.

Advances in marker-less motion capture technology now allow the accurate replication of facial motion and deformation in computer-generated imagery (CGI). A forced-choice discrimination paradigm using such CGI facial animations showed that human observers can categorize identity solely from facial motion cues. Animations were generated from motion captures acquired during natural speech, thus e...

Psychophysical evidence for a non-linear representation of facial identity

It has been proposed that faces are represented in the visual brain as points within a multi-dimensional "face space", with the average at its origin. We adapted a psychophysical procedure that measures non-linearities in contrast transduction (by measuring discrimination around different reference/pedestal levels of contrast) to examine the encoding of facial-identity within such a notional sp...

Running head : Identity from Facial Motion 1 Categorising Identity from Facial Motion

Linear Disentangled Representation Learning for Facial Actions

Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features. However, a linear model with just several parameters normally is not demanding in terms of training data. In this paper, we propose an elegant linear model to untangle confounding factors in challenging realistic m...

Lightweight Verification with Dependent Types

Dependent types, studied for many years in Logic, have recently been gaining attention in Functional Programming Languages for expressing rich properties as types. A simple example is a type 〈list A n〉, for lists of length n holding objects of type A. A more complex example is 〈trm G T 〉, for terms in some object language which have object-language type T in context G. Dependently typed program...