We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...
Abstract. Recent studies on three-dimensional face recognition proposed to model facial expressions as isometries of the facial surface. Based on this model, expression-invariant s...
Alexander M. Bronstein, Michael M. Bronstein, Ron ...
An unsupervised nonparametric approach is proposed to automatically extract representative face samples (exemplars) from a video sequence or an image set for multipleshot face rec...
We present a Modular Bilinear Disciminant Analysis (MBDA) approach for face recognition. A set of classifiers are trained independently on specific face regions, and different c...
In this paper, we introduce the concept of SelfQuotient Image (SQI) for robust face recognition under varying lighting conditions. It is based on the Quotient Image method [4][5] ...