One of the main challenges in feature learning using Deep Convolutional Neural Networks
(DCNNs) for large-scale face recognition is the design of appropriate loss functions that can …

We study the problem of transferring a sample in one domain to an analog sample in
another domain. Given two related domains, S and T, we would like to learn a generative …

In this work we propose a novel model-based deep convolutional autoencoder that
addresses the highly challenging problem of reconstructing a 3D human face from a single …

State-of-the-art face recognition systems are based on deep (convolutional) neural
networks. Therefore, it is imperative to determine to what extent face templates derived from …

We present a method for synthesizing a frontal, neutral-expression image of a person's face,
given an input face photograph. This is achieved by learning to generate facial landmarks …

Face recognition systems are increasingly being used in different applications. In such
systems, some features (also known as embeddings or templates) are extracted from each …

With the widespread use of biometric recognition, several issues related to the privacy and
security provided by this technology have been recently raised and analysed. As a result …

Face synthesis has been a fascinating yet challenging problem in computer vision and
machine learning. Its main research effort is to design algorithms to generate photo-realistic …

Face recognition based on deep convolutional neural networks (CNN) shows superior
accuracy performance attributed to the high discriminative features extracted. Yet, the …

In this article, we comprehensively evaluate the vulnerability of state-of-the-art face
recognition systems to template inversion attacks using 3D face reconstruction. We propose …