no code implementations • 30 Jun 2023 • Hamza Bouzid, Lahoucine Ballihi
In this work, we show competitive recognition rate and high memory efficiency by building our auto-encoder based on spiral convolutions, which are light weight convolution directly applied to mesh data with fixed topologies, and by modeling temporal evolution using a attention, that can handle large sequences.
no code implementations • Intelligent Systems with Applications 2022 • Hamza Bouzid, Lahoucine Ballihi
Starting from a single neutral facial image and a label indicating the desired facial expression, we aim to synthesize a video of the given identity performing the specified facial expression.
no code implementations • 23 Jul 2019 • Naima Otberdout, Mohamed Daoudi, Anis Kacem, Lahoucine Ballihi, Stefano Berretti
In this work, we propose a novel approach for generating videos of the six basic facial expressions given a neutral face image.
no code implementations • 25 Oct 2018 • Naima Otberdout, Anis Kacem, Mohamed Daoudi, Lahoucine Ballihi, Stefano Berretti
In this paper, we propose a new approach for facial expression recognition using deep covariance descriptors.
no code implementations • 10 May 2018 • Naima Otberdout, Anis Kacem, Mohamed Daoudi, Lahoucine Ballihi, Stefano Berretti
In this paper, covariance matrices are exploited to encode the deep convolutional neural networks (DCNN) features for facial expression recognition.