I worked a lot on automatic facial affect estimation, a field which bridges the gap between Computer Vision and Machine Learning. After contributing to facial landmark detection using Active Appearance Models and to emotion detection from faces, I currently focus on Machine Learning using tensor methods.

I created TensorLy, a high-level API for tensor methods and deep tensorized neural networks in Python, designed to make tensor learning simple and accessible. TensorLy allows to easily perform tensor decomposition, tensor learning and tensor algebra. Its backend system allows to seamlessly perform computation with NumPy, MXNet, PyTorch, TensorFlow, CuPy or JAX, and run methods at scale on CPU or GPU. It is open-source under BSD licensed, making it suitable for both academic and industrial applications.