About

Biography


I am currently a Research Scientist at the Samsung AI Center in Cambridge and a Research Assistant / PhD student in the Department of Computing at Imperial College London, within the iBug group. I work 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 I have shifted my focus to Machine Learning using tensors.

I created TensorLy, a high-level API for tensor methods and deep tensorized neural networks in Python that aims at making tensor learning simple and accessible.It allows to easily perform tensor decomposition, tensor learning and tensor algebra. Its backend system allows to seamlessly perform computation with NumPy, MXNet, PyTorch, TensorFlow or CuPy, 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.

Prior to my current position, I obtained a Masters in Advanced Computing from Imperial College London. I also hold a French Engineering diploma / MSc in Applied Mathematics, Computing and Finance and obtained a BSc in advanced mathematics in parallel.

You can find me on:


News

Projects

Publications

J. Kossaifi, Bulat, Adrian, Panagakis, Yannis and Pantic, Maja, Efficient N-Dimensional Convolutions via Higher-Order Factorization, in arXiv preprint arXiv:1906.06196, 2019
Mitenkova, Anna, J. Kossaifi, Panagakis, Yannis and Pantic, Maja, Valence and Arousal Estimation In-The-Wild with Tensor Methods, in 2019 14th IEEE International Conference on Automatic Face \& Gesture Recognition (FG 2019), 2019
Bulat, Adrian, J. Kossaifi, Tzimiropoulos, Georgios and Pantic, Maja, Matrix and tensor decompositions for training binary neural networks, in arXiv preprint arXiv:1904.07852, 2019
Bulat, Adrian, Tzimiropoulos, Georgios, J. Kossaifi and Pantic, Maja, Improved training of binary networks for human pose estimation and image recognition, in arXiv preprint arXiv:1904.05868, 2019
Kolbeinsson, Arinbjorn, J. Kossaifi, Panagakis, Yannis, Bulat, Adrian, Anandkumar, Anima, Tzoulaki, Ioanna, Matthews, Paul, Robust Deep Networks with Randomized Tensor Regression Layers, in arXiv, 2019
J. Kossaifi, Walecki, Robert, Panagakis, Yannis, Shen, Jie, Schmitt, Maximilian, Ringeval, Fabien, Han, Jing, Pandit, Vedhas, Schuller, Bjorn, Star, Kam, others, SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild, in TPAMI, 2019
J. Kossaifi, Bulat, Adrian, Tzimiropoulos, Georgios and Pantic, Maja, T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor, in CVPR, 2019
Tran, Linh, J. Kossaifi, Panagakis, Yannis and Pantic, Maja, Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks, in International Journal of Computer Vision (IJCV), 2019
G. G. Chrysos, J. Kossaifi and S. Zafeiriou, Robust Conditional Generative Adversarial Networks, in ICLR, 2019
J. Kossaifi, Y. Panagakis, A. Anandkumar, M. Pantic, TensorLy: Tensor Learning in Python, in JMLR, 2019
J. Kossaifi, L, Tran, Y. Panagakis and M. Pantic, GAGAN: Geometry-Aware Generative Adverserial Networks, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
G. Dhillon, K. Azizzadenesheli, Z.C.Lipton, J. Bernstein, J. Kossaifi, A.Khanna, A.Anandkumar, Stochastic activation pruning for robust adversarial defense, in ICLR, 2018
J. Kossaifi, G. Tzimiropoulos, S. Todorovic and M. Pantic, AFEW-VA database for valence and arousal estimation in-the-wild, in Image and Vision Computing, 2017
J. Kossaifi, Z. Lipton, A. Khanna, T. Furlanello, A. Anandkumar, Tensor Regression Networks, in CoRR, 2017
J. Kossaifi, A. Khanna, Z. Lipton, T. Furlanello, A. Anandkumar, Tensor Contraction Layers for Parsimonious Deep Nets, in 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), July 2017
J. Kossaifi, G. Tzimiropoulos and M. Pantic, Fast and exact Newton and Bidirectional fitting of Active Appearance Models, in IEEE Transactions on Image Processing (TIP), accepted for publication, 2016
J. Shen, S. Zafeiriou, G. Chrysos, J. Kossaifi, G. Tzimiropoulos and M. Pantic, The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results, in Proceedings of IEEE International Conference on Computer Vision, 300 Videos in the Wild (300-VW): Facial Landmark Tracking in-the-Wild Challenge and Workshop (ICCVW'15), December 2015
J. Kossaifi, G. Tzimiropoulos and M. Pantic, Fast and exact Bi-directional Fitting of Active Appearance Models, in ICIP, September 2015
A. Abraham, F. Pedregosa, M. Eickenberg, P. Gervais, A. Mueller, J. Kossaifi, A. Gramfort, B. Thirion and G. Varoquaux, Machine Learning for Neuroimaging with Scikit-Learn, in Frontiers in Neuroinformatics, 2014
J. Kossaifi, G. Tzimiropoulos and M. Pantic, Fast Newton Active Appearance Models, in ICIP, October 2014