- home
- » people
- » Jean Kossaifi
Dr. Jean Kossaifi
Biography
Jean Kossaifi is a Senior Research Scientist at NVIDIA and a Research Associate in the Department of Computing, Imperial College London. Prior to this, he was a Research Scientist at the Samsung AI Center in Cambridge. He has worked extensively on face analysis and facial affect estimation in naturalistic conditions, a field which bridges the gap between computer vision and machine learning. His current focus is tensor methods for machine learning and efficient combination of these methods with deep learning to develop better models that are memory and computation efficient, while being more robust to noise, random or adversarial, as well as domain shift. He is the creator of TensorLy, a high-level API for tensor methods and deep tensorized neural networks in Python, designed to make tensor learning simple and accessible.
Publications
Journal articles
Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks
L. Tran, J. Kossaifi, Y. Panagakis, M. Pantic. International Journal of Computer Vision (IJCV). 2019.
author = {L. Tran and J. Kossaifi and Y. Panagakis and M. Pantic},
journal = {International Journal of Computer Vision (IJCV)},
title = {Disentangling Geometry and Appearance with Regularised Geometry-Aware Generative Adversarial Networks},
year = {2019},
}
TensorLy: Tensor Learning in Python
J. Kossaifi, Y. Panagakis, A. Anandkumar, M. Pantic. Journal of Machine Learning Research (JMLR). 20(26): pp. 1 - 6, 2019.
author = {J. Kossaifi and Y. Panagakis and A. Anandkumar and M. Pantic},
pages = {1--6},
journal = {Journal of Machine Learning Research (JMLR)},
number = {26},
title = {TensorLy: Tensor Learning in Python},
url = {http://jmlr.org/papers/v20/18-277.html},
volume = {20},
year = {2019},
}
AFEW-VA database for valence and arousal estimation in-the-wild
J. Kossaifi, G. Tzimiropoulos, S. Todorovic, M. Pantic. Image and Vision Computing. 65: pp. 23 - 36, Multimodal Sentiment Analysis and Mining in the Wild Image and Vision Computing. 2017.
author = {J. Kossaifi and G. Tzimiropoulos and S. Todorovic and M. Pantic},
pages = {23--36},
journal = {Image and Vision Computing},
note = {Multimodal Sentiment Analysis and Mining in the Wild Image and Vision Computing},
title = {AFEW-VA database for valence and arousal estimation in-the-wild},
volume = {65},
year = {2017},
}
Fast and exact Newton and Bidirectional fitting of Active Appearance Models
J. Kossaifi, G. Tzimiropoulos, M. Pantic. IEEE Transactions on Image Processing (TIP). 26: pp. 1040 - 1053, 2016.
author = {J. Kossaifi and G. Tzimiropoulos and M. Pantic},
pages = {1040--1053},
journal = {IEEE Transactions on Image Processing (TIP)},
publisher = {IEEE},
title = {Fast and exact Newton and Bidirectional fitting of Active Appearance Models},
volume = {26},
year = {2016},
}
Machine Learning for Neuroimaging with Scikit-Learn
A. Abraham, F. Pedregosa, M. Eickenberg, P. Gervais, A. Mueller, J. Kossaifi, A. Gramfort, B. Thirion, G. Varoquaux. Frontiers in Neuroinformatics. 8(14): 2014.
author = {A. Abraham and F. Pedregosa and M. Eickenberg and P. Gervais and A. Mueller and J. Kossaifi and A. Gramfort and B. Thirion and G. Varoquaux},
journal = {Frontiers in Neuroinformatics},
number = {14},
title = {Machine Learning for Neuroimaging with Scikit-Learn},
url = {http://www.frontiersin.org/neuroinformatics/10.3389/fninf.2014.00014/abstract},
volume = {8},
year = {2014},
}
Conference articles
Augmenting Deep Classifiers with Polynomial Neural Networks
G. Chrysos, M. Georgopoulos, J. Deng, J. Kossaifi, Y. Panagakis, A. Anandkumar. ECCV. 2022.
booktitle = {ECCV},
title = {Augmenting Deep Classifiers with Polynomial Neural Networks},
year = {2022},
}
T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor
J. Kossaifi, A. Bulat, G. Tzimiropoulos, M. Pantic. IEEE CVPR. 2019.
author = {J. Kossaifi and A. Bulat and G. Tzimiropoulos and M. Pantic},
booktitle = {IEEE CVPR},
title = {T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensor},
year = {2019},
}
Robust Conditional Generative Adversarial Networks
G. Chrysos, J. Kossaifi, S. Zafeiriou. ICLR. May 2019.
booktitle = {ICLR},
month = {May},
title = {Robust Conditional Generative Adversarial Networks},
year = {2019},
}
GAGAN: Geometry-Aware Generative Adversarial Networks
J. Kossaifi, L. Tran, Y. Panagakis, M. Pantic. IEEE CVPR. pp. 878 - 887, June 2018.
author = {J. Kossaifi and L. Tran and Y. Panagakis and M. Pantic},
pages = {878--887},
booktitle = {IEEE CVPR},
month = {June},
title = {GAGAN: Geometry-Aware Generative Adversarial Networks},
year = {2018},
}
Stochastic activation pruning for robust adversarial defense
G. S. Dhillon, K. Azizzadenesheli, Z. Lipton, J. Bernstein, J. Kossaifi, A. Khanna, A. Anandkumar. International Conference on Learning Representations (ICLR). 2018.
author = {G. S. Dhillon and K. Azizzadenesheli and Z. Lipton and J. Bernstein and J. Kossaifi and A. Khanna and A. Anandkumar},
booktitle = {International Conference on Learning Representations (ICLR)},
title = {Stochastic activation pruning for robust adversarial defense},
year = {2018},
}
Tensor Regression Networks
J. Kossaifi, Z. Lipton, A. Khanna, T. Furlanello, A. Anandkumar. 2017.
author = {J. Kossaifi and Z. Lipton and A. Khanna and T. Furlanello and A. Anandkumar},
journal = {CoRR},
title = {Tensor Regression Networks},
url = {http://arxiv.org/abs/1707.08308},
year = {2017},
}
Tensor Contraction Layers for Parsimonious Deep Nets
J. Kossaifi, A. Khanna, Z. Lipton, T. Furlanello, A. Anandkumar. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). pp. 1940 - 1946, July 2017.
author = {J. Kossaifi and A. Khanna and Z. Lipton and T. Furlanello and A. Anandkumar},
pages = {1940--1946},
booktitle = {2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
month = {July},
title = {Tensor Contraction Layers for Parsimonious Deep Nets},
year = {2017},
}
The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results
J. Shen, S. Zafeiriou, G. Chrysos, J. Kossaifi, G. Tzimiropoulos, M. Pantic. Proceedings of IEEE International Conference on Computer Vision, 300 Videos in the Wild (300-VW): Facial Landmark Tracking in-the-Wild Challenge & Workshop (ICCVW'15). December 2015.
author = {J. Shen and S. Zafeiriou and G. Chrysos and J. Kossaifi and G. Tzimiropoulos and M. Pantic},
booktitle = {Proceedings of IEEE International Conference on Computer Vision, 300 Videos in the Wild (300-VW): Facial Landmark Tracking in-the-Wild Challenge & Workshop (ICCVW'15)},
month = {December},
title = {The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results},
year = {2015},
}
Fast and exact Bi-directional Fitting of Active Appearance Models
J. Kossaifi, G. Tzimiropoulos, M. Pantic. Proceedings of the IEEE Int’l Conf. on Image Processing (ICIP’15). Quebec City, QC, Canada, pp. 1135 - 1139, September 2015.
author = {J. Kossaifi and G. Tzimiropoulos and M. Pantic},
pages = {1135--1139},
address = {Quebec City, QC, Canada},
booktitle = {Proceedings of the IEEE Int’l Conf. on Image Processing (ICIP’15)},
month = {September},
title = {Fast and exact Bi-directional Fitting of Active Appearance Models},
year = {2015},
}
Fast Newton Active Appearance Models
J. Kossaifi, G. Tzimiropoulos, M. Pantic. Proceedings of the IEEE Int’l Conf. on Image Processing (ICIP’14). Paris, France, pp. 1420 - 1424, October 2014.
author = {J. Kossaifi and G. Tzimiropoulos and M. Pantic},
pages = {1420--1424},
address = {Paris, France},
booktitle = {Proceedings of the IEEE Int’l Conf. on Image Processing (ICIP’14)},
month = {October},
title = {Fast Newton Active Appearance Models},
year = {2014},
}