J
Jean Kossaifi
Researcher at Nvidia
Publications - 66
Citations - 3986
Jean Kossaifi is an academic researcher from Nvidia. The author has contributed to research in topics: Tensor & Computer science. The author has an hindex of 19, co-authored 62 publications receiving 2670 citations. Previous affiliations of Jean Kossaifi include Samsung & Imperial College London.
Papers
More filters
Journal ArticleDOI
Machine learning for neuroimaging with scikit-learn.
Alexandre Abraham,Alexandre Abraham,Fabian Pedregosa,Fabian Pedregosa,Michael Eickenberg,Michael Eickenberg,Philippe Gervais,Philippe Gervais,Andreas Mueller,Jean Kossaifi,Alexandre Gramfort,Alexandre Gramfort,Alexandre Gramfort,Bertrand Thirion,Bertrand Thirion,Gaël Varoquaux,Gaël Varoquaux +16 more
TL;DR: It is illustrated how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps and its application to neuroimaging data provides a versatile tool to study the brain.
Proceedings ArticleDOI
The First Facial Landmark Tracking in-the-Wild Challenge: Benchmark and Results
Jie Shen,Stefanos Zafeiriou,Grigoris G. Chrysos,Jean Kossaifi,Georgios Tzimiropoulos,Maja Pantic +5 more
TL;DR: The first benchmark for long-term facial landmark tracking, containing currently over 110 annotated videos, is presented, and the results of the competition on facial landmark localisation in static imagery are summarized.
Posted Content
Stochastic Activation Pruning for Robust Adversarial Defense
Guneet S. Dhillon,Kamyar Azizzadenesheli,Zachary C. Lipton,Jeremy Bernstein,Jean Kossaifi,Aran Khanna,Animashree Anandkumar +6 more
TL;DR: In this paper, a stochastic activation pruning (SAP) strategy is proposed for adversarial defense against adversarial examples in deep learning networks, where a random subset of activations are pruned and the survivors are scaled up to compensate.
Posted Content
TensorLy: Tensor Learning in Python
TL;DR: TensorLy is a Python library that provides a high-level API for tensor methods and deep tensorized neural networks and aims to follow the same standards adopted by the main projects of the Python scientific community, and to seamlessly integrate with them.
Posted Content
Machine Learning for Neuroimaging with Scikit-Learn
Alexandre Abraham,Fabian Pedregosa,Michael Eickenberg,Philippe Gervais,Andreas Müller,Jean Kossaifi,Alexandre Gramfort,Bertrand Thirion,Gaël Varoquaux +8 more
TL;DR: Scikit-learn as mentioned in this paper contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain.