Publications Competitions Internships Teaching Review Activities Education Scholar Profile LinkedIn

Natalia Neverova

I am a research scientist at Facebook AI Research (FAIR) in Paris.

Before coming to FAIR, I worked on my PhD at INSA Lyon and University of Guelph under the guidance of Christian Wolf and Graham Taylor. I also spent several months as a visiting researcher at Google in Mountain View, USA.

Research interests: statistical machine learning and computer vision with emphasis on deep learning, action and gesture recognition, and motion analysis.

Publications

Mass Displacement Networks
Natalia Neverova, Iasonas Kokkinos
arXiv preprint, 2017
PDF Bibtex
Houdini: Fooling Deep Structured Prediction Models
Moustapha Cisse, Yossi Adi*, Natalia Neverova*, Joseph Kesnet
* denotes equal contribution
NIPS, 2017
PDF Bibtex
Predicting Deeper into the Future of Semantic Segmentation
Pauline Luc*, Natalia Neverova*, Camille Couprie, Jakob Verbeek, Yann LeCun
* denotes equal contribution
ICCV, 2017
PDF Bibtex
Multi-task, Multi-domain Learning: application to semantic segmentation and pose regression
Damien Fourure, Remi Emonet, Elisa Fromont, Damien Muselet, Natalia Neverova, Alain Trémeau, Christian Wolf
Neurocomputing, 2017
Modout: Learning Multi-modal Architectures by Stochastic Regularization
Fan Li, Natalia Neverova, Christian Wolf, Graham Taylor
FG, 2017
PDF Bibtex
Hand Pose Estimation through Semi-Supervised and Weakly-Supervised Learning
Natalia Neverova, Christian Wolf, Florian Nebout, Graham Taylor
Computer Vision and Image Understanding (CVIU), 2017
PDF Bibtex
Learning Human Identity from Motion Patterns
Natalia Neverova, Christian Wolf, Griffin Lacey, Lex Fridman, Deepak Chandra, Brandon Barbello, Graham Taylor
IEEE Access, 2016
PDF Bibtex
ModDrop: adaptive multi-modal gesture recognition
Natalia Neverova, Christian Wolf, Graham W. Taylor, Florian Nebout
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2015
PDF Bibtex
Gestural HRI in an ecological dynamic experiment: the GEE corpus based approach for the Emox robot
Leslie Guillaume, Veronique Auberge, Romain Magnani, Frederic Aman, Cecile Cottier, Yuko Sasa, Christian Wolf, Florian Nebout, Natalia Neverova, Nicolas Bonnefond, Amaury Negre, et al.
International Workshop on Advanced Robotics and its Social Impacts (ARSO), 2015
PDF Bibtex
Hand segmentation with structured convolutional learning
Natalia Neverova, Christian Wolf, Graham W. Taylor and Florian Nebout
ACCV, 2014
PDF Bibtex
Multi-scale deep learning for gesture detection and localization
Natalia Neverova, Christian Wolf, Graham W. Taylor and Florian Nebout
Workshop on Looking at People - ECCV, 2014 (oral)
PDF Bibtex
A multi-scale approach to gesture detection and recognition
Natalia Neverova, Christian Wolf, Giulio Paci, Giacomo Sommavilla, Graham W. Taylor and Florian Nebout
Workshop on Understanding Human Activities: Context and Interactions (HACI) - ICCV, 2013 (oral)
PDF Bibtex
2.5D Scene Reconstruction of Indoor Scenes from Single RGB-D Images
Natalia Neverova, Damien Muselet and Alain Tremeau
IAPR Computational Color Imaging Workshop (CCIW), 2013 (oral)
PDF Bibtex
Lighting Estimation in Indoor Environments from Low-Quality Images
Natalia Neverova, Damien Muselet and Alain Tremeau
Color and Photometry in Computer Vision Workshop - ECCV, 2012 (oral)
PDF Bibtex
Edge-based method for sharp region extraction from low depth of field images
Natalia Neverova and Hubert Konik
VCIP, 2012
PDF Bibtex
Deep Learning for Human Motion Analysis
PhD thesis, 2016
PDF Bibtex

Scientific competitions

ECCV Looking at People Challenge - track 3, Gesture Recognition
Team LIRIS: Natalia Neverova, Christian Wolf, Graham W. Taylor, Florian Nebout
First place (1/17)

CVPR OpenCV State of the Art Vision Challenge
Team LIRIS: Natalia Neverova, Christian Wolf, Graham W. Taylor, Florian Nebout
Winner (in a category "gesture recognition")

ICCV Multimodal Gesture Recognition Challenge
Team lrs: Natalia Neverova, Christian Wolf, Graham W. Taylor et al.
Ranked 6/23

Research and industrial internships

2015, Spring - Google, Mountain View, USA (visiting researcher)
Google ATAP, project Abacus

2014, Fall - University of Guelph, Canada (visiting researcher)
2011, Summer - University Jean Monnet, Saint-Etienne, France (intern)

Invited talks

"Deep Learning for Human Motion Analysis", GRETSI 2017, XXVI Colloque, invited talk
Juan-les-Pins, France, September 7th, 2017
"Deep Learning for Human Motion Analysis", LIRIS annual general assembly, invited talk
Lyon, France, July 3rd, 2017
"Introduction to deep learning", Soft-Shake 2015, invited talk
Geneva, Switzerland, October 23rd, 2015
"Introduction to deep learning", invited talk at the European Patent Office
The Hague, Netherlands, July 13th, 2015

In the press

Sneaky attacks trick AIs into seeing or hearing what’s not there, New Scientist, July 27th, 2017
Biometrics: Identification in Action, CNRS journal, April 5th, 2016
Google and University of Guelph team up to abolish Android smartphone passwords, CBC, March 29th, 2016

Review activities

ICCV, NIPS, IEEE TPAMI, CVIU, IEEE Transactions on Multimedia
IEEE Transactions on Cloud Computing, Pattern Recognition, Neurocomputing

Teaching

2014, Spring - Probability theory at CPE Lyon
2013, Fall - Linear algebra and numerical analysis at CPE Lyon
2012-2007 - Preparatory courses in mathematics at BMSTU

Education

Engineering degree (with honors)
Bauman Moscow State University
Optics and Electronics
2002-2008

Master of Science (with excellent distinction, first ranked)
University of Saint-Etienne, France and University of Gjovik, Norway
Color in Informatics and Media Technology (CIMET)
20010-2012

Scholarships and awards

2016 French award of Club EEA/GRETSI/GDR ISIS for the best thesis "Signal, Image et Vision"
Erusmus Mundus Scholarship, 2010-2012
Ph.D Fellowship "Investissements d'Avenir", 2012-2015
GdR ISIS mobility grant, 2014

Summer schools

Summer 2015 - Deep Learning Summer School - Montreal, Canada (awarded a scholarship)
Summer 2013 - IPAM Graduate Summer School: Computer Vision - Los Angeles, USA (awarded a scholarship)
Summer 2012 - International Computer Vision Summer School - Sicily, Italy
Summer 2012 - INRIA Visual Recognition and Machine Learning - Grenoble, France