Sotabase

Career

· Board Member, Calibrate Ventures2024–
· Founder, Stealth Startup2023–2025
· Technical Advisor to the CEO, Toyota Research Institute (TRI)2023–2025
· Adjunct Professor, Stanford University2021–
· Head of Machine Learning, Toyota Research Institute (TRI)2017–2023
· Research Scientist, Computer Vision, Xerox Research Center Europe2013–2016
· R&D Engineer in Computer Vision, LEAR team, Inria2008–
· Doctoral Researcher, ML for Computer Vision, Microsoft Research & Inria2008–2012
· PhD in Computer Science, Microsoft Research - Inria2008–2012
· PhD in Computer Science, Université Grenoble Alpes2008–2012
· Research intern, Inria Rocquencourt2007–2007
· MSc in Artificial Intelligence, Institut Polytechnique (INP)2007–2008
· Master of Science (M.Sc.), Université Joseph Fourier (Grenoble I)2007–2008
· Engineer's degree, Ecole Nationale Supérieure d'Informatique et de Mathématiques Appliquées de Grenoble / ENSIMAG2005–2008
· Engineer Diploma in Computer Science and Applied Mathematics, ENSIMAG2005–2008

Publications (180)

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Neural Information Processing Systems · 2019
1,924
cited
VirtualWorlds as Proxy for Multi-object Tracking Analysis
Computer Vision and Pattern Recognition · 2016
1,160
cited
3D Packing for Self-Supervised Monocular Depth Estimation
Computer Vision and Pattern Recognition · 2019
751
cited
Exploring the Limitations of Behavior Cloning for Autonomous Driving
IEEE International Conference on Computer Vision · 2019
627
cited
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
European Conference on Computer Vision · 2020
543
cited
Is Pseudo-Lidar needed for Monocular 3D Object detection?
IEEE International Conference on Computer Vision · 2021
386
cited
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss
Neural Information Processing Systems · 2021
374
cited
ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape
Computer Vision and Pattern Recognition · 2018
291
cited
Spatio-Temporal Graph for Video Captioning With Knowledge Distillation
Computer Vision and Pattern Recognition · 2020
264
cited
Semantically-Guided Representation Learning for Self-Supervised Monocular Depth
International Conference on Learning Representations · 2020
254
cited
Learning to Track with Object Permanence
IEEE International Conference on Computer Vision · 2021
237
cited
SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation
IEEE International Conference on Robotics and Automation · 2018
227
cited
Differentiable Rendering: A Survey
arXiv.org · 2020
203
cited
Revisiting the “Video” in Video-Language Understanding
Computer Vision and Pattern Recognition · 2022
202
cited
Temporal Localization of Actions with Actoms
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2013
189
cited
Self-supervised Learning is More Robust to Dataset Imbalance
International Conference on Learning Representations · 2021
186
cited
Actom sequence models for efficient action detection
Computer Vision and Pattern Recognition · 2011
181
cited
Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
IEEE Robotics and Automation Letters · 2020
181
cited
Procedural Generation of Videos to Train Deep Action Recognition Networks
Computer Vision and Pattern Recognition · 2016
150
cited
Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors
Computer Vision and Pattern Recognition · 2019
126
cited
Sotabase