I am an associate professor (maître de conférence) at Telecom Paris, France, where I lead the multimedia research team. My research interests cover machine learning for computer vision problems (eg. adaptation of visual foundation models, continual learning) and deep models for image and video generation. I published papers in the most prestigious computer vision conferences (CVPR, ICCV, ECCV, NeurIPS) and top journals (T-PAMI).

Until October 2019, I was a post-doctoral fellow at the University of Trento in the Multimedia and Human Understanding Group, led by Prof. Nicu Sebe and Prof. Elisa Ricci. I worked towards my Ph.D. in mathematics and computer science in the Perception Team at Inria under the supervision of Dr. Radu Horaud, and obtained it from Université Grenoble Alpes (France) in 2018.

Last news

  • 2 papers accepted at ECCV 2024  with oral presentations on Continual learning with weight averaging and Privacy-Preserving ReId.
  • 1 paper accepted at CVPR 2024 on Collaborating Foundation models for Domain Generalized Semantic Segmentation
  • 2 papers accepted at WACV 2024 on efficient VIT adaptation and the adaptation of Re-ID models with privacy-preserving constraints
  • 2 Papers accepted at ICCV 2023 on Zero-shot semantic image synthesis and domain adaptation with vision-language models
  • 1 Paper accepted at CVPR 2023 on Few-shot semantic image synthesis + 2 workshop papers
  • A postdoc  position is opened in my group to work on deep learning, computer vision, generative models, or video processing. If you are interested , please contact me.
  • 2 papers accepted to ECCV 2022 about image generation (+ one workshop).
  • 1 paper accepted to CVPR 2022 about image generation (+ one at the continual learning workshop ).
  • An associate/assistant professor (maitre de conférence) position is opened in my group to work on deep learning, computer vision or video processing.
  • A postdoc position is open in my group. Contact me if you are interested in working on domain adaptation, online learning, and continual learning. More details here.  
  • 2 papers accepted to ICCV 2021 about Novel Class discovery (Oral) and video generation
  • 1 paper accepted to CVPR 2021 (Oral) on Playable video Generation
  • 1 paper accepted to ICASSP 2021 on Deep learning-based video compression
  • My project Odace has been awarded by ANR (young researcher grant from the French agency for research).

Team

  • Yasser Benigmim, PhD student co-advised with S. Essid and V. Kalogeiton
  • Hamza Rami,  PhD student at Atos co-advised with M.Ospici 
  • Marlène Careil, PhD student at Facebook AI Research co-advised with J. Verbeek and C. Couprie
  • Marcelin Tworski, PhD student at DxOMark, co-advised with M. Cagnazzo
  • Goluck Konuko, PhD student co-advised with G. Valenzise
  • Willi Menapace, PhD student at University of Trento, co-advised with E. Ricci

Contact 

19 place Marguerite Perey, 91120 Palaiseau, France
Office 5D28

Selected Publications

Full and updated list available on Google Scholar.

Click to Move: Controlling Video Generation with Sparse Motion
Pierfrancesco Ardino, Marco De Nadai, Bruno Lepri, Elisa Ricci, Stéphane Lathuilière
ICCV 2021 [paper]

A Unified Objective for Novel Class Discovery
Enrico Fini, Enver Sangineto, Stéphane Lathuilière, Zhun Zhong, Moin Nabi, Elisa Ricci
ICCV 2021 (Oral) [paper]

Playable Video Generation
Willi Menapace, Stéphane Lathuilière, Sergey Tulyakov, Aliaksandr Siarohin, Elisa Ricci
CVPR 2021 (Oral) [paper]

Online Continual Learning under Extreme Memory Constraints
Enrico Fini, Stéphane Lathuilière, Enver Sangineto, Moin Nabi, Elisa Ricci
ECCV 2020 [paper]

Learning to Cluster under Domain Shift
Willi Menapace, Stéphane Lathuilière, Elisa Ricci ECCV 2020 [paper]

First Order Motion Model for Image Animation
Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
Neurips 2019 [paper]

Budget-Aware Adapters for Multi-Domain Learning
Rodrigo Berriel, Stéphane Lathuilière, Moin Nabi, Tassilo Klein, Thiago Oliveira-Santos, Nicu Sebe, Elisa Ricci
ICCV 2019 [paper]

Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation
Andrea Pilzer, Stéphane Lathuilière, Nicu Sebe, Elisa Ricci
CVPR 2019 [paper]

Animating Arbitrary Objects via Deep Motion Transfer
Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
CVPR 2019 (Oral) [paper]

DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model
Stéphane Lathuilière, Pablo Mesejo, Xavier Alameda-Pineda, Radu Horaud
ECCV 2018 [paper]

A Comprehensive Analysis of Deep Regression
Stéphane Lathuilière, Pablo Mesejo, Xavier Alameda-Pineda, Radu Horaud
T-PAMI 2019 [paper]

Deformable GANs for Pose-based Human Image Generation
Aliaksandr Siarohin, Enver Sangineto, Stephane Lathuiliere, Nicu Sebe
CVPR 2018 [paper]

Deep mixture of linear inverse regressions applied to head-pose estimation
Stéphane Lathuilière, Rémi Juge, Pablo Mesejo, Rafael Munoz-Salinas, Radu Horaud
CVPR 2017 [paper]

 
 

where I lead the multimedia research team.