Our seminars/reading groups usually take place Wednesdays at 11am.
For this year (2025) they are organized by Raphael Baena.
If you are interested in presenting your work, please contact us [1].
2025
January 15th | Theo Moutakanni (FAIR and MICS CentraleSupelec) : You Don’t Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning, DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
January 22th | Justin Carpentier (INRIA) : Towards Fully Differentiable Control Architecture for Robotics: Simpler, Nimbler, Faster, Stronger
January 29th | Clémentin Boittiaux (IMAGINE)
February 2nd | Eric Brachman (Niantic) : Pushing the boundaries of structure-from-motion with machine learning
February 12th | Guillaume Astruc,(IMAGINE) Arijit Ghosh (IMAGINE) and Lucas Degeorge (IMAGINE & VISTA LIX) : Doctoral research presentation
February 19th | Abhishek Kuriya, Hyolim Kang
Feburay 26th | ICCV Poster Session
Mars 12th | Nicolas Audebert (IGN): A tour of generative models and synthetic data for photogrammetry and
remote sensing
Mars 19th | Juliette Marrie (INRIA) : LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes
Mars 26th | Timothée Darcet (FAIR & INRIA) : Cluster and Predict Latents Patches for Improved Masked Image Modeling
April 2th | Presentation from PhD Students: Srikar Yellapragada, Varun Belagali and Minh-Quan Le
April 9th | Jianbo Shi (Univeristy of Pensylvania): Brain Decodes Deep Nets
2024
September 18th | Marta López, Arijit Ghosh, Abhishek Kuriyal (IMAGINE) and Lucas Degeorge (IMAGINE & VISTA) : Intern Project
September 11th | Armand Lacombe (Direction Générale des Entreprises) : AI act
Octobre 16th | Dimitris Samaras ( Stony Brook University) : Generative modeling in Stony Brook: From Very Large Images to Dynamic Faces
Octobre 30th | Giles Puy (Valeo.ai): Leveraging image foundation models to pretrain lidar networks
Novembre 27th | Morris Alper: Kiki or Bouba? Sound Symbolism in Vision-and-Language Models
December 19th | Taras Kucherenko
2023
September 28th | Zorah Lähner (University of Siegen) : Permutations in Neural Networks and Quantum Annealing
September 20th | Intern projects: Hongyu Zhou, Constantin Aronssohn, and Shiyao Li
September 13th | Juliette Bertrand (Recent collaboration with CTU Prague and NaverLabs Europe) : Limited Data Challenges in Video Understanding
September 6th | Nicolas Dufour, Lucas Ventura, Georgy Ponimatkin and Mathis Petrovich (Imagine) : Tutorial session on Language Models
May 30th | Maxime Oquab (MetaAI) : DINOv2 – Learning Robust Visual Features without Supervision
May 24th | Thomas Capelle (W&B) : Using video demonstrations as guidance for robot learning | Hands-On
May 24th | Kateryna Zorina (CTU) : Using video demonstrations as guidance for robot learning
May 17th | Alaaeldin El-Nouby (MetaAI) : Bringing the power of Transformers to Computer Vision
April 26th | Antoine Guédon (Imagine) : Automated 3D reconstruction of large structures with scalable deep learning strategies
April 26th | Roberto Dessì (UPF, MetaAI) : Cross-Domain Image Captioning with Discriminative Finetuning
April 19th | Frédéric Jurie (ENSICAEN) : Adversarial Counterfactual Visual Explanations
April 12th | Nicolas Dufour (IMAGINE) : Recent advances in diffusion models
April 5th | Bülent Sarıyıldız (NAVER,THOTH) : Learning and evaluating visual representations for transfer learning
March 29th | Emre Akbas (METU) : Imbalance in object detection and ranking-based loss functions to the rescue
March 20th | Efstratios Gavves (UvA) : Computer Vision 3.0: Learning Invariances of Dynamics, Causality, Geometry, and Physics towards a Theory of Foundational and Embodied AI
March 15th | Raoul de Charette (INRIA) : Video, Language, Physics: Computer vision with other means of supervision
March 1st | Georg Martius (MPI) : Towards Model-Based Reinforcement Learning on Real Robots
February 22th | Thomas Müller (NVIDIA) : Instant NGP: Neural Networks in High Performance Graphics
February 15th | Hugo Touvron (FAIR) : Architectures and Training for Visual Understanding
February 8th | Denis Coquenet (CNAM) : Towards End-to-end Handwritten Document Recognition
January 25th | Ruben Villegas (Google Brain) : Visual storytelling with generative models of video.
January 18th | Jurgen Gall (University of Bonn) : Efficient CNNs and Transformers for Video Understanding and Image Synthesis
January 11th | Bill Peebles (BAIR) : Scalable Generative Modeling with Transformers and Diffusion
2022
December 7th | Shizhe Chen (Willow, Inria Paris) : Vision-and-Language Navigation
November 30th | Fatma Guney (Koç University) : Efficient Multi-Agent Trajectory Prediction and Unknown Object Segmentation
November 16th | Veronica Belmega (LIGM) : Handling anxiety when speaking in public.
November 2nd | Georgia Gkioxari (FAIR) : From 2D to 3D Visual Recognition: New Benchmarks, Models and Methods for 3D in the Wild
October 19th | Bernard Ghanem (KAUST) : Beyond Temporal Activity Localization (TAL) in Untrimmed Video
October 12th | Intern Day
September 28th | Yannis Siglidis : Diffusion 101
September 15th | Alyosha Efros (BAIR): TBA
September 21st | Robin Rombach (Heidelberg University, LMU Munich) : High-Resolution Image Synthesis via Two-Stage Generative Models
July 20th | Mathilde Caron (Google) : Self-Supervised Vision Transformers
July 13th | CVPR highlights
July 6th | Jean-Baptiste Alayrac (DeepMind) : Flamingo: a Visual Language Model for Few-Shot Learning
June 29nd | Antonín Vobecký (Czech Technical University) : Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
June 15th | Damien Robert (ENGIE Lab, Univ. Gustave Eiffel, IGN-ENSG) : Deep View Aggregation in the Wild
June 8th | Sagar Vaze (VGG) : Learning From Images in an Open World
May. 25th | Vincent Lepetit : How to write a research paper
May. 18th | Yangtao Wang (Université Grenoble Alpes): Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
May. 10th | Katerina Fragkiadaki (Carnegie Mellon University): Modular 3D neural scene representations for visuomotor control and language grounding
May. 4th | Elena Sizikova (NYU): Learning with Incomplete Supervision in Imaging Applications
Apr. 27th | Nanne van Noord (University of Amsterdam): Interdisciplinarity, Computer Vision, and Visual Culture
Apr. 20th | Nicolas Dufour : Perceiver papers presentation
Apr. 13th | Liliane Momeni (University of Oxford) : Computer Vision for Sign Language
March. 30th | Dmitriy Smirnov (MIT) : Deep Learning on Geometry Representations
March. 16th | Nermin Samet : Integrating near and long-range evidence for visual detection
March. 9th | Dimitris Tsipras (Stanford University): Controlling model behavior beyond the training data
Feb. 23rd | Fivos Kalogiannis (National Technical University of Athens): Min-max optimization in two-team zero-sum games
Rahima Djahel: A 3D Segments Based Algortihm For Heterogeneous Data Registration – Detecting Openings To Improve Indoor/Outdoor Registration
Feb. 16th | Stéphane Lathuilière (Télécom Paris): Self-Supervised Representation Learning for Video Generation
Feb. 9th | ECCV submission
Jan. 26th | Oriane Simeoni (Valeo.ia): Localizing Objects with Self-Supervised Transformers and no Labels
Jan. 19th | Thomas Belos: MOD SLAM: Mixed Method for a More Robust SLAM Without Loop Closing
Amanda Duarte: Sign Language Video Retrieval with Free-Form Textual Queries
Jan. 12th | Diogo Luvizon (Max Planck Institute): Novel view synthesis from a single image through multiplane image representation
Jan. 5th | Thibaut Issenhuth and Nicolas Dufour: Tutorial on GAN and Latent reweighting, an almost free improvement for GANs
2021
Dec. 14th | Pierre Alliez (INRIA): Progressive Discrete Domains for Implicit Surface Reconstruction
Dec. 8th | Emanuele Dalsasso (Télécom Paris): As if by magic: self-supervised training of deep despeckling networks with MERLIN
Arthur Oukanine (Télécom Paris and Valeo.ai): Multi-View Radar Semantic Segmentation
Dec. 1st | Van Huy Vo (Ecole Normale Superieure, INRIA and Valeo.ai) – Unsupervised Object Discovery
Nov. 24th | Yannis Kalantidis (NaverLabs): Measuring and Improving the Generalization of Self-supervised Learning
Nov. 17th | –
Nov. 10th | CVPR submission 2
Nov. 3rd | Yuming Du : Brief overview of deep learning based object detection/segmentation & Presentation of Champion Methods for UVO Challenges
Oct. 27th | ICCV 2021 highlights 2
Oct. 20th | ICCV 2021 highlights
Oct. 13th | CVPR submission
Oct. 6th | Intern projects : Nicolas Dufour, Georgy Ponimatkin and Yannis Siglidis
Sep. 29th | Francesc Moreno-Noguer (Institut de Robòtica i Informàtica Industrial): Deep Human Modeling from Single Images
Sep. 20th | Pascal Fua (EPFL): Deep Surface Meshes
Sep. 15th | Vicky Kalogeiton (École Polytechnique): Towards a moving word: The who, what and with whom for video understanding
Sep. 8th | Vivien Sainte-Fare-Garnot (IGN): Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks
Sep. 1st | Mathis Petrovich: Tutorial on Humans modeling, estimation and generation
Jul. 28th | Simon Roburin: Spherical Perspective on Learning with Batch Normalization and
Philippe Chiberre: Detecting Stable Keypoints from Events through Image Gradient Prediction
Jul. 21st | CVPR highlights (part 2)
Jul. 15th | CVPR highlights (part 1)
Jul. 7th | Jia-Bin Huang (University of Maryland): Learning to See the 3D world
Jun. 30th | Yasu Furukawa (Simon Fraser University): Teaching Computers to Design Architecture
Jun. 23rd | Rahima Djahel: Towards Efficient Indoor/Outdoor Registration Using Planar Polygons
Jun. 16th | Welcome seminar
Jun. 9th | Nicolas Gonthier: Convolutional Neural Networks for Art Analysis
Jun. 2nd | Yuki Asano (VGG Oxford University): Self-supervised Learning from Images, Videos, Audio and Text to Representations and Beyond
May. 12th | Victor Besnier: Uncertainty in neural networks
May. 5th | Tutorial on encoders (part 2)
Apr. 28th | Yana Hasson (INRIA): Hand-object reconstruction
Apr. 21st | Tutorial on encoders (part 1)
Apr. 14th | Yann Labbé (Inria)
Apr. 7th | Max Bain, Vincent Lepetit, Van-Nguyen Nguyen
March. 31st | Romain Loiseau: 3D point transformers
March. 3rd | ICCV submissions (part 2) Mathis Petrovich
Feb. 24th | ICCV submissions (part 1)
Feb. 17th | Siyu Tang (ETH Zurich)
Feb. 10th | Zan Gojcic (ETH Zurich): PREDATOR: Registration of 3D Point Clouds with Low Overlap and Weakly Supervised Learning of Rigid 3D Scene Flow
Feb. 3rd | Ahmet Iscen (Google): Memory-Efficient Incremental Learning Through Feature Adaptation
Jan. 27th | Pierre Jacob, Mathis Petrovich and Othman Sbai: Tutorial on Transformers
Jan. 13th | NeurIPS highlights (part 2)
Jan. 6th | NeurIPS highlights (part 1)
2020
Dec. 16th | Nerf
Dec. 9th | Pierre Jacob and Xi Chen: Metric learning
Dec. 2nd | Shangzhe Wu (VGG): Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
Nov. 25th | Muxingzi Li: Approximating shapes in images with low-complexity polygons
Oct. 28th | Tolga Birdal (Stanford)
Oct. 21st | CVPR submissions
Oct. 14th | Gül Varol: Scaling up sign language recognition
Oct. 7th | Tom Monnier and Elliot
Sep. 23rd | Interns project presentations
Sep. 16th | Helisa Dhamo: Layered Depth Images and Scene Graphs
Sep. 9th | ECCV highlights
Sep. 2nd | Sergey Zakharov
March. 11th | Francois Darmon and Hugo Germain
March. 4th | Thomas Belos: An introduction to Simultaneous Localization and Mapping
Feb. 12th | ECCV submissions
Jan. 30th | Elmar Mair (Google X)
Jan. 29th | Francisco Massa (FAIR)
Jan. 22nd | Jan Bednařík (CVLab): Shape Reconstruction by Learning Differentiable Surface Representation
Jan. 15th | Spyros Gidaris (ValeoAI): Few-Shot Learning
Jan. 8th | Loic Landrieu (IGN)
2019
Dec. 18th | Jan Bednařík (CVLab): Shape Reconstruction by Learning Differentiable Surface Representation
Dec. 18th | Yongchao Xu: Learning the relationship between neighboring pixels for some vision tasks
Dec. 10th | Raphael Groscot: 3D Deep Learning
Dec. 4th | Tom Monnier: Deep Segmentation Overview
Nov. 18th | ICCV highlights
Oct. 23rd | CVPR submissions : Yuming Du – Pierre-Alain Langlois – Othman Sbai – Xi Shen – Michaël Ramamonjisoa
Oct. 16th | Shell Xu Hu and Francois Darmon
Oct. 11th | Antoine Labatie (Graphcore)
Oct. 2nd | Bryan Russell (Adobe)
Sept. 26th | Xi Shen, Yang Xia: Domain Adaptation
May. 9th | Jean Feydy (ENS Cachan): Robust shape matching with Optimal Transport
May. 6th | Xi Shen
Apr. 25th | Othman Sbai, Oumayma Bounou: StyleGAN
Apr. 19th | Emilie Chouzenoux (UMLV-CentraleSupélec): Deep Unfolding of a Proximal Interior Point Method for Image Restoration
Apr. 15th | Ignacio Rocco (INRIA-WILLOW): Neighbourhoud Consensus Networks
Apr. 12th | Simon Roburin: Regularity of Neural Networks
Mar. 25th | Guillaume Charpiat (Inria-TAU – LRI): Deep Learning for Satellite Imagery
Mar. 18th | ICCV submissions
Mar. 11th | David Picard (ENSEA)
Mar. 4th | Corentin Tallec (Inria TAU-LRI): Reinforcement learning
Feb. 27th | Edouard Oyallon (CentraleSupélec): Layerwise learning
Feb. 25th | ICCV plans
Feb. 18th | Xuchong Qiu: Object pose estimation
Feb. 11th | Shell Hu, François Darmon: Bayesian deep learning
Feb. 4th | Gül Varol (Inria Willow): BodyNet – volumetric inference of 3D human body shapes in videos
Jan. 28th | Xuchong Qiu, Yang Xiao: Visual servoing & RL overview
Jan. 21st | Xi Shen: Low shot learning
Jan. 14th | Robin Champenois: Text generation
Jan. 7th | Thibault Groueix, Pierre-Alain Langlois: Solving earth mover’s distance (EMD)
2018
Dec. 20th | Pierre-Alain, Benjamin Dubois: Causality (and beyond)
Nov. 5th | CVPR plans 2
Oct. 29th | CVPR plans 1
Oct. 22nd | Adrien Kaiser (Telecom Paris): A survey of simple geometric primitives detection methods for captured 3D data
Oct. 15th | David Fouhey (UC Berkeley)
Oct. 8th | Théo Deprelle: GroupNorm, InstanceNorm, LayerNorm, BatchNorm…
Oct. 1st | Leman Feng: Curved optimal Delaunay triangulation
Sep. 17th | Othman Sbaï, Thibault Groueix, Théo Deprelle: ECCV highlightsth