Computer Vision

Working Memory in Recurrent Spiking Neural Networks Using Heterogeneous Synaptic Delays
Working memory, the ability to store and retrieve precise temporal patterns of neural activity, remains a fundamental challenge for …
2026-04-16 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite Slides URL
Foveated Retinotopy Improves Classification and Localization in CNNs
Foveated Retinotopy in CNNs. We represent Left an input image and how it is transformed by foveated retinotopy. We show below a …
PDF Cite DOI URL arXiv
Foveated Retinotopy Improves Classification and Localization in CNNs
2026-01-29-emergences
Sparse representations in biological vision applied to the effciency of machine learning.
2026-01-29 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
A saccade-inspired approach to image classification using vision transformer attention maps
Saccade selection method: (a.) The input image of dimensionH× Wis split intoH16×Wnsized patches and embeddedinto token vectors. (b.) …
Cite DOI arXiv
Lab Tour for Art - Perception Collaboration
By construction, deep convolutional networks treat all pixels equally. Result: they are energy-hungry, fragile to rotations or zooms, …
2026-01-01 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite URL
Lab Tour for Art - Perception Collaboration
A New Look for Convolutional Deep Networks
By construction, deep convolutional networks treat all pixels equally. Result: they are energy-hungry, fragile to rotations or zooms, …
2025-12-12 Behavioural Neuroscience, Biological Neuroscience, Computer Vision, NeuroAI & Machine Learning, Visual Neuroscience
Cite MAIN Slides YouTube
A New Look for Convolutional Deep Networks
By construction, deep convolutional networks treat all pixels equally. Result: they are energy-hungry, fragile to rotations or zooms, …
2025-12-02 Behavioural Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite URL
Foveal Retinotopy and Dual Pathways: A Computational Model for Active Visual Search
Abstract This thesis investigates visual search through the lens of the dual visual pathways found in biological systems : the ventral …
Cite
Soutenance de Jean-Nicolas Jérémie "Foveal Retinotopy and Dual Pathways: A Computational Model for Active Visual Search"
Jean-Nicolas Jérémie soutiendra publiquement ses travaux de thèse intitulés: Foveal Retinotopy and Dual Pathways: A Computational Model …
2025-10-10 4 min read Behavioural Neuroscience, Biological Neuroscience, Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
Soutenance de Jean-Nicolas Jérémie "Foveal Retinotopy and Dual Pathways: A Computational Model for Active Visual Search"
DynTex: A Real-Time Generative Model of Dynamic Naturalistic Luminance Textures
The visual systems of animals work in diverse and constantly changing environments where organism survival requires effective senses. …
Cite Project DOI URL HAL
DynTex: A Real-Time Generative Model of Dynamic Naturalistic Luminance Textures
2025-03-11-phd-program-sparse-representations
Sparse representations in machine learning applied to the understanding of biological vision
2025-03-11 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
2025-02-11-neuromath
When Cortical Neurons Talk Sideways: Beyond Feedforward Visual Processing
2025-02-11 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience, Visual Neuroscience
Project
How and why foveated retinotopy provides efficient vision
The retinas of many animals, including humans, have a specialized area of high visual acuity called the fovea, while peripheral regions …
2025-01-08 Biological Neuroscience, Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Visual Neuroscience
Cite URL
Integrating the What and Where Visual Pathways to Improve CNN Categorisation
Convolutional Neural Networks (CNNs) have been widely used for categorisation tasks over the past decades. Many studies have attempted …
PDF Cite URL HAL URL Abstract
Integrating the What and Where Visual Pathways to Improve CNN Categorisation
Sparse representations
Sparse coding is a technique used in signal processing and machine learning to represent data in a more concise and efficient manner. …
2024-04-17 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite Project Slides Code URL
2024-04-17-phd-program-sparse-representations
Sparse representations in machine learning applied to the understanding of biological vision
2024-04-10 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
2024-02-05-udem.md
Neuromorphic models of vision, a Seminar at UdeM’s School of Optometry, Montréal
2024-02-05 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
Event-based vision
Event-based cameras mimic the way biological retinas process visual information: each pixel independently reports brightness changes as …
2023-12-14 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite Slides Venue URL
2023-12-14-jraf.md
Event-based vision
2023-12-14 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
Event-based vision
Event-based cameras mimic the way biological retinas process visual information: each pixel independently reports brightness changes as …
Last updated on 2023-11-29 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite Slides URL
Event-based vision
The biological retina represents changes in light intensity and communicates them to the brain by means of spikes. Similarly, …
2023-12-01 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite Slides URL
Event-based vision
2023-12-01-biocomp.md
Event-based vision
2023-12-01 Computer Vision
Time-to-Contact Map by Joint Estimation of Up-to-Scale Inverse Depth and Global Motion using a Single Event Camera
Event cameras asynchronously report brightness changes with a temporal resolution in the order of microseconds, which makes them …
Cite DOI Venue Pdf Code URL
Time-to-Contact Map by Joint Estimation of Up-to-Scale Inverse Depth and Global Motion using a Single Event Camera
Event-based vision
Event-based cameras mimic the way biological retinas process visual information: each pixel independently reports brightness changes as …
Last updated on 2023-09-05 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite Slides URL
2023-09-08_fresnel.md
Event-based vision
2023-09-08 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
Ultra-rapid visual search in natural images using active deep learning
Visual search, that is, the simultaneous localization and detection of a visual target of interest, is a vital task. Applied to the …
PDF Cite Venue
Ultra-rapid visual search in natural images using active deep learning
Retinotopic mapping improves the reliability of image classification
Follows a previous work A dual foveal-peripheral visual processing model implements efficient saccade selection Emmanuel Daucé, Pierre …
Last updated on 2022-05-20 Biological Neuroscience, Computer Vision, Visual Neuroscience
PDF Cite URL
What You See Is What You Transform: Foveated Spatial Transformers as a Bio-Inspired Attention Mechanism
Convolutional Neural Networks have been considered the go-to option for object recognition in computer vision for the last couple of …
PDF Cite DOI URL
What You See Is What You Transform: Foveated Spatial Transformers as a Bio-Inspired Attention Mechanism
Understanding natural vision using deep predictive coding
Building models which efficiently process images is a great source of inspiration to better understand the processes which underly our …
2020-09-25 Biological Neuroscience, Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
Cite Slides Code URL
PhD offer "Ultra-fast vision using Spiking Neural Networks"
THE POSITION HAS BEEN FILLED. Offre de thèse “Vision ultra-rapide par réseaux de neurones impulsionnels” à Marseille
2020-06-30 9 min read Behavioural Neuroscience, Computer Vision, NeuroAI & Machine Learning
PhD offer "Ultra-fast vision using Spiking Neural Networks"
A dual foveal-peripheral visual processing model implements efficient saccade selection
In computer vision, the visual search task consists in extracting a scarce and specific visual information (the target) from a large …
Cite DOI Pdf Code URL bioRxiv
2020-03-13: Soutenance de thèse Victor Boutin
Victor Boutin (Equipe NeOpTo) a soutenu sa thèse de doctorat intitulée: Sparse deep predictive coding: a bio-inspired model of visual perception / Etude d’un algorithme hiérarchique et codage épars et prédictif : vers un modèle bio-inspiré de la perception visuelle le Vendredi 13 mars à 14h
Last updated on 2020-03-04 4 min read Biological Neuroscience, Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
2020-03-13: Soutenance de thèse Victor Boutin
Postdoc position on Visual computations using Spatio-temporal Diffusion Kernels and Traveling Waves
THE POSITION HAS BEEN FILLED. 18 month Post-doc position coordinated by Laurent Perrinet, supported by (INT, Marseille) and Yves Frégnac (UNIC-NeuroPSI, Gif).
2019-10-21 7 min read Behavioural Neuroscience, Biological Neuroscience, Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience, Visual Neuroscience
Postdoc position on Visual computations using Spatio-temporal Diffusion Kernels and Traveling Waves
APROVIS3D (2019/2023)
Analog PROcessing of bioinspired VIsion Sensors for 3D reconstruction (APROVIS3D) is 2018 CHIST-ERA laureate.
Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
APROVIS3D (2019/2023)
Learning where to look: a foveated visuomotor control model
In computer vision, the visual search task consists in extracting a scarce and specific visual information (the target) from a large …
2019-07-15 Behavioural Neuroscience, Biological Neuroscience, Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience, Visual Neuroscience
PDF Cite Slides Pdf Code URL
SpikeAI: laureat du Défi Biomimétisme (2019)
Algorithmes événementiels d’Intelligence Artificielle / Event-Based Artificial Inteligence (2019).
Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience
SpikeAI: laureat du Défi Biomimétisme (2019)
A hierarchical, multi-layer convolutional sparse coding algorithm based on predictive coding
Sparse coding holds the idea that signals can be concisely described as a linear mixture of few components (called atoms) picked from a …
PDF Cite URL
An adaptive homeostatic algorithm for the unsupervised learning of visual features
The formation of structure in the visual system, that is, of the connections between cells within neural populations, is by large an …
PDF Cite Project DOI Code URL
A low-cost, accessible eye tracking framework
Recording eye movements is a technique that attracts an increasing number of scientists, but also in the general public. Indeed, this …
Cite Pdf URL
What dynamic neural codes for efficient visual processing
This seminar is an exercise to introduce the AMU masters into the format of international conferences. As such, we will try to …
2017-11-15 Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
Cite Slides URL
Controlling an aerial robot with human gestures using bio-inspired algorithm
Improve performances of existing recognition computer vision algorithms with biological concepts. The gain are expected in the …
Cite
Biologically-inspired characterization of sparseness in natural images
2016-10-26 Computational Neuroscience, Computer Vision
Cite Conference Slides Code URL
Categorization of microscopy images using a biologically inspired edge co-occurrences descriptor
See a followup in Edge co-occurrences can account for rapid categorization of natural versus animal images Laurent U Perrinet, James A …
2016-10-26 Computational Neuroscience, Computer Vision
Cite Conference Slides Code URL
2016-10-26 : EUVIP BICV
EUVIP Session 7: Biologically Inspired Computer Vision (Special Session).
2016-10-26 2 min read Behavioural Neuroscience, Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning
2016-10-26 : EUVIP BICV
ANR TRAJECTORY (2016/2019)
ANR TRAJECTORY (2016/2019).
Biological Neuroscience, Computational Neuroscience, Computer Vision, Visual Neuroscience
Project
ANR TRAJECTORY (2016/2019)
Open Science
To enable the dissemination of the knowledge that is produced in our lab, we share all source code with open source licences.
Project Project
Open Science
Introduction
This is the introductory chapter of the book, which serves as a comprehensive but rigorous reference in the area of biologically …
Cite DOI URL
Sparse Models for Computer Vision
The representation of images in the brain is known to be sparse. That is, as neural activity is recorded in a visual area, for instance …
Cite Project DOI Code URL arXiv
Sparse Models for Computer Vision
Visual motion processing and human tracking behavior
Appeared in this book: Gabriel Cristóbal, Laurent U Perrinet, Matthias S Keil (2015). Biologically Inspired Computer Vision. Cite DOI …
Cite DOI Pdf URL arXiv
Biologically Inspired Computer Vision
As the state-of-the-art imaging technologies became more and more advanced, yielding scientific data at unprecedented detail and …
Cite DOI Code URL
Biologically Inspired Computer Vision
Edge co-occurrences can account for rapid categorization of natural versus animal images
Making a judgment about the semantic category of a visual scene, such as whether it contains an animal, is typically assumed to involve …
Cite DOI Code URL HAL
Edge co-occurrences can account for rapid categorization of natural versus animal images
Advances in Texture Analysis for Emphysema Classification
In recent years, with the advent of High-resolution Computed Tomography (HRCT), there has been an increased interest for diagnosing …
Cite DOI URL
Computational Neuroscience: From Representations to Behavior
Computational Neuroscience: From Representations to Behavior, the Second NeuroComp Marseille Workshop.
2008-10-08 8 min read Behavioural Neuroscience, Biological Neuroscience, Computational Neuroscience, Computer Vision, NeuroAI & Machine Learning, Theoretical Neuroscience, Visual Neuroscience
Project
Computational Neuroscience: From Representations to Behavior
Self-Invertible 2D Log-Gabor Wavelets
Meanwhile biorthogonal wavelets got a very popular image processing tool, alternative multiresolution transforms have been proposed for …
PDF Cite Project DOI Code URL
Self-Invertible 2D Log-Gabor Wavelets