Cortical spatiotemporal dimensionality reduction for visual grouping

DOI10.1162/NECO_A_00738zbMATH Open1414.92084arXiv1407.0733WikidataQ41136304 ScholiaQ41136304MaRDI QIDQ5380249FDOQ5380249

Giacomo Cocci, Giovanna Citti, Davide Barbieri, A. Sarti

Publication date: 4 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Abstract: The visual systems of many mammals, including humans, is able to integrate the geometric information of visual stimuli and to perform cognitive tasks already at the first stages of the cortical processing. This is thought to be the result of a combination of mechanisms, which include feature extraction at single cell level and geometric processing by means of cells connectivity. We present a geometric model of such connectivities in the space of detected features associated to spatio-temporal visual stimuli, and show how they can be used to obtain low-level object segmentation. The main idea is that of defining a spectral clustering procedure with anisotropic affinities over datasets consisting of embeddings of the visual stimuli into higher dimensional spaces. Neural plausibility of the proposed arguments will be discussed.

Full work available at URL: https://arxiv.org/abs/1407.0733

Recommendations

• A cortical-inspired geometry for contour perception and motion integration
• Mathematical models of visual perception based on cortical architectures
• Spatially-variant structuring elements inspired by the neurogeometry of the visual cortex
• Local and global gestalt laws: a neurally based spectral approach
• The symplectic structure of the primary visual cortex

zbMATH Keywords

spectral clusteringcortical spatiotemporal dimensionality reductionvisual grouping

Mathematics Subject Classification ID

Psychophysics and psychophysiology; perception (91E30) Neural biology (92C20)

Cites Work

• Title not available (Why is that?)
• Diffusion maps
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Title not available (Why is that?)
• Title not available (Why is that?)
• A cortical-inspired geometry for contour perception and motion integration
• What geometric visual hallucinations tell us about the visual cortex
• On clusterings
• Neuromathematics of vision
• Representation of local geometry in the visual system
• The visual cortex is a contact bundle
• The constitution of visual perceptual units in the functional architecture of V1
• Numerical approaches for linear left-invariant diffusions on \(SE(2)\), their comparison to exact solutions, and their applications in retinal imaging
• The explicit solutions of linear left-invariant second order stochastic evolution equations on the 2D Euclidean motion group
• Persistent Neural States: Stationary Localized Activity Patterns in Nonlinear Continuous n-Population, q-Dimensional Neural Networks
• Title not available (Why is that?)
• Geometrical Computations Explain Projection Patterns of Long-Range Horizontal Connections in Visual Cortex
• Stochastic simulation and Monte Carlo methods. Mathematical foundations of stochastic simulation
• How uncertainty bounds the shape index of simple cells

Cited In (6)

• Perceptual grouping and the interactions between visual cortical areas
• Analysis of vessel connectivities in retinal images by cortically inspired spectral clustering
• A sub-Riemannian model of the visual cortex with frequency and phase
• Local and Global Gestalt Laws: A Neurally Based Spectral Approach
• A geometric model of multi-scale orientation preference maps via Gabor functions
• Functional architecture of M1 cells encoding movement direction

This page was built for publication: Cortical spatiotemporal dimensionality reduction for visual grouping

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380249)