A neural model of figure-ground organization.

By Edward Craft, Hartmut Schütze, Ernst Niebur, R. von der Heydt. 2007

280 citations recorded by the source corpus.

Subfields: Cellular and Molecular Neuroscience, Cognitive Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cellular and Molecular Neuroscience

In Cognitive Neuroscience

Citations in the corpus

A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs (2017, background): “Contours generated by the contour hierarchy interact with the surface CRF in a specific way: Contours signal the breaks in continuity of surfaces that occur both within an object and between the object and its background, a representational choice inspired by neurobiology (19).”
Spike Synchrony Reveals Emergence of Proto-Objects in Visual Cortex (2015, background): “Given the low conduction velocity of intracortical fibers, it is hard to explain the speed of this extensive context integration by lateral propagation of signals in V2 or V1 (Craft et al., 2007; Zhang and von der Heydt, 2010).”
Figure–ground organization and the emergence of proto-objects in the visual cortex (2015, background): “The G-cells have fixed summation templates (the Craft et al., 2007, model assumes annular templates summing ‘co-circular’ edge signals).”
Mechanisms of perceptual organization provide auto-zoom and auto-localization for attention to objects (2010, background): “A parsimonious explanation of how these neurons can respond highly specifically to stimuli far outside their receptive fields proposes the existence of “grouping cells” (G cells) that organize visual input into proto-objects, without going all of the way to complete object recognition (13).”
Figure-ground mechanisms provide structure for selective attention (2007, background): “We have previously proposed a model for border-ownership assignment that is based on simple circuits that integrate image contex”
Recurrent Processing during Object Recognition (2013, methodology): “This is because extensive research has indicated that early levels of the visual pathway, specifically in area V2, contain specialized figure-ground processing mechanisms that perform border ownership labeling (Zhaoping, 2005; Craft et al., 2007; Poort et al., 2012).”