3-D vision and figure-ground separation by visual cortex

By Stephen Grossberg. Perception & Psychophysics, 2010

501 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/578bc7eeda773ee1f28a73b2a1f55086522514c9

How researchers see this paper

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

In Cognitive Neuroscience

1. Stephen Grossberg
2. Heiko Neumann
3. Pierre Bayerl
4. Iasonas Kokkinos
5. Rachid Deriche
6. Petros Maragos
7. Olivier D. Faugeras
8. G. Stoner

In Computer Vision and Pattern Recognition

1. Rachid Deriche
2. Daniel Cremers
3. Iasonas Kokkinos
4. Stephen Grossberg
5. Heiko Neumann
6. Pierre Bayerl
7. Petros Maragos
8. Olivier D. Faugeras

Citations in the corpus

• A neural model of figure-ground organization. (2007, unknown): “…used region labeling, assuming, for example, that color/brightness signals spread within a cortical sheet to fill in the regions within the boundaries given by the contour representation (Arrington 1994; Gerrits and Vendrik 1970; Grossberg 1994; Grossberg and Mingolla 1985; Roelfsema et al. 2002).”
• FigureGround Segregation in a Recurrent Network Architecture (2002, unknown): “In a relatively elaborate modeling approach, Gross-berg and Mingolla (1985, 1993), Grossberg (1994), and Cohen and Grossberg (1984) suggested that boundaries and surface properties are represented by separate neural systems, localized in different functional compartments of areas V1 and V2, which…”
• Adaptive Resonance Theory: How a brain learns to consciously attend, learn, and recognize a changing world (2013, background): “A basic discovery and prediction about perceptual boundaries and surfaces is that they obey complementary computational laws (Grossberg, 1994):”
• Disambiguating Visual Motion Through Contextual Feedback Modulation (2004, methodology): “Grossberg, Mingolla and Viswanathan (2001) and Mingolla (2003) presented a model of motion integration and segmentation in MT and MST based on inputs from the form pathway (modeled as the FACADE framework—Form-And-Color-And-DEpth) (Grossberg, 1994).”
• 2007 Special Issue: Consciousness CLEARS the mind (2007, unknown): “…interactions occur between the boundary and surface representations in cortical areas V1 and V2, and are predicted to help separate figures from their background in depth, and to control saccadic eye movements (Fang and Grossberg, 2007; Fazl, Grossberg, and Mingolla, 2007; Grossberg, 1994, 1997).”
• Context-sensitive binding by the laminar circuits of V1 and V2: A unified model of perceptual grouping, attention, and orientation contrast (2001, background): “, 1995; Polat & Sagi, 1993) and of smooth contours (Field, Hayes, & Hess, 1993; Kovacs & Julesz, 1993), and which also gives rise to the percept of illusory contours (Kanizsa, 1979) when the inducing stimuli also cause a brightness difference across the two sides of the collinear group (Grossberg, 1”
• Border ownership from intracortical interactions in visual area v2. (2005, unknown): “Grossberg (1994) has suggested a number of interesting models of border and surface processing, though these also do not address BOWN tuning.”
• Computational analysis and learning for a biologically motivated model of boundary detection (2008, methodology): “This contradicts typical computational [50,64,83] and biological [24,48] models which assume texture processing takes place in a separate stream that cooperates with boundary processing.”
• Visual motion perception. (1995, background): “They act like statistical and-gates that that permit grouping only when there is sufficient evidence from pairs or greater numbers of inducers on both sides of the cell body (Grossberg, 1994; Grossberg and Mingolla, 1985a, 1985b).”