Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. By David Marr

By Malcolm Acock. 1985

Subfields: Computer Vision and Pattern Recognition, Neuroscience, Cognitive Science & Psychology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Neuroscience

In Cognitive Science & Psychology

Citations in the corpus

How Can We Accelerate Progress Towards Human-like Linguistic Generalization? (2020, background): “These implementational-level factors (Marr, 1982) are orthogonal to our generalization concerns, which are formulated at the level of input–output correspondence.”
MarrNet: 3D Shape Reconstruction via 2.5D Sketches (2017, methodology): “Researchers in human perception argued that our 3D perception could rely on recovering 2.5D sketches [Marr, 1982], which include intrinsic images [Barrow and Tenenbaum, 1978, Tappen et al., 2003] like depth and surface normal maps (Figure 1b).”
The Method of Levels of Abstraction (2008, background): “For the specific case of a system that solves an information-processing problem, there are in addition the twin strands of process and representation, and both these ideas need some discussion’’ (Marr 1982, pp. 19–20). In particular, in the case of an information-processing system, Marr and his foll”
Diagnostic Classifiers Revealing how Neural Networks Process Hierarchical Structure (2016, methodology): “Diagnostic Classifiers To analyse the internal dynamics of the GRU, we propose a generic method that can be used to test and formulate hypotheses about solutions a model could be implementing on an algorithmic level [Marr, 1982].”
Emotions as a mechanism for boundedly rational agents : the fast and frugal way (2005, background): “Marr (1982) argues that there are three levels of analysis within an evolutionary explanation of the human mind.”
Visual Parsing After Recovery From Blindness (2009, background): “How this is achieved is a fundamental question, and has been researched extensively in the domains of experimental and computational neuroscience (Brady & Kersten, 2003; Hummell & Biederman, 1992; Hupe et al., 1998; Marr, 1982; Needham, 2001; Tu, Chen, Yuille, & Zhu, 2003; Ullman, 1996; Wertheimer, ”
Explanation and Abductive Inference (2012, background): “The unique explanatory contributions of mechanistic and functional explanations may be familiar to psychologists acquainted with Marr's levels of analysis (Marr, 1982).”
The iterative reprocessing model: A multilevel framework for attitudes and evaluation. (2007, methodology): “We describe the Iterative Reprocessing Model at the computational, algorithmic, and implementational levels of analysis (Marr, 1982) to more fully characterize its premises and predictions.”
Dual Process Th eories (2013, background): “operations that transform environmental inputs into behavioral outputs (De Houwer, 2011; Gawronski & Bodenhausen, 2015a; Marr, 1982).”
Components of bottom-up gaze allocation in natural images. (2005, background): “These reflect many of the fundamental computational operations thought to be performed in the early stages of the visual system (Marr, 1982; Wandell, 1995).”
Task and context determine where you look. (2016, background): “Whereas the former is directed more toward a mechanistic implementation, the latter addresses the question of the goal of vision (Marr, 1982).”
Associative learning of likes and dislikes: a review of 25 years of research on human evaluative conditioning. (2001, methodology): “The referential model as formulated by Baeyens et al. (Baeyens & De Houwer, 1995; Baeyens, Eelen, & Crombez, 1995) can be characterized as a functional model rather than as a computational or algorithmic model (Marr, 1982).”
Some puzzling findings in multiple object tracking (MOT): II. Inhibition of moving nontargets (2006, background): “Processes that identify tokens by clustering image features were among the first studied in computational vision (Marr, 1982).”
A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex (2005, background): “, Barlow’s suspicious coincidences [Barlow, 1989] or smoothness properties [Sutton and Barto, 1981; Marr, 1982; Becker and Hinton, 1992; Stone and Bray, 1995; de Sa and Ballard, 1998], etc.”
Reconciling intuitive physics and Newtonian mechanics for colliding objects. (2013, methodology): “Marr (1982) was sympathetic to Gibson's (1966) claim that people used perceptual invariants, such as the mass ratio in the KSD approach, but believed Gibson had greatly underestimated the difficulty required to construct invariants.”
Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks (2011, methodology): “These are located by nding the zero crossing pointof the Laplacian as introduced by Marr (1982).”
An Introduction to Model-Based Cognitive Neuroscience (2015, methodology): “For example, Hashemi, Bradley, and Lisanti [45] give a mostly nontechnical description of MR physics, whereas Haacke, Brown, Thompson, and Venkatesan [46] provide a much more rigorous treatment.”
NEUROECONOMICS: A CRITICAL RECONSIDERATION (2008, background): “Some, such as Ross (2005: 322) define neuroeconomics partly in terms of a research program, perhaps best associated with Glimcher (2003) and Montague and Berns (2002), by way of Marr (1982), that uses economics principles to explain the evolution of neural behavior in animals.”