VISION A Computational Investigation into the Human Representation and Processing of Visual Information

By Shimon Ullman, Tomaso A. Poggio. 2009

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020, background): “Marr’s (Marr, 1982) levels of computation make it clear that this must be the case: any given computation can be implemented in many ways, and not every implementation is transparent.”
Visualisation and 'diagnostic classifiers' reveal how recurrent and recursive neural networks process hierarchical structure (2017, positive): “Symbolic strategies In a similar fashion, diagnostic classiﬁers can be used to probe the strategy networks could be implementing on an algorithmic level (Marr, 1982), provided such strategies can be translated into sequences of targets for each time step.”
Information seeking, curiosity and attention: computational and neural mechanisms (2013, neutral): “However, important questions remain about the nature of intrinsic rewards at what David Marr would call the computational, representational and physical levels of description (Marr 2010).”
How does the brain solve visual object recognition? (2012, neutral): “One framework postulates that each successive visual area serially adds more processing power so as to solve increasingly complex tasks, such as the untangling of object identity manifolds (DiCarlo and Cox, 2007; Marr, 1982; Riesenhuber and Poggio, 1999b).”
Auto-Encoding Scene Graphs for Image Captioning (2018, background): “Not surprisingly, cognitive evidences [32] show that the visually grounded language generation is not end-toend and largely attributed to the “high-level” symbolic reasoning, that is, once we abstract the scene into symbols, the generation will be almost disentangled from the visual perception.”
PSYCHOLOGICAL SCIENCE Research Article Using Speakers ’ Referential Intentions to Model Early Cross-Situational Word Learning (unknown): “Our model operates at the ‘‘computational theory’’ level of explanation (Marr, 1982).”
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency (2020, background): “Irrespective of any potential differences at Marr’s implementational level [12] (which may be quite large, e.”
The Meaning of ‘Most’: Semantics, Numerosity and Psychology (2009, background): “Section 3 extends this point via the distinction between algorithms and functions computed (Church, 1941; Marr, 1982) in the context of semantics; cf.”
Three types of incremental learning (2022, unknown): “We put forward the view that, at the computational level 10 , there are three fundamental types, or ‘scenarios’, of supervised continual learning.”
Engineering a Less Artificial Intelligence. (2019, background): “These types of improvements relate to Marr’s three levels of analysis (Marr, 1982).”
How simple rules determine pedestrian behavior and crowd disasters (2011, background): “In fact, navigation and collision-avoidance concepts of multirobot systems have often been inspired by human behavior (32, 33).”
Bridging Levels of Analysis for Probabilistic Models of Cognition (2012, background): “Probabilistic models of cognition are cast at what Marr (1982) called the computational level.”
Optical techniques for 3D surface reconstruction in computer-assisted laparoscopic surgery (2013, background): “The 3D spatial understanding capabilities of the human visual system are heavily reliant on binocular vision and stereopsis (Marr and Poggio, 1979; Marr, 1983).”
EDITORIAL: ATTITUDES CAN BE MEASURED! BUT WHAT IS AN ATTITUDE? (2007, background): “Distinguishing between computational, algorithmic, and implementational levels of analysis (Marr, 1982), Cunningham et al. discuss the implications of their model for various questions, including the distinction between automatic (implicit) and reflective (explicit) evaluations, attitude…”
How Little Do We Need for 3-D Shape Perception? (2011, methodology): “This work builds upon the work of generalized cylinders by Binford (1971) and Marr (1982).”
Probing Physics Knowledge Using Tools from Developmental Psychology (2018, background): “Developmental psychologists are still debating various algorithmic-level explanations (Marr, 1982) underpinning intuitive physics in infants (see the Physical Reasoning System (Baillargeon & Carey, 2012) for an example).”