We present CV4Code $$^1$$ , a compact and effective computer vision method for sourcecode understanding. Our leverages the contextual structural information available from code snippet by treating each as two-dimensional image, which naturally encodes context retains underlying through an explicit spatial representation. To codify snippets images, we propose ASCII codepoint-based image represen...

Perception and cognition are highly interrelated. Given the influence that these systems exert on one another, it is important to explain how perceptual representations and cognitive representations interact. In this paper, I analyze the similarities between visual perceptual representations and cognitive representations in terms of their structural properties and content. Specifically, I argue...

Automated reasoning about the design of effective visual problem representations is possible when we adopt the view that visual problem representations, along with the perceptual procedures that humans use to manipulate them, can be described using information-processing models of the sort introduced by Newell and Simon (1972). This approach provides us not only with a means of characterizing v...

This paper examines the construction and use of visual representations for reasoning. Visual representations have often been categorized by a resemblance criterion: representations of objects are considered iconic, because they resemble a perceived object, while representations of abstractions, which cannot resemble an object, are considered unconstrained and therefore arbitrary. In contrast, I...

One of the main functions of visual system is to construct representations of objects. These visual objects are formed by developing and modifying the structure of more primitive visual representations. In the paper, I consider the type of structural change that transforms visual regions, which may be treated as maximal non-object representations, into basic, low-level visual objects. In order ...