We propose a semi-supervised model which segments and annotates images using very few labeled images and a large unaligned text corpus to relate image regions to text labels. Give...
The Gauss map projects surface normals to a unit sphere, providing a powerful visualization of the geometry of a graphical object. It can be used to predict visual events caused b...
Bradley C. Lowekamp, Penny Rheingans, Terry S. Yoo
Graphs are often visualized using node-link representations: vertices are depicted as dots, edges are depicted as (poly)lines connecting two vertices. A directed edge running from...
The objective of this paper is to study the existing methods for unsupervised object recognition and image categorization and propose a model that can learn directly from the outp...
This paper discusses a unique way to visualize height field data – the use of solid fabricated parts with a photomapped texture to display scalar information. In this process, t...