Gaze visualizations represent an effective way for gaining fast insights into eye tracking data. Current approaches do not adequately support eye tracking studies for three-dimens...
Scientific data-sets often come with an inherent hierarchical structure such as functional substructures within organs. In this work we propose a new visualization approach for vo...
Jean-Paul Balabanian, Ivan Viola, Martin Ystad, Ar...
Abstract--Modeling background and segmenting moving objects are significant techniques for video surveillance and other video processing applications. Most existing methods of mode...
We present a Bayesian approach to image-based visual hull reconstruction. The 3-D shape of an object of a known class is represented by sets of silhouette views simultaneously obs...
Kristen Grauman, Gregory Shakhnarovich, Trevor Dar...
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...