This paper conducts an in-depth study on a classical perceptual-organization problem: finding salient closed boundaries from a set of boundary fragments detected in a noisy image....
We present a complete system for the purpose of automatically assembling 3D pots given 3D measurements of their fragments commonly called sherds. A Bayesian approach is formulated...
We consider the problem of computing the likelihood of a gesture from regular, unaided video sequences, without relying on perfect segmentation of the scene. Instead of requiring ...
The notion of using context information for solving highlevel vision problems has been increasingly realized in the field. However, how to learn an effective and efficient context...
This paper presents a purely image-based approach to fusing foreground silhouette information from multiple arbitrary views. Our approach does not require 3D constructs like camer...