This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflec...
We present a method that using only an uncalibrated camera allows the capture of object geometry and appearance, and then at a later stage registration and AR overlay into a new s...
This paper presents a framework for a learning based approach to dynamically evolve the conceptual structure of a database in order to facilitate virtual representation of data in ...
We present a new role system for specifying changing referencing relationships of heap objects. The role of an object depends, in large part, on its aliasing relationships with ot...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...