Context-dependent word similarity can be measured over multiple cross-cutting dimensions. For example, lung and breath are similar thematically, while authoritative and superfici...
We propose an approach for learning visual models of object categories in an unsupervised manner in which we first build a large-scale complex network which captures the interacti...
This paper introduces a new feature-based technique for implicitly modelling objects in visual surveillance. Previous work has generally employed background subtraction and other ...
In this paper, we explore several extensions to surface pasting. In particular, using the task of modelling a ferret as a driving force, we improved the user interface for cylindr...
This paper presents a generative model based approach to man-made structure detection in 2D natural images. The proposed approach uses a causal multiscale random field suggested i...