In this paper we propose a novel approach to the perceptual interpretation of building facades that combines shape grammars, supervised classification and random walks. Procedural...
This paper exploits the properties of the commute time between nodes of a graph for the purposes of clustering and embedding, and explores its applications to image segmentation a...
Image restoration is a keen problem of low level vision. In this paper, we propose a novel - assumption-free on the noise model - technique based on random walks for image enhancem...
Image annotation plays an important role in image retrieval and management. However, the results of the state-of-the-art image annotation methods are often unsatisfactory. Therefo...
Changhu Wang, Feng Jing, Lei Zhang, HongJiang Zhan...
Global shape information is an effective top-down complement
to bottom-up figure-ground segmentation as well
as a useful constraint to avoid drift during adaptive tracking.
We p...