The chapter describes visual classification by a hierarchy of semantic fragments. In fragment-based classification, objects within a class are represented by common sub-structures ...
In this paper, we present a generative model for textured motion phenomena, such as falling snow, wavy river and dancing grass, etc. Firstly, we represent an image as a linear sup...
Bottom-up segmentation tends to rely on local features. Yet, many natural and man-made objects contain repeating elements. Such structural and more spread-out features are importa...
A correct video segmentation, namely the detection of moving objects within a scene plays a very important role in many application in safety, surveillance, trafic monitoring and ...
The use of surface harmonics for rigid and nonrigid shape description is well known. In this paper we define a set of complete hemispherical harmonic basis functions on a hemisph...
Heng Huang, Lei Zhang 0002, Dimitris Samaras, Li S...