In this paper we propose a technique for segmenting images by texture content with application to indexing images in a large image database. Using a quad-tree decomposition, textu...
We propose a novel approach for modelling correlations
between activities in a busy public space captured by multiple
non-overlapping and uncalibrated cameras. In our approach,
...
Chen Change Loy (Queen Mary, University of London)...
High quality rendering and physics-based modeling in volume graphics have been limited because intensity-based volumetric data do not represent surfaces well. High spatial frequen...
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
Learning from data streams is a research area of increasing importance. Nowadays, several stream learning algorithms have been developed. Most of them learn decision models that c...