Most methods for object class segmentation are formulated as a labelling problem over a single choice of quantisation of an image space - pixels, segments or group of segments. It...
Lubor Ladicky, Christopher Russell, Pushmeet Kohli...
Practical data mining rarely falls exactly into the supervised learning scenario. Rather, the growing amount of unlabeled data poses a big challenge to large-scale semi-supervised...
To minimize the number of wavelengths required by a multicast session in sparse light splitting Wavelength Division Multiplexing (WDM) networks, a light-hierarchy structure, which ...
Terrains are an essential part of outdoor environments. Terrain models are important for computer games and applications in architecture, urban design and archaeology. A popular a...
: Single training image face recognition is one of main challenges to appearance-based pattern recognition techniques. Many classical dimensionality reduction methods such as LDA h...