In this paper we describe a hybrid approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple feature s...
Alexander G. Hauptmann, Ming-yu Chen, Michael G. C...
In this paper, we propose a method for 3D-model retrieval from one or more photos. This method provides an ”optimal” selection of 2D views to represent a 3D-model, and a proba...
We propose a novel Bayesian learning framework of hierarchical mixture model by incorporating prior hierarchical knowledge into concept representations of multi-level concept struc...
In this paper we propose a new General Image DataBase (GIDB) model. The model establishes taxonomy based on the systematisation of existing approaches. The GIDB model is based on t...
Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require ite...