We propose a solution to the problem of object recognition given a continuous video sequence containing multiple views of an object. Initially, object models are acquired from ima...
Under natural viewing conditions, human observers shift their gaze to allocate processing resources to subsets of the visual input. Many computational models try to predict such v...
This paper presents a novel method for the interactive identification of contextual interest points within volumetric data by picking on a direct volume rendered image. In clinica...
Peter Kohlmann, Stefan Bruckner, Armin Kanitsar, M...
We treat feature selection and basis selection in a unified framework by introducing the masking matrix. If one considers feature selection as finding a binary mask vector that de...
We introduce a general formulation, called non-negative graph embedding, for non-negative data decomposition by integrating the characteristics of both intrinsic and penalty graph...