One of the pre-requisites for the realization of the Semantic Web vision are matching techniques which are capable of handling the open, dynamic and heterogeneous nature of the se...
Distance functions are an important component in many learning applications. However, the correct function is context dependent, therefore it is advantageous to learn a distance f...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...
In this paper, we address the problem of detecting pedestrians in still images. We introduce an algorithm for learning shapelet features, a set of mid?level features. These featur...
This paper presents a novel spatio-temporal Markov random field (MRF) for video denoising. Two main issues are addressed in this paper, namely, the estimation of noise model and t...