Datasets are an integral part of contemporary object recognition research. They have been the chief reason for the considerable progress in the field, not just as source of large...
We present a surprisingly simple system that allows for robust normal reconstruction by dense photometric stereo, in the presence of severe shadows, highlight, transparencies, com...
This paper describes an original method for classifying object motion trajectories in video sequences in order to recognize dynamic events. Similarities between trajectories are e...
Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre L...
This paper proposes to combine spatial and color coherency with the pixel-wise GMM to determine the background model. We first represent each pixel with a hybrid feature vector, w...
In this paper we propose a set of algorithms that combine the anisotropic smoothing using the heat kernel with the outlier rejection capability of robust statistics. The proposed ...