We consider how tracking in stereo may be enhanced by coupling pairs of active contours in different views via affine epipolar geometry and various subsets of planar affine transf...
Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised. In this paper we present a novel method for obtaini...
This paper discusses the relevance of a form of cut elimination theorem for linear logic tensor theories to the concept of a process on a Petri net. We base our discussion on two ...
In semi-supervised learning, a number of labeled examples are usually required for training an initial weakly useful predictor which is in turn used for exploiting the unlabeled e...
We introduce the problem of scene viewpoint recognition, the goal of which is to classify the type of place shown in a photo, and also recognize the observer’s viewpoint within ...
Jianxiong Xiao, Krista A. Ehinger, Aude Oliva, Ant...