A key problem in learning multiple objects from unlabeled images is that it is a priori impossible to tell which part of the image corresponds to each individual object, and which...
Abstract. Human perception of shape is based on visual parts of objects to a point that a single, significant visual part is sufficient to recognize the whole object. For example,...
A hybrid (statistical/structural)approach is presented, for scale- and orientation-invariant recognition of multi-component cartographic symbols. A decision-tree classifier (DTC) ...
Abstract. While there has been substantial progress in segmenting natural images, state-of-the-art methods that perform well in such tasks unfortunately tend to underperform when c...
While there has been substantial progress in segmenting natural im-
ages, state-of-the-art methods that perform well in such tasks unfortunately tend
to underperform ...
A. Lucchi, K. Smith, R. Achanta, V. Lepetit, P. Fu...