We introduce a new descriptor for images which allows the construction of efficient and compact classifiers with good accuracy on object category recognition. The descriptor is the...
We consider clustering situations in which the pairwise affinity between data points depends on a latent ”context” variable. For example, when clustering features arising fro...
Abstract. In this paper we introduce a new representation for shapebased object class detection. This representation is based on very sparse and slightly flexible configurations of...
Objects in the world can be arranged into a hierarchy based on their semantic meaning (e.g. organism ? animal ? feline ? cat). What about defining a hierarchy based on the visual ...
Josef Sivic, Bryan C. Russell, Andrew Zisserman, W...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...