This paper studies two types of spatial relationships that can be learned from training examples for object recognition. The first one employs deformable relationships between obj...
This paper presents a multi-scale generative model for representing animate shapes and extracting meaningful parts of objects. The model assumes that animate shapes (2D simple clo...
Abstract. The complexity of visual representations is substantially limited by the compositional nature of our visual world which, therefore, renders learning structured object mod...
We study the problem of object classification when training
and test classes are disjoint, i.e. no training examples of
the target classes are available. This setup has hardly be...
Christoph H. Lampert, Hannes Nickisch, Stefan Harm...
Latent Layout Analysis (LLA) is a novel unsupervised learning technique to discover objects in unseen images using a set of un-annotated training images. LLA defines a generative ...