In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...
A system is described that tracks moving objects in a video dataset so as to extract a representation of the objects' 3D trajectories. The system then finds hierarchical clus...
In this publication, we apply the concept of foveal imaging to appropriately direct the attention of the viewer during browsing raster image contents. The proposed approaches are ...
This paper describes a framework for constructing a linear subspace model of image appearance for complex articulated 3D figures such as humans and other animals. A commercial mo...
Hedvig Sidenbladh, Fernando De la Torre, Michael J...
Multimodal grammars provide an expressive formalism for multimodal integration and understanding. However, handcrafted multimodal grammars can be brittle with respect to unexpecte...