While stereo matching was originally formulated as the recovery of 3D shape from a pair of images, it is now generally recognized that using more than two images can dramatically ...
Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent "atomic" events. It also requires the capacity to ro...
We propose a practical path-based framework for deriving and simplifying source-tracking information for term unification in the empty theory. Such a framework is useful for debugg...
Robust joint visual attention is necessary for achieving a common frame of reference between humans and robots interacting multimodally in order to work together on realworld spat...
Taxonomic case retrieval systems significantly outperform standard conversational case retrieval systems. However, their feature taxonomies, which are the principal reason for thei...