In many vision problems, instead of having fully annotated training data, it is easier to obtain just a subset of data with annotations, because it is less restrictive for the use...
Bayesian networks are an attractive modeling tool for human sensing, as they combine an intuitive graphical representation with ef?cient algorithms for inference and learning. Ear...
Tanzeem Choudhury, James M. Rehg, Vladimir Pavlovi...
This paper introduces Mycrocosm, a microblogging site in which users communicate via statistical graphics, rather than the usual short text statements. Users of Mycrocosm can reco...
Abstract. Navigating consists of coordinating egocentric and allocentric spatial frames of reference. Virtual environments have afforded researchers in the spatial community with ...
Mathieu Simonnet, Dan Jacobson, Stephane Vieillede...
We present a novel data-driven algorithm that leverages online image repositories such as Flickr for automatically generating tourist maps. Our hypothesis is that, given a large e...