— In this paper, we introduce an approach to active camera control for visual SLAM. Features, detected by a biologically motivated attention system, are tracked over several fram...
Semantic concepts cement the ability to correlate visual information to higher-level semantic concepts. Traditional image search leverages text associated with images, a lowlevel ...
Eric Zavesky, Zhu Liu, David C. Gibbon, Behzad Sha...
We consider the problem of vision-based position estimation in urban environments. In particular, we are interested in position estimation from visual cues, but using only limited...
We consider the problem of learning to map between two vector spaces given pairs of matching vectors, one from each space. This problem naturally arises in numerous vision problem...
In this paper we propose to achieve a semantic equivalence between a visual- and a script-based workflow development paradigm. We accomplish this by building a script language whi...