Enabling a domain expert to maintain his own knowledge in a Knowledge Based System has long been an ideal for the Knowledge Engineering community. In this paper we report on our ex...
Many perception and multimedia indexing problems involve datasets that are naturally comprised of multiple streams or modalities for which supervised training data is only sparsely...
Ashish Kapoor, Chris Mario Christoudias, Raquel Ur...
In this paper, we study how estimates of ego-motion based on feature tracking (visual odometry) can be improved using a rough (low accuracy) map of where the observer has been. We...
This paper proposes a new registration algorithm, Covariance Driven Correspondences (CDC), that depends fundamentally on the estimation of uncertainty in point correspondences. Th...
Object recognition accuracy can be improved when information from multiple views is integrated, but information in each view can often be highly redundant. We consider the problem...
Chris Mario Christoudias, Raquel Urtasun, Trevor D...