Abstract. In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class ...
Without a deformation model, monocular 3D shape recovery of deformable surfaces is severly under-constrained. Even when the image information is rich enough, prior knowledge of th...
This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
Abstract. This paper studies the properties and performance of models for estimating local probability distributions which are used as components of larger probabilistic systems â€...
Kristina Toutanova, Mark Mitchell, Christopher D. ...
We apply a constrained Hidden Markov Model architecture to the problem of simultaneous localization and surveying from sensor logs of mobile agents navigating in unknown environmen...