Natural scene images coming usually from lowresolution sensors in embedded context suffer from low text recognition results. Due to several types of degradations, existing algorit...
This paper addresses the problem of recognizing freeform 3D objects in point clouds. Compared to traditional approaches based on point descriptors, which depend on local informati...
Bertram Drost, Markus Ulrich, Nassir Navab, Slobod...
Spoken language interfaces based on interactive semantic language models [16, 14] allow probabilities for hypothesized words to be conditioned on the semantic interpretation of th...
Lane Schwartz, Luan Nguyen, Andrew Exley, William ...
Abstract. The paper presents an implemented model for priming speech recognition, using contextual information about salient entities. The underlying hypothesis is that, in human-r...
Colour cues were used to obtain robust detection and tracking of people in relatively unconstrained dynamic scenes. Gaussian mixture models were used to estimate probability densi...