Model-based recognition of an object typically involves matching dense 3D range data. The computational cost is directly affected by the amount of data of which a transformation n...
The conditional phrase translation probabilities constitute the principal components of phrase-based machine translation systems. These probabilities are estimated using a heurist...
Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
: This paper discusses the user-centered location model used in comMotion. In this context, the location model refers to a set of learned places (destinations), which coincide to a...
This paper presents an approach for view-based recognition of gestures. The approach is based on representing each gesture as a sequence of learned body poses. The gestures are re...
Ahmed M. Elgammal, Vhay Shet, Yaser Yacoob, Larry ...