High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
Providing route directions is a complicated interaction. Utterances are combined with gestures and pronounced with appropriate timing. This study proposes a model for a robot that...
Recent advances have brought real-time physically based simulation within reach, but simulations are still difficult to control in real time. We present interactive simulations of...
Recently proposed novel interaction techniques such as cursor jumping [1] and target expansion for tiled arrangements [13] are predicated on an ability to effectively estimate the...
We present a new framework to represent and analyze dynamic facial motions using a decomposable generative model. In this paper, we consider facial expressions which lie on a one d...