We describe a method for learning classes of facial motion patterns from video of a human interacting with a computerized embodied agent. The method also learns correlations betwe...
This paper describes Kinematics: a novel construction toy for children consisting of both active (shape-changing or rotating) and passive building blocks. In comparison to similar...
Leonhard Oschuetz, Daniel Wessolek, Wolfgang Sattl...
In this paper, we propose a novel graph embedding method for the problem of lipreading. To characterize the temporal connections among video frames of the same utterance, a new di...
Abstract— Situated agents engaged in open systems continually face with external events requiring adequate services and behavioral responses. In these conditions agents should be...
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...