Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
Social media websites promote diverse user interaction on media objects as well as user actions with respect to other users. The goal of this work is to discover community structu...
Yu-Ru Lin, Jimeng Sun, Paul Castro, Ravi B. Konuru...
We introduce a method for predicting a control signal from another related signal, and apply it to voice puppetry: Generating full facial animation from expressive information in ...
To ensure the consistency of database subsystems involved in wireless communication systems, appropriate scheduled maintenance policies are necessary. However, the short-persisten...
Amine Chohra, Felicita Di Giandomenico, Stefano Po...
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
Michael L. Littman, Richard S. Sutton, Satinder P....