We present spatio-temporal feature descriptors that can be inferred from video and used as building blocks in action recognition systems. They capture the evolution of ``elementar...
A number of recent technological trends have made data intensive applications such as continuous media (audio and video) servers a reality. These servers store and retrieve a larg...
We have extended the ACL2 theorem prover to automatically prove properties of VHDL circuits with IBM's Internal SixthSense verification system. We have used this extension to...
The idea behind Aspect-Oriented Modeling (AOM) is to apply aspect-oriented techniques to (software) models with the aim of modularizing crosscutting concerns. This can be done with...
This work presents an agenda-based approach to improve the robustness of the dialog manager by using dialog examples and n-best recognition hypotheses. This approach supports n-be...