Recent approaches to action classification in videos have used sparse spatio-temporal words encoding local appearance around interesting movements. Most of these approaches use a ...
Recently, mining data streams with concept drifts for actionable insights has become an important and challenging task for a wide range of applications including credit card fraud...
Context trees are a popular and effective tool for tasks such as compression, sequential prediction, and language modeling. We present an algebraic perspective of context trees for...
Harald Ganzinger, Robert Nieuwenhuis, Pilar Nivela
Classification of images in many category datasets has
rapidly improved in recent years. However, systems that
perform well on particular datasets typically have one or
more lim...
We present CThru, a self-guided video-based educational environment in a large multi-display setting. We employ a video-centered approach, creating and combining multimedia conten...
Hao Jiang, Alain Viel, Meekal Bajaj, Robert A. Lue...