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 ...
We present a new machine learning framework called "self-taught learning" for using unlabeled data in supervised classification tasks. We do not assume that the unlabele...
Rajat Raina, Alexis Battle, Honglak Lee, Benjamin ...
Surface data such as the segmented cortical surface of the human brain plays an important role in medical imaging. To increase the signal-to-noise ratio for data residing on the b...
In this paper we explore the interlink between temporally dense view-based object recognition and sparse image representations with local keypoints. The temporal component is an a...
We investigate dynamical models of human motion that can
support both synthesis and analysis tasks. Unlike coarser
discriminative models that work well when action classes are ...