When classifying high-dimensional sequence data, traditional methods (e.g., HMMs, CRFs) may require large amounts of training data to avoid overfitting. In such cases dimensional...
We propose a principled framework to model persistent motion in dynamic scenes. In contrast to previous efforts on object tracking and optical flow estimation that focus on local...
We introduce Xampling, a design methodology for analog compressed sensing in which we sample analog bandlimited signals at rates far lower than Nyquist, without loss of informatio...
Current video coding schemes employ motion compensation to exploit the fact that the signal forms an auto-regressive process along the motion trajectory, and remove temporal redun...
This paper presents the case of Arinia, a custommade piece of social software with strong similarities to today’s microblogging applications. Arinia has been in use in a medium-...