Most existing techniques for analyzing face images assume that the faces are at near-frontal poses. Generalizing to non-frontal faces is often difficult, due to a dearth of groun...
We present algorithms for automatic feature selection for unsupervised structure discovery from video sequences. Feature selection in this scenario is hard because of the absence ...
We propose a new model for the probabilistic estimation of continuous state variables from a sequence of observations, such as tracking the position of an object in video. This ma...
We propose a new method for human action recognition from video sequences using latent topic models. Video sequences are represented by a novel “bag-of-words” representation, w...
In this paper, we study how estimates of ego-motion based on feature tracking (visual odometry) can be improved using a rough (low accuracy) map of where the observer has been. We...