In this paper, a framework that combines feature extraction, model learning, and likelihood computation, is presented for video event detection. First, the independent component a...
Effective mode-switching techniques provide users of tablet interfaces with access to a rich set of behaviors. While many researchers have studied the relative performance of mode...
We combine Bayesian online change point detection with Gaussian processes to create a nonparametric time series model which can handle change points. The model can be used to loca...
This paper presents a dynamic conditional random field (DCRF) model to integrate contextual constraints for object segmentation in image sequences. Spatial and temporal dependenci...
This paper presents motion field histograms as a new way of extracting facial features and modeling expressions. Feature are based on local receptive field histograms, which are r...