This paper presents a bottom-up approach that combines audio and video to simultaneously locate individual speakers in the video (2-D source localization) and segment their speech ...
Suppose we have a large table T of items i, each with a weight wi, e.g., people and their salary. In a general preprocessing step for estimating arbitrary subset sums, we assign e...
Noga Alon, Nick G. Duffield, Carsten Lund, Mikkel ...
This article presents a new adaptive framework for locally parallel texture modeling. Oscillating patterns are modeled with functionals that constrain the local Fourier decompositi...
This paper treats tracking as a foreground/background classification problem and proposes an online semisupervised learning framework. Initialized with a small number of labeled ...
This paper presents a spatiotemporal pyramid representation for recognizing facial expressions and hand gestures. This approach works by partitioning video sequence into increasin...