In this paper, we propose a novel semi-supervised speaker identification method that can alleviate the influence of nonstationarity such as session dependent variation, the reco...
Dynamic optimization presents opportunities for finding run-time bottlenecks and deploying optimizations in statically compiled programs. In this paper, we discuss our current impl...
Howard Chen, Jiwei Lu, Wei-Chung Hsu, Pen-Chung Ye...
A likelihood formulation for human tracking is presented based upon matching feature statistics on the surface of an articulated 3D body model. A benefit of such a formulation ove...
Timothy J. Roberts, Stephen J. McKenna, Ian W. Ric...
A block based video coder that supports multiple motion models is proposed. Apart from the typical translational motion model, we employ parametric models to more accurately repre...
Haricharan Lakshman, Heiko Schwarz, Thomas Wiegand
We propose a two component method for denoising multidimensional signals, e.g. images. The first component uses a dynamic programing algorithm of complexity O(N log N) to find an ...