This paper presents a principled and practical method for the computation of visual saliency of spatiotemporal events in full motion videos. Based on the assumption that uniquenes...
With the exponential growth of Web 2.0 applications, tags have been used extensively to describe the image contents on the Web. Due to the noisy and sparse nature in the human gene...
Almost all medium- and large-scale businesses rely on electronic workflow systems to manage their business processes. A key challenge is to enable the easy re-use and modification...
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 novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...