This paper presents a probabilistic algorithm for segmenting and recognizing text embedded in video sequences. The algorithm approximates the posterior distribution of segmentatio...
—This paper presents a system-level Network-on-Chip modeling framework that integrates transaction-level model and analytical wire model for design space exploration. It enables ...
This paper presents a spatiotemporal pyramid representation for recognizing facial expressions and hand gestures. This approach works by partitioning video sequence into increasin...
We present a component-based description language for heterogeneous systems composed of several data flow processing components and a unique eventbased controller. Descriptions a...
Abstract. The location of video scenes is an important semantic descriptor especially for broadcast news video. In this paper, we propose a learning-based approach to annotate shot...