We present an unsupervised technique for detecting unusual activity in a large video set using many simple features. No complex activity models and no supervised feature selection...
This paper describes a methodology for synthesizing the data-path of a Very Long Instruction Word (VLIW) based Video Signal Processor (VSP). Offering both performance and programm...
Abstract. Multi-view video is a new video application requiring efficient coding algorithm to compress the huge data, while the color variations among different viewpoints deterior...
Disease-specific understanding of echocardiographic sequences requires accurate characterization of spatio-temporal motion patterns. In this paper we present a method of automatic ...
Tanveer Fathima Syeda-Mahmood, Fei Wang, David Bey...
In this paper we present a clustering-based method for representing semantic concepts on multimodal low-level feature spaces and study the evaluation of the goodness of such model...