Computational models of visual attention result in considerable data compression by eliminating processing on regions likely to be devoid of meaningful content. While saliency map...
Abstract— A fully-distributed collaborative multi-target tracking framework that eliminates the need for a central data associator or a central coordinating node for wireless sen...
Abstract. Dimensionality reduction is an essential aspect of visual processing. Traditionally, linear dimensionality reduction techniques such as principle components analysis have...
This paper presents a spatiotemporal pyramid representation for recognizing facial expressions and hand gestures. This approach works by partitioning video sequence into increasin...
This paper presents an approach for human activity recognition by representing the frames of the video sequence with the distribution of local motion features and their spatiotemp...