In this paper, we present a method for human action recognition from multi-view image sequences that uses the combined motion and shape flow information with variability considera...
In this paper we show that efficient object recognition can be obtained by combining informative features with linear classification. The results demonstrate the superiority of in...
There are many applications where multiple data sources, each with its own features, are integrated in order to perform an inference task in an optimal way. Researchers have shown...
In this work we present an approach to capture the total semantics in multimedia-multimodal web pages. Our research improves upon the state-ofthe-art with two key features: (1) cap...
Abstract. We present a markerless real-time, model-based 3D face tracking methodology. The system combines two robust and complimentary optimization-based strategies, namely active...