Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single...
Recent works in object recognition often use visual words, i.e. vector quantized local descriptors extracted from the images. In this paper we present a novel method to build such ...
In many image retrieval applications, the mapping between highlevel semantic concept and low-level features is obtained through a learning process. Traditional approaches often as...
Human motion can be seen as a type of texture pattern. In this paper, we adopt the ideas of spatiotemporal analysis and the use of local features for motion description. movements...
This paper presents an efficient and homogeneous paradigm for automatic acquisition and recognition of nonparametric shapes. Acquisition time varies from linear to cubic in the nu...