Many previous studies have investigated gender classification in well-lit frontal images. In this paper we consider images where the pose, expression and lighting are relatively u...
We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled f...
Geographic information retrieval (GIR) is, as a branch of traditional information retrieval, a discipline that tries to enrich data with geographical information to make it suitab...
This paper presents a novel discriminative learning method, called Manifold Discriminant Analysis (MDA), to solve the problem of image set classification. By modeling each image s...
Audio segmentation is an essential preprocessing step in several audio processing applications with a significant impact e.g. on speech recognition performance. We introduce a no...