Detecting and segmenting moving objects in dynamic scenes is a hard but essential task in a number of applications such as surveillance. Most existing methods only give good resul...
In this work, we systematically study the problem of event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which video clip s...
—This paper presents NetViewer, a network measurement approach that can simultaneously detect, identify and visualize attacks and anomalous traffic in real-time by passively moni...
The frequent and large-scale network attacks have led to an increased need for developing techniques for analyzing network traffic. This paper presents NetViewer, a network measure...
Sign language recognition constitutes a challenging field of research in computer vision. Common problems like overlap, ambiguities, and minimal pairs occur frequently and require...