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...
Video-based human recognition at a distance remains a challenging problem for the fusion of multimodal biometrics. As compared to the approach based on match score level fusion, i...
Background: The ability to distinguish between genes and proteins is essential for understanding biological text. Support Vector Machines (SVMs) have been proven to be very effici...
Tapio Pahikkala, Filip Ginter, Jorma Boberg, Jouni...
In this paper, we present a complete system for automatic face replacement in images. Our system uses a large library of face images created automatically by downloading images fr...
Dmitri Bitouk, Neeraj Kumar, Samreen Dhillon, Pete...
The World Wide Web is becoming increasingly important in the provision of education, as recognised by several high profile UK government reports. Improved tools for developing We...