Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
We propose an infotainment presentation system that relies on eye gaze as an intuitive and unobtrusive input modality. The system analyzes eye movements in real-time to infer user...
Helmut Prendinger, Tobias Eichner, Elisabeth Andr&...
: Sentient Computing gives perception to computing systems so that they can detect, interpret and respond to changing aspects of users' context. The location attribute of a us...
Abstract--We present a new technique for audio signal comparison based on tonal subsequence alignment and its application to detect cover versions (i.e., different performances of ...
—We present a novel convex programming scheme to solve matching problems, focusing on the challenging problem of matching in a large search range and with cluttered background. M...