Learn More
1. INTRODUCTION Recording live lectures has proven to be a fast and efficient way of creating content for e-learning (Lauer & Ottmann, 2002). This content can be used in a number of ways ranging from simply augmenting a lecture to profoundly changing its didactic setting. See (Mertens et al., 2004 a) for an overview. A number of application scenarios aim(More)
Vector graphics are an ideal content format for slide based lecture recordings. File sizes can be kept small and graphics can be displayed in superior quality. Information about text and slide objects is stored symbolically which allows texts to be searched and objects on slides to be used interactively, e.g. for navigation purposes. The use of vector(More)
Lecture recordings can be a powerful addition to traditional lectures and they can even serve as a main content source in a number of didactic scenarios. If users can quickly locate relevant passages in a recording, the recording combines the ease of search that comes with electronic text based media with the authenticity and wealth of information that is(More)
This paper presents a system that uses symbolic representations of audio concepts as words for the descriptions of audio tracks, that enable it to go beyond the state of the art, which is audio event classification of a small number of audio classes in constrained settings, to large-scale classification in the wild. These audio words might be less(More)
—Recently, audio concepts emerged as a useful building block in multimodal video retrieval systems. Information like " this file contains laughter " , " this file contains engine sounds " or " this file contains slow music " can significantly improve purely visual based retrieval. The weak point of current approaches to audio concept detection is that they(More)