Content Classification of Multimedia Documents using Partitions of Low-Level Features

Audio-visual documents obtained from German TV news are classified according to the IPTC topic categorization scheme. To this end usual text classification techniques are adapted to speech, video, and non-speech audio. For each of the three modalities word analogues are generated: sequences of syllables for speech, “video words” based on low level color features (color moments, color correlogram and color wavelet), and “audio words” based on low-level spectral features (spectral envelope and spectral flatness) for non-speech audio. Such audio and video words provide a means to represent the different modalities in a uniform way. The frequencies of the word analogues represent audio-visual documents: the standard bag-of-words approach. Support vector machines are used for supervised classification in a 1 vs. n setting. Classification based on speech outperforms all other single modalities. Combining speech with non-speech audio improves classification. Classification is further improved by supplementing speech and non-speech audio with video words. Optimal F-scores range between 62% and 94% corresponding to 50% - 84% above chance. The optimal combination of modalities depends on the category to be recognized. The construction of audio and video words from low-level features provide a good basis for the integration of speech, non-speech audio and video.

System Architecture of a Mixed Reality Framework

In this paper the software architecture of a framework which simplifies the development of applications in the area of Virtual and Augmented Reality is presented. It is based on VRML/X3D to enable rendering of audio-visual information. We extended our VRML rendering system by a device management system that is based on the concept of a data-flow graph. The aim of the system is to create Mixed Reality (MR) applications simply by plugging together small prefabricated software components, instead of compiling monolithic C++ applications. The flexibility and the advantages of the presented framework are explained on the basis of an exemplary implementation of a classic Augmented Realityapplication and its extension to a collaborative remote expert scenario.

Simbrain: A visual framework for neural network analysis and education

Simbrain is a visually-oriented framework for building and analyzing neural networks. It emphasizes the analysis of networks which control agents embedded in virtual environments, and visualization of the structures which occur in the high dimensional state spaces of these networks. The program was originally intended to facilitate analysis of representational processes in embodied agents, however it is also well suited to teaching neural networks concepts to a broader audience than is traditional for neural networks courses. Simbrain was used to teach a course at a new university, UC Merced, in its inaugural year. Experiences from the course and sample lessons are provided.