Virtual Reality Multimedia Analytics: An interactive approach to large-scale multimedia analysis in a virtual environment

ended

While the popular press often depicts a future where white collar jobs have been taken over by artificial intelligence, evidence suggests it is far more likely that many jobs will require non-IT specialists to analyse, in real-time, huge volumes of complex data with the help of a computer. Media files make up a large portion of these data volumes, and already today our personal and professional lives are full of large digital media collections (e.g. Netflix, Google, YouTube, etc.) that must be interactively explored, analysed, understood, annotated, and used. The research described in this proposal seeks to address this trend by designing and evaluating a large-scale interactive multimedia analytics prototype designed for a rapidly emerging new mode of visual access, namely virtual reality. Platforms supporting virtual reality provide unparalleled immersion and can afford the ability to submerge their users into an environment where visual analysis can occur in three spatial dimensions and six degrees of freedom. In this proposal we discuss our hypothesis that by combining the state-of-the-art in scalable multimedia analytics with a highly interactive access mechanism such as virtual reality, it will enable the development of pioneering applications to support unprecedented analysis of large-scale multimedia datasets. The research proposed in this application aims to significantly extend the state of the art in this domain by addressing a confluence of three major trends in computing: interactive analysis, novel access mechanisms, and collection scale.