Human knowledge is inherently multi-modal, and it is more than just a collection of isolated pieces of information, independently of the form of expression. Instead, it emerges from the interconnectedness of all of these information fragments. While the means for producing media in various modalities have become more powerful and more broadly accessible, methods to capture the relations between the content present in images, audio and video recording, etc., have so far been rather lacking.
The MediaGraph project aims at addressing this, by extending the concept of Knowledge Graph, which can be used to model the relations between textual or more abstract information, to the various types of multimedia. In contrast to a Knowledge graph whose nodes are associated with a textual label, the nodes in a Media Graph will be able to represent and interrelate any part of any multimedia document. The result will be new ways to represent and interact with multimedia and access the richness of human knowledge contained within.
SNF Ambizione grants are aimed at young researchers who wish to conduct, manage and lead an independent project at a Swiss higher education institution.