While traditional content-based retrieval approaches provide query-driven access under the assumption that the users' needs are clearly specified, modern content-based exploration approaches support users in browsing and navigating through multimedia databases when imprecise or even no retrieval intent is given. By means of interactive graphical user interfaces, exploration approaches offer a convenient and intuitive access to unknown multimedia databases which becomes even more important with the arrival of powerful mobile devices, such as the iPad and iPhone.
Because interactivity of the multimedia exploration process turns in massive triggering of similarity queries, their efficient implementation is one of the key requirements. Moreover, during the exploration process the evolving user preferences could arbitrarily change the underlying similarity measures, so the implementation should cope with dynamic (and possibly non-metric) distance functions. To develop a successful exploration access method, SRG aims to investigate novel adaptive indexing methods supporting near-realtime query processing