The interactive join

Direct, ad-hoc interaction with databases has typically been performed over console-oriented conversational interfaces using query languages such as SQL. With the rise in popularity of gestural user interfaces and computing devices that use gestures as their exclusive mode of interaction, database query interfaces require a fundamental rethinking to work without keyboards. Unlike domain-specific applications, the scope of possible actions is significantly larger if not infinite. Thus, the recognition of gestures and their consequent queries is a challenge. We present a novel gesture recognition system that uses both the interaction and the state of the database to classify gestural input into relational database queries. Preliminary results show that using this approach allows for fast, efficient and interactive gesture-based querying over relational databases.