We define Computational Media Aesthetics as the algorithmic study of a number of image and aural elements in media and the computational analysis of the principles that have emerged underlying their use and manipulation, individually or jointly, in the creative art of clarifying, intensifying, and interpreting some event for the audience.

The current level of processing, storage and transmission technologies have made possible the creation, duplication and sharing of vast amounts of multimedia data, leaving current indexing, retrieval and browsing technologies lost in the sea of it. The lab aims to research the technologies that are necessary to giving this data a usefulness commensurate with its size, and we take our starting point to be the semantic grid through which this content is brought into being. That is, to interpret the data with validity, we must approach it with its maker's eye.