The overall objective of the project is to develop a formal theory of multimedia information retrieval and to evaluate it by running experiments on realistic document bases. This theory will be the theoretical foundation of information systems supporting the retrieval of multimedia documents on the basis of their structure and content. A new retrieval model which will embody the above theory is the main aim of the project.
APPROACH AND METHODS
The project will follow a logico-probabilistic approach. Four orthogonal research directions will be explored: the logical, the probabilistic, the computational and the multimedia directions. At the logical level, the project will identify a suitable logic, or family of logics, for reasoning on the structure and the content of multimedia documents. At the probabilistic level, the project will apply the theory of probability to endow the logic with the treatment of uncertainty. At the computational level, the properties of the logic(s) and uncertainty treatment will be studied and, where possible, parallel and probabilistic algorithms to improve the performance of retrieval will be developed. At the multimedia level, different types of multimedia data will be investigated in order to understand the representational and inference mechanisms necessary to perform effective retrieval. Finally, an appropriate evaluation methodology for multimedia document retrieval systems based on the above mentioned theoretical principles will be defined and experimented.
It is expected that the multimedia information theory will have a significant impact both on the industrial world and the scientific community. As far as the former is concerned, it will allow the development of the technology supporting the construction of a new generation of multimedia document retrieval. As far as the latter is concerned, it is believed that the theory will contribute significantly to the definition of a well-founded framework for research in multimedia information retrieval.