The volume of multimedia content is increasing at a fast space due to the widespread availability of portable devices for the acquisition of images and videos, and the availability of large space for its storage through Internet. Consequently, there is the need for advanced tools for managing such a large volume of data in terms of automatic content classification techniques for the efficient retrieval of multimedia content related to a specific concept.
These content are often shared through web sites such as social networks, and they are often described by low-quality tags. Interactive retrieval systems are based instead on querying by example provided by the user. Through specific similarity measures the systems retrieve the documents in the database that are more similar to those desired by the user. These systems are also able to refine iteratively the search by following the instructions provided by the user on which documents are relevant to the example initially supplied.