Semantic Media Retrieval is about the search of knowledge from multimedia data sources. In our research group we focus the attention to images and videos.

People describe their life experience using words, that is a representation that could have many differences, when we consider different persons, due to the users’ knowledge and experience and because of the context.
This represent a “semantic gap” between the conceptualizations of the world expressed using language, and the experience of the world, whose most direct representations are photos and media in general.
Due to this, current media understanding systems are still very much example-driven (e.g., find photos similar to a given one on the basis of a set of features).

Whatever they are everyday personal experiences (e.g., a wedding or a birthday party) or large social happenings (e.g., a concert or a sport event), events mark our lives and memories. Recent studies demonstrate that users find it easier to navigate and search through such huge multimedia galleries if the data are grouped into events.
Moreover, events are more and more associated to massive quantities of media: photos, videos, audio recordings, tweets, web pages, etc. For this reason it is fundamental to properly organize such big collection of data, in order to allow easy access to them also in the future.

The massive quantities of media available in everyday life, make the processing of these data, via innovative multimedia content-and-context-based search engines, a challenging task. In this framework, the interaction with the user together with the exploitation of a-priori knowledge are combined in order to bridge the gap between the current multimedia understanding algorithms and the richness and subjectivity of semantics in human interpretations of multimedia data.