With the increasing amount of available multimedia data, it has become more and more important to be able to automatically analyze multimedia content and retrieve it according to the user's wishes. There are many technologies involved in such a task. First of all, the content of the multimedia data should be represented in a suitable way to facilitate successful retrieval. This requires the use of audio-visual and text analysis tools to derive descriptions of the multimedia data. Afterwards, the search can be conducted either in a fully automatic way or in an interactive way by adding the user to the decision loop.
As a member of the Franco-German project Quaero, we are working on visual and multimodal analysis of multimedia content. Here, our contributions include detection, localization and identification of people in multimedia content, as well as multimodal recognition of high-level features, genres and events.
You can find more information on our research in person identification and multimedia analysis on our project page.