Combining text/image in WikipediaMM task

Abstract. This paper reports our multimedia information retrieval ex-periments carried out for the ImageCLEF track 2009. In 2008, we pro-posed a multimedia document model defined as a vector of textual and visual terms weighted using a tf.idf approch [5]. For our second partic-ipation, our goal was to improve this previous model in the following ways: 1) use of additional information for the textual part (legend and image bounding text extracted from the original documents, 2) use of different image detectors and descriptors, 3) new text / image combina-tion approach. Results allow to evaluate the benefits of these different improvements.