XRCE's Participation in Wikipedia Retrieval, Medical Image Modality Classification and Ad-hoc Retrieval Tasks of ImageCLEF 2010

This year, XRCE participated in three main tasks of ImageCLEF 2010. The Visual Concept Detection and Annotation Task is presented in a separate paper. In this working note, we rather focus on our participation in the Wikipedia Retrieval Task and in two sub-tasks of the Medical Retrieval Task (Image Modality Classification and Ad-hoc Image Retrieval). We investigated mono-modal (textual and visual) and multi-modal retrieval and classification systems. For representing text we used either standard language model or a power law (log-logistic or smoothed power law) distribution-based information retrieval model. For representing images, we used Fisher Vectors improved by power and L2 normalizations and a spatial pyramid representation. With theses representations and simple linear classifiers we achieved excellent image modality classification both using mono-modal and combined textual and visual information. Concerning the retrieval performances, text based runs performed very well, but visual-only retrieval performances were in general poor showing that even state-of-the art image representations are insufficient to address these tasks accurately. However, we have shown that despite poor visual retrieval results, multimodal runs that combine both visual and textual retrieval scores, can outperform mono-modal systems as long as the information fusion is done appropriately. As a conclusion we can say that our participation in these tasks was successful, as the proposed systems obtained leading positions both in retrieval and modality classification and for each type of run: text, image or mixed.