This article presents two methods for the automatic detection of social events that were evaluated on the annotated set of pictures as part of the 2011 Mediaeval benchmark [1]. The first method uses a set of web pages and a semantic space obtained by Latent Dirichelet Allocation (LDA, [2, 3]) to classify pictures from Flickr. The second approach uses the query to extract a subset of pictures and classify this subset. Theses approches are compared in the experimental framework of Mediaeval 2011 Social Event Detection task .