Information to be updated!
Information fusion for social image retrieval and diversification. Reuses the publicly available datasets issued from the 2013-2016 MediaEval Retrieving Diverse Social Images Tasks (i.e., Div400, Div150Cred, Div150Multi, and Div150Adhoc), together with the participant runs. These data consist of hundreds of Flickr image query results (>500 queries, both single- and multi- topic) and include: images (up to 300 images per query), social metadata (e.g., description, number of comments, tags, etc.), descriptors for visual, text, social information (e.g. user tagging credibility), as well as deep learning features, expert annotations for image relevance and diversification (i.e. clustering of images according to the similarity of their content). An example is presented in Table 1. The data will be accompanied by 180 participant runs which correspond to the output of image search retrieval diversification techniques (each run contains the diversification of each query from a dataset). These would allow to experiment with various fusion strategies.