Tagrank - Measuring tag importance for image annotation

Traditional image annotation approaches are only applicable for datasets with small and limited lexicon. Besides, annotation words are treated equally without considering the importance of each word in the real world. To address these problems, we propose TagRank, a method to model the relative importance of every candidate word. By exploiting tag clusters on Flickr, TagRank could be modeled as random walk with restarts, which incorporates both word frequency and word correlation information. As a result, a ranked annotation vocabulary could be built. By utilizing the tag importance in a real image annotation experiment, we show that TagRank is helpful for improving the performance of image annotation.