Learning Visual Contexts for Image Annotation from Flickr GroupsAdrian Ulges; Marcel Worring; Thomas Breuel
In: Sheila S. Hemami (Hrsg.). IEEE Transactions on Multimedia (TransMM), Vol. 13, No. 3, Pages 1-12, IEEE Computer Society, 4/2011.
We present an extension of automatic image annotation that takes the context of a picture into account. Our core assumption is that users do not only provide individual images to be tagged, but group their pictures into batches (e.g., all snapshots taken over the same holiday trip), whereas the images within a batch are likely to have a common style. These batches are matched with categories learned from Flickr groups, and an accurate context-specific annotation is performed. In quantitative experiments, we demonstrate that Flickr groups, with their user-driven categorization and their rich group space, provide an excellent basis for learning context categories. Our approach -- which can be integrated with virtually any annotation model -- is demonstrated to give significant improvements of above 100%, compared to standard annotations of individual images.