MIL at ImageCLEF 2013: Scalable System for Image Annotation

We give details of our methods in the ImageCLEF 2013 Scalable Concept Image Annotation task. For the textual feature, we propose a method for selecting text closely related to an image from its webpage. In addition, to consider the meaning of the concept, we propose to use WordNet for getting words related to the concept. For visual features, we use Fisher Vector (FV), which is regarded as an extension of the Bagof-Visual-Words representation. We trained linear classifiers by Passive– Aggressive with Averaged Pairwise Loss (PAAPL), an online multilabel learning method based on Passive–Aggressive. Since PAAPL is computationally efficient and able to cope with multilabel data appropriately, it is suitable for this task. Results show that our annotation pipeline is simple but works well in this task.