Image tag clarity

Abstract

Tags associated with images in various social media sharing web sites are valuable information source for superior image retrieval experiences. Due to the nature of tagging, many tags associated with images are not visually descriptive. In this paper, we propose Normalized Image Tag Clarity (NITC) to evaluate the effectiveness of a tag in describing the visual content of its annotated images. It is measured by computing the zero-mean normalized distance between the tag language model estimated from the images annotated by the tag and the collection language model. The visual-representative tags that are commonly used to annotate visually similar images are given high tag clarity scores. Evaluated on a large real-world dataset containing more than 269K images and their associated tags, we show that NITC score can effectively identify the visual-representative tags from all tags contributed by users. We also demonstrate through experiments that most popular tags are indeed visually representative.