A survey on social image understanding

Abstract

Over the past twenty years, the computer vision and natural language processing groups have achieved great success in their respective fields. But their communities have rarely interacted. Recently, automatic image description generation has gathered a lot of attention in computer vision and natural language processing communities. The automatic image description generation associates computer vision with natural language processing. In the last five years, a large of literatures about image description generation have appeared. In this survey, we give a comprehensive overview of approaches and datasets used for image description generation that exist in the literatures.