Visual Question Generation

Abstract

Visual question generation (VQG) is an interesting problem that has recently received attention. The task of VQG involves generating meaningful questions based on the input image. It is a multi-modal problem involving image understanding and natural language generation, especially using deep learning methods. VQG can be considered as complementary task of visual question answering. In this article, we review the current state of VQG in terms of methods to understand the problem, existing datasets to train the VQG model, evaluation metrics, and algorithms to handle the problem. Finally, we discuss the challenges that need to be conquered and the possible future directions for an effective VQG.