Automatic Generation of Grounded Visual Questions
This addresses the lack of automatic methods for generating varied question types in visual question generation, which is incremental as it builds on existing captioning models.
The paper tackles the problem of automatically generating diverse and meaningful visually grounded questions for a single image, proposing a model that outperforms baselines in correctness and diversity on two real-world datasets.
In this paper, we propose the first model to be able to generate visually grounded questions with diverse types for a single image. Visual question generation is an emerging topic which aims to ask questions in natural language based on visual input. To the best of our knowledge, it lacks automatic methods to generate meaningful questions with various types for the same visual input. To circumvent the problem, we propose a model that automatically generates visually grounded questions with varying types. Our model takes as input both images and the captions generated by a dense caption model, samples the most probable question types, and generates the questions in sequel. The experimental results on two real world datasets show that our model outperforms the strongest baseline in terms of both correctness and diversity with a wide margin.