Vision Skills Needed to Answer Visual Questions
This work addresses the gap between real-world user needs and AI research focus in visual question answering, with implications for assisting visually impaired populations.
The paper analyzed the vision skills required for visual question answering across two datasets, identifying object, text, color recognition, and counting as key skills, and quantified their difficulty for humans and computers.
The task of answering questions about images has garnered attention as a practical service for assisting populations with visual impairments as well as a visual Turing test for the artificial intelligence community. Our first aim is to identify the common vision skills needed for both scenarios. To do so, we analyze the need for four vision skills---object recognition, text recognition, color recognition, and counting---on over 27,000 visual questions from two datasets representing both scenarios. We next quantify the difficulty of these skills for both humans and computers on both datasets. Finally, we propose a novel task of predicting what vision skills are needed to answer a question about an image. Our results reveal (mis)matches between aims of real users of such services and the focus of the AI community. We conclude with a discussion about future directions for addressing the visual question answering task.