Vision Skills Needed to Answer Visual Questions
Authors:
Open Access
- 14 October 2020
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 4 (CSCW2) , 1-31
Abstract
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.Keywords
All Related Versions
Funding Information
- National Science Foundation (IIS-1755593)
- Microsoft
This publication has 35 references indexed in Scilit:
- CrowdVerge2017
- Revisiting Visual Question Answering Baselines2016
- Answer-Type Prediction for Visual Question Answering2016
- Deep Residual Learning for Image Recognition2016
- Stacked Attention Networks for Image Question Answering2016
- VQA: Visual Question Answering2015
- Visual Turing test for computer vision systemsProceedings of the National Academy of Sciences, 2015
- Microsoft COCO: Common Objects in Context2014
- Zero-Shot Learning via Visual Abstraction2014
- The Word Tree, an Interactive Visual ConcordanceIEEE Transactions on Visualization and Computer Graphics, 2008