InfographicVQA
This work addresses the challenge of interpreting complex infographics for applications in document analysis and visual question answering, though it is incremental as it primarily introduces a dataset.
The authors tackled the problem of automatically understanding infographics by introducing InfographicVQA, a new dataset with natural language questions and answers that require reasoning over layout, text, graphics, and visualizations, and they established baseline performance using state-of-the-art multi-modal VQA models.
Infographics are documents designed to effectively communicate information using a combination of textual, graphical and visual elements. In this work, we explore the automatic understanding of infographic images by using Visual Question Answering technique.To this end, we present InfographicVQA, a new dataset that comprises a diverse collection of infographics along with natural language questions and answers annotations. The collected questions require methods to jointly reason over the document layout, textual content, graphical elements, and data visualizations. We curate the dataset with emphasis on questions that require elementary reasoning and basic arithmetic skills. Finally, we evaluate two strong baselines based on state of the art multi-modal VQA models, and establish baseline performance for the new task. The dataset, code and leaderboard will be made available at http://docvqa.org