Alabama won ugly in Athens with absurd third-down efficiency and just enough clock management to pull off the upset.

Abstract: Machine Learning models for chart-grounded Q&A (CQA) often treat charts as images, but performing CQA on pixel values has proven challenging. We thus investigate a resource overlooked by ...

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Can the users of financial statements and annual reports rely upon the charts in them for accuracy? A sample of 50 public companies’ yearly reports collected by the author found that 86% had at least ...

Abstract: This article presents a systematic study of the generalization of convolutional neural networks (CNNs) and humans on relational reasoning tasks with bar charts. We first revisit previous ...