DocVQA: A Dataset for VQA on Document Images
arXiv:2007.00398
Abstract
We present a new dataset for Visual Question Answering (VQA) on document images called DocVQA. The dataset consists of 50,000 questions defined on 12,000+ document images. Detailed analysis of the dataset in comparison with similar datasets for VQA and reading comprehension is presented. We report several baseline results by adopting existing VQA and reading comprehension models. Although the existing models perform reasonably well on certain types of questions, there is large performance gap compared to human performance (94.36% accuracy). The models need to improve specifically on questions where understanding structure of the document is crucial. The dataset, code and leaderboard are available at docvqa.org
arXiv commentaccepted at WACV 2021
References in corpus (12)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Deep Residual Learning for Image Recognition
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- FigureQA: An Annotated Figure Dataset for Visual Reasoning
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
- NewsQA: A Machine Comprehension Dataset
- C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset
- DVQA: Understanding Data Visualizations via Question Answering
- Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text
- On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering