TY  - CONF
AU  - Minesh Mathew
AU  - Dimosthenis Karatzas
AU  - C.V. Jawahar
A2  - WACV
PY  - 2021//
TI  - DocVQA: A Dataset for VQA on Document Images
BT  - IEEE Winter Conference on Applications of Computer Vision
SP  - 2200
EP  - 2209
N2  - 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
L1  - http://refbase.cvc.uab.es/files/MKJ2021.pdf
N1  - DAG; 600.121
ID  - Minesh Mathew2021
ER  -