Document Visual Question Answering Challenge 2020
This addresses the problem of automated document understanding for researchers and practitioners in computer vision and document analysis, but it is incremental as it builds on existing VQA concepts applied to documents.
The paper introduced the Document Visual Question Answering Challenge, tackling the problem of visual question answering on document images by organizing two tasks: single-image QA and retrieval over collections, and created new datasets including 50,000 QA pairs for task 1 and 20 questions over 14,362 images for task 2.
This paper presents results of Document Visual Question Answering Challenge organized as part of "Text and Documents in the Deep Learning Era" workshop, in CVPR 2020. The challenge introduces a new problem - Visual Question Answering on document images. The challenge comprised two tasks. The first task concerns with asking questions on a single document image. On the other hand, the second task is set as a retrieval task where the question is posed over a collection of images. For the task 1 a new dataset is introduced comprising 50,000 questions-answer(s) pairs defined over 12,767 document images. For task 2 another dataset has been created comprising 20 questions over 14,362 document images which share the same document template.