What license is DocVQA: A Dataset for VQA on Document Images under?

DocVQA: A Dataset for VQA on Document Images is available under mit.

DocVQA: A Dataset for VQA on Document Images

Active

DocVQA is a Visual Question Answering benchmark that consists of 50,000 questions covering 12,000+ document images. This implementation solves and scores the "validation" split.

Open

Publisher: Computer Vision Center (CVC) at UAB
Domain: Multimodal
License: mit
Published: Nov 2024
Notable for: Benchmark for evaluating Multimodal.
Canonical: github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/docvqa

Cite

Notes

Only stored in your browser.

Attribution

README: github.com/UKGovernmentBEIS/inspect_evals/blob/main/src/inspect_evals/docvqa/eval.yamlMIT

Attribution policy →

FAQ

What is DocVQA: A Dataset for VQA on Document Images?: DocVQA is a Visual Question Answering benchmark that consists of 50,000 questions covering 12,000+ document images. This implementation solves and scores the "validation" split.
What license is DocVQA: A Dataset for VQA on Document Images under?: DocVQA: A Dataset for VQA on Document Images is available under mit.