SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.00398 · 2020

DocVQA: A Dataset for VQA on Document Images

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
anisha2102/docvqa pwc_unofficial 4 of 6
FunctionStatusWhere it lives
to_list Ran anisha2102/docvqa/run_docvqa.py
code served (permissive licence) · get_code("9df40357afea56cc")
bbox_string Ran anisha2102/docvqa/create_dataset.py
code served (permissive licence) · get_code("33893096d0c88812")
clean_text Ran anisha2102/docvqa/create_dataset.py
code served (permissive licence) · get_code("58efca4ff69d4f1c")
convert_to_unicode Ran anisha2102/docvqa/tokenization.py
code served (permissive licence) · get_code("1923fc05163d207d")
load_vocab Not yet run anisha2102/docvqa/tokenization.py
code served (permissive licence) · get_code("ff83ccc8b0b6462d")
printable_text Not yet run anisha2102/docvqa/tokenization.py
code served (permissive licence) · get_code("0e5615f8994003cf")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.00398")
get_code_for_paper("2007.00398")
have("2007.00398")

Connect an agent — have() is free.