DocVQA

Measures: Extractive questions about single scanned document pages (forms, letters, reports, figures); answers scored by ANLS (Average Normalized Levenshtein Similarity) on a hidden test set.

Maintainer: DocVQA organizers: CVC-UAB (Computer Vision Center, Barcelona) and CVIT, IIIT Hyderabad
Introduced: 2020
Status: Active
Saturation: Saturated
Typical provenance: Mixed
In scoring set: No

Paper Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.