Document AI (Microsoft Research Asia) (original) (raw)

• Overview
• Repositories
• Projects
• Packages
• People

Pinned Loading

1. TableBank: A Benchmark Dataset for Table Detection and Recognition
   1.1k 146
2. DocBank: A Benchmark Dataset for Document Layout Analysis
   Python 640 79
3. XFUND: A Multilingual Form Understanding Benchmark
   217 21
4. ReadingBank: A Benchmark Dataset for Reading Order Detection
   116 4

Repositories

Type

Select type

All Public Sources Forks Archived Mirrors Templates

Language

Select language

All CSS HTML Python

Sort

Select order

Last updated Name Stars

Showing 8 of 8 repositories

• ReadingBank Public
  ReadingBank: A Benchmark Dataset for Reading Order Detection
  doc-analysis/ReadingBank’s past year of commit activity
  116 4 8 0
  Updated Aug 26, 2024
• DocBank Public
  DocBank: A Benchmark Dataset for Document Layout Analysis
  doc-analysis/DocBank’s past year of commit activity
  Python
  640
  Apache-2.0
  79 31 0
  Updated Aug 12, 2024
• TableBank Public
  TableBank: A Benchmark Dataset for Table Detection and Recognition
  doc-analysis/TableBank’s past year of commit activity
• doc-analysis/tablebank-page’s past year of commit activity
  HTML
  1 1 0 0
  Updated Jul 19, 2023
• doc-analysis/docbank-page’s past year of commit activity
  HTML
  1
  0
  1 0
  Updated Jul 19, 2023
• XFUND Public
  XFUND: A Multilingual Form Understanding Benchmark
  doc-analysis/XFUND’s past year of commit activity
• doc-analysis/doc-analysis.github.io’s past year of commit activity
  CSS
  2
  0
  0 0
  Updated Sep 28, 2021
• DocBankLoader Public
  DocBankLoader is a dataset loader for DocBank, and can convert DocBank to the Object Detection models' format.
  doc-analysis/DocBankLoader’s past year of commit activity
  Python
  24
  MIT
  8 0 0
  Updated Mar 17, 2021

Most used topics

Loading…