ReadingBank is a benchmark dataset for reading order detection built with weak supervision from WORD documents, which contains 500K document images with a wide range of document types as well as the corresponding reading order information.
Variants: ReadingBank
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Reading Order Detection | TPP (LayoutMask) | Reading Order Matters: Information Extraction … | 2023-10-17 |
| Reading Order Detection | LayoutReader | LayoutReader: Pre-training of Text and … | 2021-08-26 |
Recent papers with results on this dataset: