Paper | Code | F1 | ModelName | ReleaseDate |
---|---|---|---|---|
GeoLayoutLM: Geometric Pre-training for Visual Information Extraction | ✓ Link | 89.45 | GeoLayoutLM | 2023-04-21 |
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding | ✓ Link | 88.46 | RORE (GeoLayoutLM) | 2024-09-29 |
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction | ✓ Link | 79.20 | TPP (LayoutMask) | 2023-10-17 |
DocTr: Document Transformer for Structured Information Extraction in Documents | 73.9 | DocTr | 2023-07-16 | |
DGCN Based Solution for Entity Linking on Visual Rich Document | 70.51 | SINGU_GROUP | 2022-11-16 | |
Entity Relation Extraction as Dependency Parsing in Visually Rich Documents | 65.96 | SERA | 2021-10-19 | |
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks | ✓ Link | 53.36 | Doc2Graph | 2022-08-23 |