📊 Showing 6 results | 📏 Metric: F1
| Rank | Model | Paper | F1 | Date | Code |
|---|---|---|---|---|---|
| 1 | GeoLayoutLM | GeoLayoutLM: Geometric Pre-training for Visual Information Extraction | 89.45 | 2023-04-21 | 📦 alibabaresearch/advancedliteratemachinery |
| 2 | RORE (GeoLayoutLM) | Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding | 88.46 | 2024-09-29 | 📦 chongzhangFDU/ROOR |
| 3 | TPP (LayoutMask) | Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction | 79.20 | 2023-10-17 | 📦 chongzhangfdu/tpp 📦 WinterShiver/Token-Path-Prediction |
| 4 | DocTr | DocTr: Document Transformer for Structured Information Extraction in Documents | 73.90 | 2023-07-16 | - |
| 5 | SERA | Entity Relation Extraction as Dependency Parsing in Visually Rich Documents | 65.96 | 2021-10-19 | - |
| 6 | Doc2Graph | Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks | 53.36 | 2022-08-23 | 📦 andreagemelli/doc2graph |