| Paper | Code | key-value pair F1 | ModelName | ReleaseDate |
|---|---|---|---|---|
| PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction | ✓ Link | 82.52 | PEneo (LayoutLMv3_base_chinese) | 2024-01-07 |
| PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction | ✓ Link | 82.36 | PEneo (LiLT[InfoXLM]_base) | 2024-01-07 |
| PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction | ✓ Link | 82.23 | PEneo (LayoutXLM_base) | 2024-01-07 |
| LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking | ✓ Link | 73.51 | LayoutLMv3_base_chinese | 2022-04-18 |
| LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding | ✓ Link | 72.76 | LiLT ([InfoXLM]_base) | 2022-02-28 |
| LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding | ✓ Link | 70.45 | LayoutXLM | 2021-04-18 |
| OCR-free Document Understanding Transformer | ✓ Link | 17.26 | Donut | 2021-11-30 |