Reading Order Detection On Roor
Metriken
Segment-level F1
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| LayoutLMv3-GlobalPointer (large) | 82.38 | Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding |
| LayoutLMv3-GlobalPointer (base) | 68.60 | Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding |
| TPP (LayoutLMv3-base) | 42.96 | Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction |
| LayoutReader | 9.44 | LayoutReader: Pre-training of Text and Layout for Reading Order Detection |
0 of 4 row(s) selected.