Reading Order Detection
Reading order detection aims to capture the word sequence which can be naturally comprehended by human readers from visually-rich documents. It is a fundamental task for visually-rich document understanding.
Papers
No papers found.
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | LayoutLMv3-GlobalPointer (large) | Segment-level F1 | 82.38 | — | Unverified |
| 2 | LayoutLMv3-GlobalPointer (base) | Segment-level F1 | 68.6 | — | Unverified |
| 3 | TPP (LayoutLMv3-base) | Segment-level F1 | 42.96 | — | Unverified |
| 4 | LayoutReader | Segment-level F1 | 9.44 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | LayoutReader | Average Relative Distance (ARD) | 1.75 | — | Unverified |
| 2 | TPP (LayoutMask) | Average Relative Distance (ARD) | 0.37 | — | Unverified |