Table 6 Semantic Structural Congruence (SSC) across datasets for different document layout models with input embeddings: Image and Layout Only.
From: Representation learning approach for understanding structured documents
Dataset / Model | LayoutLMv36 | DocLayout-YOLO30 | DocSAM28 | LayoutLLM36 | DocLayLLM37 | D-REEL |
|---|---|---|---|---|---|---|
PRImA Newspaper Dataset34 | 59.34 | 61.27 | 60.18 | 66.41 | 67.58 | 75.42 |
German-Brazilian Newspapers (GBN)35 | 61.05 | 62.13 | 61.59 | 66.52 | 67.04 | 74.38 |
S2-VL Dataset10 | 85.53 | 87.42 | 88.16 | 89.03 | 89.57 | 91.49 |
IIIT AR 13K33 | 86.51 | 87.36 | 88.28 | 89.24 | 89.54 | 90.37 |
Publaynet32 | 87.11 | 88.44 | 88.53 | 89.57 | 90.19 | 90.58 |
