LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding

Benchmark Model Rank Results
key-value-pair-extraction-on-sibrLayoutXLM#6key-value pair F1: 70.45
key-value-pair-extraction-on-rfund-enLayoutXLM_base#9key-value pair F1: 53.98
document-image-classification-on-rvl-cdipLayoutXLM#13Accuracy: 95.21%
semantic-entity-labeling-on-funsdLayoutXLM Large#15F1: 82.25