DiT Annotated Paper
DIT: SELF-SUPERVISED PRE-TRAINING FOR DOCUMENT IMAGE TRANSFORMER
DIT: SELF-SUPERVISED PRE-TRAINING FOR DOCUMENT IMAGE TRANSFORMER
WebFormer: The Web-page Transformer for Structure Information Extraction
LayoutLMv2: Multi-Modal Pre-Training For Visually-Rich Document Understanding
Fastformer: Additive Attention Can Be All You Need
LayoutLM: Pre-training of Text and Layout for Document Image Understanding