Search Results for author:
Found 2 papers, 0 papers with code
DECDM: Document Enhancement using Cycle-Consistent Diffusion Models
The performance of optical character recognition (OCR) heavily relies on document image quality, which is crucial for automatic document processing and document intelligence.
RE$^2$: Region-Aware Relation Extraction from Visually Rich Documents
Current research in form understanding predominantly relies on large pre-trained language models, necessitating extensive data for pre-training.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
