7 citations · 7 across the 9 of their papers we have counts for
3 papers · 1 filter
DECDM: Document Enhancement using Cycle-Consistent Diffusion Models
Jiaxin Zhang, Joy Rimchala, Lalla Mouatadid +2
The performance of optical character recognition (OCR) heavily relies on document image quality, which is crucial for automatic document processing and document intelligence. Howev…
RE: Region-Aware Relation Extraction from Visually Rich Documents
Pritika Ramu, Sijia Wang, Lalla Mouatadid +2
Current research in form understanding predominantly relies on large pre-trained language models, necessitating extensive data for pre-training. However, the importance of layout s…
A Scalable Technique for Weak-Supervised Learning with Domain Constraints
Sudhir Agarwal, Anu Sreepathy, Lalla Mouatadid
We propose a novel scalable end-to-end pipeline that uses symbolic domain knowledge as constraints for learning a neural network for classifying unlabeled data in a weak-supervised…