Login / Signup
Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding.
Shuwei Feng
Tianyang Zhan
Zhanming Jie
Trung Quoc Luong
Xiaoran Jin
Published in:
CoRR (2023)
Keyphrases
</>
visual information
knowledge discovery
natural language processing
image classification
visual features