Login / Signup

Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding.

Shuwei FengTianyang ZhanZhanming JieTrung Quoc LuongXiaoran Jin
Published in: CoRR (2023)
Keyphrases
  • visual information
  • knowledge discovery
  • natural language processing
  • image classification
  • visual features