A language-decoupled pre-training method, using a text-editing diffusion model to remove readable text from document images, improves cross-lingual visual information extraction from English-only data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LDP: Generalizing to Multilingual Visual Information Extraction by Language Decoupled Pretraining
A language-decoupled pre-training method, using a text-editing diffusion model to remove readable text from document images, improves cross-lingual visual information extraction from English-only data.