Fine-tuning an open vision-language model with multi-task learning and perceptual chain-of-thought, plus MBR decoding, achieves strong BLEU scores on end-to-end document image translation at ICDAR 2025.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DIMT25@ICDAR2025: HW-TSC's End-to-End Document Image Machine Translation System Leveraging Large Vision-Language Model
Fine-tuning an open vision-language model with multi-task learning and perceptual chain-of-thought, plus MBR decoding, achieves strong BLEU scores on end-to-end document image translation at ICDAR 2025.