PRIM provides the first real-world, multilingual in-image translation benchmark, and the proposed VisTrans end-to-end model improves visual quality over prior end-to-end systems while trailing strong cascade models on translation accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PRIM: Towards Practical In-Image Multilingual Machine Translation
PRIM provides the first real-world, multilingual in-image translation benchmark, and the proposed VisTrans end-to-end model improves visual quality over prior end-to-end systems while trailing strong cascade models on translation accuracy.