A lightweight sign generation model plus synthetic data pretraining improves sign language recognition accuracy, setting new state-of-the-art results on the LSFB and DiSPLaY benchmarks.
, author Zhao, X
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HandCraft: Dynamic Sign Generation for Synthetic Data Augmentation
A lightweight sign generation model plus synthetic data pretraining improves sign language recognition accuracy, setting new state-of-the-art results on the LSFB and DiSPLaY benchmarks.