Pose normalization based on the signer's signing space substantially improves gloss-free sign language translation with a T5 model, while interpolation and augmentation give smaller, less certain gains.
Vision transformers need registers, 2024
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
-
Exploring Pose-based Sign Language Translation: Ablation Studies and Attention Insights
Pose normalization based on the signer's signing space substantially improves gloss-free sign language translation with a T5 model, while interpolation and augmentation give smaller, less certain gains.