SAGE uses a frozen sign-segmentation model to turn sign videos into about half as many visual tokens as prior methods, then aligns those tokens with a language model to reach BLEU-4 of 24.10 on PHOENIX14T.
Neural sign language trans- lation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SAGE: Segment-Aware Gloss-Free Encoding for Token-Efficient Sign Language Translation
SAGE uses a frozen sign-segmentation model to turn sign videos into about half as many visual tokens as prior methods, then aligns those tokens with a language model to reach BLEU-4 of 24.10 on PHOENIX14T.