Feeding an LLM sign-language visual features plus pseudo-glosses, previous-sentence translations, and background captions improves open-vocabulary sign language translation on BOBSL and How2Sign.
Is context all you need? scaling neural sign language translation to large domains of discourse
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
unclear 1representative citing papers
citing papers explorer
-
Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues
Feeding an LLM sign-language visual features plus pseudo-glosses, previous-sentence translations, and background captions improves open-vocabulary sign language translation on BOBSL and How2Sign.