A temporally aligned gloss-level conditioning method with local fusion improves lexical order and semantic accuracy in sign language generation, reporting state-of-the-art results on CSL-Daily and Phoenix-2014T.
Layer normalization
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
-
SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning
A temporally aligned gloss-level conditioning method with local fusion improves lexical order and semantic accuracy in sign language generation, reporting state-of-the-art results on CSL-Daily and Phoenix-2014T.