DiffSLT uses a latent diffusion model conditioned on fused multi-level visual features to produce diverse, accurate sign language translations, and DiffSLT-P conditions on pseudo-glosses to improve accuracy further.
Neural sign language trans- lation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiffSLT: Enhancing Diversity in Sign Language Translation via Diffusion Model
DiffSLT uses a latent diffusion model conditioned on fused multi-level visual features to produce diverse, accurate sign language translations, and DiffSLT-P conditions on pseudo-glosses to improve accuracy further.