Sign language video generation demands precise hand and facial articulation, yet modern video diffusion models, trained predominantly on spoken-language video, produce artifacts that render signing unintelligible. We propose SignRefine, a sign language video generation model that produces comprehensible signing from 2D...
A. Pelykh, Edward Fish, Ozge Mercanoglu Sincan et al.· 0 citations
BLEU-4 is the standard metric for evaluating sign language translation (SLT), but spoken-language metrics may not adequately reflect sign language proficiency. The multimodal, low-resource context of SLT allows models to exploit spurious correlations and spoken-language priors, rather than learning stronger sign repres...
Oline Ranum, Edward Fish, Simon Hadfield et al.· 0 citations
SignBind-LLM, a modular framework that addresses limitations of sign language translation systems through three dedicated expert streams: one for continuous signing, one for fingerspelling, and one for lipreading, confirms that the gains are architectural rather than a consequence of scaling the language model.
Marshall Thomas, Edward Fish, Richard Bowden· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
