English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Existing sign language translation methods follow a two-stage pipeline: firstconverting the sign language video to a gloss sequence (i.e. Sign2Gloss) andthen translating the generated gloss sequence into a spoken language sentence(i.e. Gloss2Text). While previous studies have focused on boosting theperformance of the Sign2Gloss stage, we emphasize the optimization of theGloss2Text stage. However, this task is non-trivial due to two distinctfeatures of Gloss2Text: (1) isolated gloss input and (2) low-capacity glossvocabulary. To address these issues, we propose a vision and context knowledgeenhanced Gloss2Text model, named VK-G2T, which leverages the visual content ofthe sign language video to learn the properties of the target sentence andexploit the context knowledge to facilitate the adaptive translation of glosswords. Extensive experiments conducted on a Chinese benchmark validate thesuperiority of our model.

VK-G2T: Vision and Context Knowledge enhanced Gloss2Text