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

The Sign Language Production (SLP) project aims to automatically translatespoken languages into sign sequences. Our approach focuses on thetransformation of sign gloss sequences into their corresponding sign posesequences (G2P). In this paper, we present a novel solution for this task byconverting the continuous pose space generation problem into a discretesequence generation problem. We introduce the Pose-VQVAE framework, whichcombines Variational Autoencoders (VAEs) with vector quantization to produce adiscrete latent representation for continuous pose sequences. Additionally, wepropose the G2P-DDM model, a discrete denoising diffusion architecture forlength-varied discrete sequence data, to model the latent prior. To furtherenhance the quality of pose sequence generation in the discrete space, wepresent the CodeUnet model to leverage spatial-temporal information. Lastly, wedevelop a heuristic sequential clustering method to predict variable lengths ofpose sequences for corresponding gloss sequences. Our results show that ourmodel outperforms state-of-the-art G2P models on the public SLP evaluationbenchmark. For more generated results, please visit our project page:\textcolor{blue}{\url{https://slpdiffusier.github.io/g2p-ddm}}

G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model