AI Paper Atlas

Research map / Video / Video segmentation and tracking

Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production

Ben Saunders, Necati Cihan Camgoz, Richard Bowden

CVPR 2022 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 74 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace direct pose regression with learned temporal frame selection and alignmentGloss-to-Pose production · PHOENIX14T back translation testBLEU-4: 13.30 -> 21.10Improved
Use learned co-articulation rather than an interpolated dictionary sequenceGloss-to-Pose production · PHOENIX14T back translation testBLEU-4: 16.27 -> 18.78Improved
Add a hand keypoint loss (ablation)SignGAN · C4AHand SSIM: 0.582 -> 0.605Improved
Add a hand keypoint loss (ablation)SignGAN · C4AFID: 39.33 -> 27.75Improved
Add a hand discriminator instead of a hand keypoint loss (ablation)SignGAN · C4AHand SSIM: 0.582 -> 0.565Hurt
Add a hand discriminator instead of a hand keypoint loss (ablation)SignGAN · C4ASSIM: 0.743 -> 0.738Hurt
Generate photo-realistic signing videos instead of skeleton sequencesSignGAN · Deaf user comprehension evaluationunderstandability rating: 3.2 -> 3.9Improved
Use FS-Net co-articulated sequences rather than the baseline SLP methodSign language production · mDGS and PHOENIX14T comprehension preferenceparticipant preference: 0% -> 95%Improved
Use FS-Net co-articulation rather than isolated non-trimmed dictionary signsDictionary-sign production · Non-trimmed dictionary signssmooth-transition preference: 0% -> 100%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy