AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Progressive Transformers for End-to-End Sign Language Production

Ben Saunders, Necati Cihan Camgoz, Richard Bowden

ECCV 2020 · Large language models › Language, safety and interpretability · approach: Sign language datasets and translation · 198 citations (OpenAlex)

Read the paperCheck 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
add future prediction of the next 10 frames (ablation)Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test)BLEU-4: 5.03 -> 8.38Improved
feed only counter values as target input (just counter) (ablation)Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test)BLEU-4: 5.03 -> 9.16Improved
add Gaussian noise augmentation to skeleton poses (ablation)Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test)BLEU-4: 5.03 -> 10.02Improved
combine future prediction with Gaussian noise (ablation)Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test)BLEU-4: 5.03 -> 10.43Improved
add Gaussian noise on top of future prediction (ablation)Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (dev)BLEU-4: 9.96 -> 11.93Improved
add future prediction to Gaussian noise (ablation)Progressive Transformer (gloss to pose) · PHOENIX14T gloss-to-pose (test)BLEU-4: 10.02 -> 10.43Improved
use gloss intermediary (T2G2P) instead of direct text to poseProgressive Transformer · PHOENIX14T text-to-pose (test)BLEU-4: 10.51 -> 9.68Hurt
use gloss intermediary instead of direct text inputProgressive Transformer · PHOENIX14T text-to-pose (dev)BLEU-4: 11.82 -> 11.43Hurt
use gloss intermediary instead of direct text inputProgressive Transformer · PHOENIX14T text-to-pose (dev)BLEU-1: 31.41 -> 33.12Improved
use transformer instead of GRU encoder-decoder for text to glossSymbolic Transformer · PHOENIX14T text-to-gloss (test)BLEU-4: 15.26 -> 19.10Improved

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