AI Paper Atlas

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

Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives

Ben Saunders, Necati Cihan Camgoz, Richard Bowden

ICCV 2021 · Large language models › Language, safety and interpretability · approach: Sign language datasets and translation · 62 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 randomness in BCD expert selection (ablation)MoMP · PHOENIX14T Gloss to Pose (dev)BLEU-4: 12.14 -> 13.32Improved
add block coordinate descent training (ablation)MoMP · PHOENIX14T Gloss to Pose (dev)BLEU-4: 10.85 -> 13.32Improved
use BCD instead of simple EM training (ablation)MoMP · PHOENIX14T Gloss to Pose (dev)BLEU-4: 11.84 -> 13.32Improved
add expert balance loss (ablation)MoMP · PHOENIX14T Gloss to Pose (dev)BLEU-4: 12.20 -> 13.32Improved
add variance loss (ablation)MoMP · PHOENIX14T Gloss to Pose (dev)BLEU-4: 11.88 -> 13.32Improved
use 8 motion primitives instead of 10 (ablation)MoMP · PHOENIX14T Gloss to Pose (dev)BLEU-4: 12.53 -> 13.32Improved
add gloss-supervised translation loss (lambda_T 0.0 to 1.0) (ablation)MoMP · PHOENIX14T Text to Pose (dev)BLEU-4: 12.74 -> 13.72Improved
raise translation loss weight from 1.0 to 2.0 (ablation)MoMP · PHOENIX14T Text to Pose (dev)BLEU-4: 13.72 -> 14.03Improved
raise translation loss weight from 2.0 to 10.0 (ablation)MoMP · PHOENIX14T Text to Pose (dev)BLEU-4: 14.03 -> 13.51Hurt
go from spoken text directly rather than via gloss intermediateMoMP · PHOENIX14T devBLEU-4: 13.32 -> 14.03Improved
keep all motion primitives active at test time (vs deactivating one) (ablation)MoMP · PHOENIX14T Gloss to PoseBLEU-4: -0.83 BLEU-4 when disabling oneImproved
use MoMP instead of Mixture Density NetworksMoMP · Perceptual study, skeletonspreference (%): 33 -> 49Improved

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