AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Focal-General Diffusion Model with Semantic Consistent Guidance for Sign Language Production

Yiheng Yu, Sheng Liu, Yuan Feng, Zhelun Jin, Yining Jiang, Min Xu

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Compositional scene generation

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 the Focal stage (ASGCN + TCN) to the General-only baseline (ablation)FGDM · PHOENIX14T DEVWER: 81.00 -> 76.57Improved
add Semantic Consistent Guidance (SCG) to the General-only baseline (ablation)FGDM · PHOENIX14T DEVWER: 81.00 -> 78.92Improved
combine Focal stage and SCG (ablation)FGDM · PHOENIX14T TESTWER: 79.76 -> 70.70Improved
add contextual correlation term A_a to ASGCN (ablation)ASGCN · PHOENIX14T DEVBLEU-1: 23.29 -> 28.09Improved
add skeletal topology term A_b to ASGCN (ablation)ASGCN · PHOENIX14T DEVBLEU-1: 26.44 -> 28.09Improved
add semantic mask M to ASGCN (ablation)ASGCN · PHOENIX14T DEVWER: 77.66 -> 76.57Improved
increase Focal layers from 3 to 4 (ablation)FGDM · PHOENIX14T DEVWER: 72.22 -> 72.35No clear effect
increase Focal layers from 1 to 3 (ablation)FGDM · PHOENIX14T DEVWER: 76.27 -> 72.22Improved
use 2 General layers instead of 1 or 3 (ablation)FGDM · PHOENIX14T DEVWER: 79.13 (L2=1), 73.79 (L2=3) -> 72.22 (L2=2)Improved
FGDM versus strongest diffusion baseline Sign-IDDFGDM · PHOENIX14T TESTWER: 79.15 -> 70.70Improved
FGDM versus Sign-IDD on harder splitFGDM · USTC-CSL TEST (Split-II)BLEU-3: 2.68 -> 15.71Improved

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