AI Paper Atlas

Research map / Video / Video generation

SignPR: A Progressive Vector-Quantized Diffusion Framework for Sign Language Production

Xiao Liu, Shiwei Gan, Yafeng Yin, Bowen Guo, Zhiwei Jiang, Shunmei Meng, Lei Xie, Sanglu Lu

CVPR 2026 · Video › Video generation · approach: Text-to-motion diffusion

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
use SignPR (no glosses) instead of gloss-based Sign-IDDsign pose generation · PHOENIX-14T testMPJPE: 47.19 -> 23.04Improved
add regional codebooks to the semantic codebook in S-VQVAE (ablation)S-VQVAE · PHOENIX-14T reconstructionrROUGE: 36.69 -> 39.51Improved
share one regional codebook across regions instead of separate codebooks (ablation)S-VQVAE · PHOENIX-14T reconstructionrROUGE: 39.51 -> 37.54Hurt
add structural consistency loss Lcons (ablation)SignPR · PHOENIX-14T testROUGE: 24.35 -> 32.86Improved
use GCN encoder instead of Transformer encoder (ablation)S-VQVAE · PHOENIX-14T testMPJPE: 28.07 -> 23.04Improved
add regional diffusion on top of semantic diffusion (ablation)S-Diffusion · PHOENIX-14T testROUGE: 22.53 -> 32.86Improved
add semantic diffusion on top of regional diffusion (ablation)S-Diffusion · PHOENIX-14T testROUGE: 23.90 -> 32.86Improved
use separate regional codebooks instead of a shared regional codebook in diffusion (ablation)S-Diffusion · PHOENIX-14T testROUGE: 27.49 -> 32.86Improved
condition regional diffusion on semantic pose in addition to text, using cross-attention (ablation)regional diffusion · PHOENIX-14T testROUGE: 23.90 (text only) -> 32.86Improved
fuse text and semantic pose by cross-attention instead of concatenation (ablation)regional diffusion · PHOENIX-14T testROUGE: 26.42 -> 32.86Improved
add block-wise causal inference (InferRef, K=8) at inference time (ablation)SignPR · PHOENIX-14T testROUGE: 31.50 -> 32.86Improved
use smaller blocks (K=8 instead of unblocked) in InferRef (ablation)SignPR · PHOENIX-14T testseconds per video: 1.47 -> 2.45Hurt

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