AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

HyperSign: Hierarchical Hypergraph-based Co-occurrence Modeling for Sign Language Recognition and Translation

Qianren Guo, Yuehang Wang, Yongji Zhang, Qi Chu, Sen Liu, Yu Jiang

AAAI 2026 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 0 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 the CGP module (physical graph plus geometric and semantic hypergraphs) (ablation)skeleton graph-conv baseline · PHOENIX-2014T SLRWER (%): 27.3 / 28.1 -> 20.8 / 21.1Improved
add the MPHF module for cross-part hypergraph fusion (ablation)Baseline+CGP · PHOENIX-2014T SLRWER (%): 20.8 / 21.1 -> 18.9 / 19.7Improved
add UACD uncertainty-aware collaborative distillation (ablation)Baseline+CGP+MPHF · PHOENIX-2014T SLRWER (%): 18.9 / 19.7 -> 18.6 / 19.2Improved
increase KNN neighbors K from 8 to 9 (P=8) (ablation)HyperSign CGP · PHOENIX-2014T SLRWER (%): 18.6 / 19.2 -> 19.0 / 20.1Hurt
increase prototypes P from 8 to 9 (K=8) (ablation)HyperSign CGP · PHOENIX-2014T SLRWER (%): 18.6 / 19.2 -> 18.7 / 20.0Hurt
decrease K from 8 to 7 (P=8) (ablation)HyperSign CGP · PHOENIX-2014T SLRWER (%): 18.6 / 19.2 -> 18.7 / 19.3Hurt
decrease P from 8 to 7 (K=8) (ablation)HyperSign CGP · PHOENIX-2014T SLRWER (%): 18.6 / 19.2 -> 18.6 / 19.5Hurt
use HyperSign instead of MSKAskeleton SLR · CSL-Daily SLRWER (%): 27.5 / 27.1 -> 26.1 / 25.7Improved
use HyperSign instead of MSKAskeleton SLT · PHOENIX-2014TBLEU4: 29.03 -> 29.35Improved
use HyperSign instead of MSKAskeleton SLT · CSL-DailyBLEU4: 25.52 -> 26.87Improved
use HyperSign instead of MSKA (efficiency)skeleton SLR · PHOENIX-2014TFPS: 1224 -> 1397Improved
skeleton HyperSign versus RGB CV-SLTSLT · PHOENIX-2014T TESTROUGE: 54.26 vs. 54.54No clear effect

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