AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections

Youwei Zhou, Tianyang Xu, Cong Wu, Xiaojun Wu, Josef Kittler

ICCV 2025 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 26 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 multi-head hyper-graph convolution (non-uniform, K=9) (ablation)baseline GCN · NTU-120 X-Sub (joint stream)accuracy: 84.7 -> 86.7Improved
use non-uniform instead of uniform hyper-graph at K=9 (ablation)M-HGC · NTU-120 X-Sub (joint stream)accuracy: 86.0 -> 86.7Improved
use uniform hyper-graph at K=5 versus non-uniform K=5 (ablation)M-HGC · NTU-120 X-Sub (joint stream)accuracy: 86.5 vs 86.2Mixed
increase K from 9 to 11 (non-uniform) (ablation)M-HGC · NTU-120 X-Sub (joint stream)accuracy: 86.7 -> 86.4Hurt
decrease K from 9 to 3 (non-uniform) (ablation)M-HGC · NTU-120 X-Sub (joint stream)accuracy: 86.7 -> 86.0Hurt
add 3 hyper joints with Divergence Loss without M-HGC (ablation)baseline GCN · NTU-120 X-Sub (joint stream)accuracy: 84.7 -> 85.2Improved
add Divergence Loss to 3 hyper joints with M-HGC (ablation)Hyper-GCN · NTU-120 X-Sub (joint stream)accuracy: 86.6 -> 86.9Improved
add Divergence Loss to 5 hyper joints without M-HGC (ablation)baseline GCN · NTU-120 X-Sub (joint stream)accuracy: 84.7 -> 85.0Improved
increase hyper joints from 3 to 5 per layer (ablation)Hyper-GCN with L_h · NTU-120 X-Sub (joint stream)accuracy: 86.9 -> 86.8Hurt
use 1 hyper joint instead of 3 with Divergence Loss (ablation)Hyper-GCN · NTU-120 X-Sub (joint stream)accuracy: 86.9 -> 86.7Hurt
scale base to large version (channels 512 in last stage)Hyper-GCN · NTU-120 X-Sub (4-stream ensemble)accuracy: 90.5 -> 90.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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