AI Paper Atlas

Research map / Video / Action recognition

Hierarchical-aware Orthogonal Disentanglement Framework for Fine-grained Skeleton-based Action Recognition

Haochen Chang, Pengfei Ren, Haoyang Zhang, Liang Xie, Hongbo Chen, Erwei Yin

ICCV 2025 · Video › Action recognition · approach: Skeleton-based action recognition · 8 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 spatial granularity-aware bases to baseline (ablation)Baseline · FineGYM (joint, ablation)accuracy (%): 92.4 -> 93.0Improved
add temporal granularity-aware bases to baseline (ablation)Baseline · FineGYM (joint, ablation)accuracy (%): 92.4 -> 92.9Improved
combine spatial and temporal bases (ablation)Baseline · FineGYM (joint, ablation)accuracy (%): 92.4 -> 94.1Improved
add shared orthogonal bases for cross-granularity interaction (ablation)HiOD · FineGYM (joint, ablation)accuracy (%): 94.1 -> 94.4Improved
use granularity-aware bases instead of channel split (ablation)HiOD · FineGYM (joint, ablation)accuracy (%): 92.7 -> 94.1Improved
use granularity-aware bases instead of FC heads (ablation)HiOD · FineGYM (joint, ablation)accuracy (%): 92.9 -> 94.1Improved
use granularity-aware bases instead of wavelet transform (ablation)HiOD · FineGYM (joint, ablation)accuracy (%): 92.8 -> 94.1Improved
hard prototype contrastive loss instead of cross-entropy for both granularities (ablation)HiOD · FineGYM (joint, ablation)accuracy (%): 93.3 -> 93.6Improved
add soft prototypes for coarse-grained features (ablation)HiOD · FineGYM (joint, ablation)accuracy (%): 93.6 -> 93.8Improved
add soft prototype weighted contrastive loss (ablation)HiOD · FineGYM (joint, ablation)accuracy (%): 93.8 -> 94.4Improved
use HiOD over HD-GCN on NTU60 hard subsetHiOD · NTU60-Hard subsetaccuracy (%): 66.3 -> 70.2Improved
use HiOD over HD-GCN on NTU60 easy subsetHiOD · NTU60-Easy subsetaccuracy (%): 95.2 -> 95.5Improved

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