AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Upper-body Hierarchical Graph for Skeleton Based Emotion Recognition in Assistive Driving

Jiehui Wu, Jiansheng Chen, Qifeng Luo, Siqi Liu, Youze Xue, Huimin Ma

ECCV 2024 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 3 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 fully connected edges to the physically connected hierarchical graph (ablation)UbH-GCN · AIDEAcc. (%): 74.55 -> 75.37Improved
replace conventional CTR-GCN graph with UbH hierarchical graph (PC edges) (ablation)CTR-GCN · AIDEAcc. (%): 71.92 -> 74.55Improved
use imbalance-aware logit variation loss instead of cross-entropy (ablation)UbH-GCN 4-ensemble · AIDEAcc. (%): 74.55 -> 77.50Improved
apply imbalance-aware loss to HD-GCN (ablation)HD-GCN 4-ensemble · AIDEAcc. (%): 76.03 -> 76.68Improved
use four-way ensemble (two roots x joint/bone) instead of two-way (ablation)UbH-GCN · AIDEAcc. (%): 75.37 -> 77.50Improved
use upper-body skeleton instead of full-body inputUbH-GCN · EmilyaAcc. (%): 93.01 -> 91.28 (3-fold), 94.42 -> 93.98 (10-fold)Mixed
drop motion streams from ensembleUbH-GCN · AIDEAcc. (%)No 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