atlas

Research map / Graph learning / Graph self-supervised learning

Uncertain Graph Neural Networks for Facial Action Unit Detection

AAAI 2021 · Graph learning › Graph self-supervised learning · approach: Graph domain adaptation · 79 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 UGN-B instead of SRERLAU detection · BP4DF1-score: 62.9 -> 63.3Helped
Use UGN-B instead of JAAAU detection · BP4DAccuracy: 78.4 -> 78.2Hurt
Use UGN-B instead of ARLAU detection · DISFAF1-score: 58.7 -> 60.0Helped
Use UGN-B instead of ARLAU detection · DISFAAccuracy: 93.3 -> 93.4Helped
Add the adaptive weighted loss based on epistemic uncertainty (ablation)UGN on BP4D · BP4DF1-score: 63.0 -> 63.3Helped
Add the adaptive weighted loss based on epistemic uncertainty (ablation)UGN on BP4D · BP4DAccuracy: 77.7 -> 78.2Helped
Use a probabilistic graph instead of a deterministic graph (ablation)AU detection on BP4D · BP4DF1-score: 62.6 -> 63.0Helped
Use a probabilistic graph instead of a deterministic graph (ablation)AU detection on BP4D · BP4DAccuracy: 77.7 -> 77.7No 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