AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Deep Facial Action Unit Recognition From Partially Labeled Data

Shan Wu, Shangfei Wang, Bowen Pan, Qiang Ji

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware facial expression recognition · 31 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 AU label distribution (RBM) constraint to the deep AU classifier (ablation)DNN+SVM AU recognizer · BP4D (complete labels)average F1 score: 0.446 -> 0.491Improved
add AU label distribution (RBM) constraint to the deep AU classifier (ablation)DNN+SVM AU recognizer · DISFA (complete labels)average F1 score: 0.532 -> 0.584Improved
add AU label distribution constraint (ablation)DNN+SVM AU recognizer · DISFA AU17F1 score: 0.201 -> 0.447Improved
add AU label distribution constraint (ablation)DNN+SVM AU recognizer · BP4D AU7F1 score: 0.666 -> 0.620Hurt
add AU label distribution constraint (ablation)DNN+SVM AU recognizer · BP4D AU2F1 score: 0.187 -> 0.166Hurt
add AU label distribution constraint (ablation)DNN+SVM AU recognizer · DISFA AU1F1 score: 0.608 -> 0.574Hurt
add AU label distribution constraint under random missing AU labels (10-50%) (ablation)DNN+SVM AU recognizer · DISFA and BP4D (partial labels)F1 scoreImproved
learn deep features instead of raw pixels (ablation)AU recognizer · BP4D and DISFAsubject-bias in t-SNE embeddingImproved
use the deep model without label constraint instead of linear SVM on handcrafted featuresAU recognizer · BP4Daverage F1 score: 0.353 -> 0.446Improved
proposed method vs JPML (handcrafted SIFT, dataset-statistics AU relations)AU recognizer · BP4Daverage F1 score: 0.459 -> 0.491Improved
proposed method vs DRML region-layer networkAU recognizer · BP4Daverage F1 score: 0.483 -> 0.491Mixed

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