AI Paper Atlas

Research map / Probabilistic and scientific modeling / Causal discovery

Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample

Zhiwen Shao, Hancheng Zhu, Yong Zheng Zhou, Xiang Xiang, Bing Liu, Rui Yao, Lizhuang Ma

IJCV 2024 · Probabilistic and scientific modeling › Causal discovery · approach: Causal representation identifiability · 27 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 adaptive constraining of average self-attention (ablation)B-Net · BP4DAvg F1-frame: 60.2 -> 62.2Improved
constrain each self-attention channel instead of the average (ablation)A^v-Net · BP4DAvg F1-frame: 62.2 -> 61.9Hurt
add causal deconfounding with per-batch prototypes in each AU branch (ablation)A^v-Net · BP4DAvg F1-frame: 62.2 -> 64.6Improved
compute sample prototypes per mini-batch rather than per epoch (ablation)AC2D · BP4DAvg F1-frame: 63.4 -> 64.6Improved
apply deconfounding per AU branch rather than on shared feature (ablation)AC2D · BP4DAvg F1-frame: 60.0 -> 64.6Improved
add sample deconfounding (BP4D to GFT) (ablation)A^v-Net · BP4D to GFT cross-datasetAvg F1-frame: 37.0 -> 42.3Improved
add sample deconfounding (GFT to BP4D) (ablation)A^v-Net · GFT to BP4D cross-datasetAvg F1-frame: 33.9 -> 38.4Improved

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