mlsanityData to 7 Oct 2026

An Attention-based Method for Action Unit Detection at the 3rd ABAW Competition

arXiv 2203.12428 ↗First posted 23 Mar 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Facial Action Coding System is an approach for modeling the complexity of human emotional expression. Automatic action unit (AU) detection is a crucial research area in human-computer interaction. This paper describes our submission to the third Affective Behavior Analysis in-the-wild (ABAW) competition 2022. We proposed a method for detecting facial action units in the video. At the first stage, a lightweight CNN-based feature extractor is employed to extract the feature map from each video frame. Then, an attention module is applied to refine the attention map. The attention encoded vector is derived using a weighted sum of the feature map and the attention scores later. Finally, the sigmoid function is used at the output layer to make the prediction suitable for multi-label AUs detection. We achieved a macro F1 score of 0.48 on the ABAW challenge validation set compared to 0.39 from the baseline model.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

23 of 32 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  3. 2015Attention-Based Models for Speech Recognitioncited by 400
  4. 2019Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFacecited by 222
  5. 2018Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyondcited by 216
  6. 2020Analysing Affective Behavior in the First ABAW 2020 Competitioncited by 178
  7. 2021Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Frameworkcited by 174
  8. 2021Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Studycited by 168
  9. 2021Analysing Affective Behavior in the second ABAW2 Competitioncited by 163
  10. 2020Suppressing Uncertainties for Large-Scale Facial Expression Recognitioncited by 157
  11. 2022ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challengescited by 156
  12. 2019Face Behavior a la carte: Expressions, Affect and Action Units in a Single Networkcited by 155
11 more
  1. 2018Facial Action Unit Detection Using Attention and Relation Learningcited by 46
  2. 2017Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusingcited by 28
  3. 2021A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognitioncited by 24
  4. 2021Global-Local Attention for Emotion Recognitioncited by 20
  5. 2016Survey on the attention based RNN model and its applications in computer visioncited by 14
  6. 2021Emotion Recognition with Incomplete Labels Using Modified Multi-task Learning Techniquecited by 10
  7. 2020Multi-label Relation Modeling in Facial Action Units Detectioncited by 7
  8. 2020Multi-Label Class Balancing Algorithm for Action Unit Detectioncited by 7
  9. 2021Action Units Recognition Using Improved Pairwise Deep Architecturecited by 6
  10. 2020Action Units Recognition by Pairwise Deep Architecturecited by 5
  11. 2021Action Unit Detection with Joint Adaptive Attention and Graph Relationcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 2.

4 papers.

  1. 2022ABAW: Learning from Synthetic Data & Multi-Task Learning Challengescited by 110
  2. 2023ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challengescited by 110
  3. 2024The 6th Affective Behavior Analysis in-the-wild (ABAW) Competitioncited by 78
  4. 20247th ABAW Competition: Multi-Task Learning and Compound Expression Recognitioncited by 53