mlsanityData to 7 Oct 2026

Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition

arXiv 2204.07935 ↗First posted 17 Apr 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Subject-invariant facial action unit (AU) recognition remains challenging for the reason that the data distribution varies among subjects. In this paper, we propose a causal inference framework for subject-invariant facial action unit recognition. To illustrate the causal effect existing in AU recognition task, we formulate the causalities among facial images, subjects, latent AU semantic relations, and estimated AU occurrence probabilities via a structural causal model. By constructing such a causal diagram, we clarify the causal effect among variables and propose a plug-in causal intervention module, CIS, to deconfound the confounder Subject in the causal diagram. Extensive experiments conducted on two commonly used AU benchmark datasets, BP4D and DISFA, show the effectiveness of our CIS, and the model with CIS inserted, CISNet, has achieved state-of-the-art performance.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 13 of its 38 references that are in the map. First posted on arXiv 17 Apr 2022.

Builds on

13 of 38 references.

References · 13

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2015Show, Attend and Tell: Neural Image Caption Generation with Visual Attentioncited by 1,421
  4. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  5. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  6. 2019Pyramid Feature Attention Network for Saliency detectioncited by 128
  7. 2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
  8. 2020Interventional Few-Shot Learningcited by 112
  9. 2018Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignmentcited by 55
  10. 2019Semantic Relationships Guided Representation Learning for Facial Action Unit Recognitioncited by 53
  11. 2018Deep Structure Inference Network for Facial Action Unit Recognitioncited by 38
  12. 2017Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusingcited by 28
1 more
  1. 2017EAC-Net: A Region-based Deep Enhancing and Cropping Approach for Facial Action Unit Detectioncited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 6; 2025: 0; 2026: 2.

11 papers.

  1. 2023Context De-confounded Emotion Recognitioncited by 34
  2. 2024Towards Multimodal Sentiment Analysis Debiasing via Bias Purificationcited by 26
  3. 2022Facial Action Unit Detection and Intensity Estimation from Self-supervised Representationcited by 14
  4. 2024De-confounded Data-free Knowledge Distillation for Handling Distribution Shiftscited by 11
  5. 2024Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Trainingcited by 11
  6. 2024Debiased Multimodal Understanding for Human Language Sequencescited by 10
  7. 2024Towards End-to-End Explainable Facial Action Unit Recognition via Vision-Language Joint Learningcited by 9
  8. 2024Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Samplecited by 6
  9. 2026Hierarchical Vision-Language Interaction for Facial Action Unit Detectioncited by 3
  10. 2022Global-to-local Expression-aware Embeddings for Facial Action Unit Detectioncited by 0
  11. 2026Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanationscited by 0