mlsanityData to 7 Oct 2026

Affective Behavior Analysis using Action Unit Relation Graph and Multi-task Cross Attention

arXiv 2207.10293 ↗First posted 21 Jul 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Facial behavior analysis is a broad topic with various categories such as facial emotion recognition, age, and gender recognition. Many studies focus on individual tasks while the multi-task learning approach is still an open research issue and requires more research. In this paper, we present our solution and experiment result for the Multi-Task Learning challenge of the Affective Behavior Analysis in-the-wild competition. The challenge is a combination of three tasks: action unit detection, facial expression recognition, and valance-arousal estimation. To address this challenge, we introduce a cross-attentive module to improve multi-task learning performance. Additionally, a facial graph is applied to capture the association among action units. As a result, we achieve the evaluation measure of 128.8 on the validation data provided by the organizers, which outperforms the baseline result of 30.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 21 Jul 2022.

Builds on

15 of 21 references.

References · 15

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  4. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  5. 2017AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wildcited by 490
  6. 2019Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFacecited by 222
  7. 2018Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyondcited by 216
  8. 2021Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Frameworkcited by 174
  9. 2021Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Studycited by 168
  10. 2022ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challengescited by 156
  11. 2022ABAW: Learning from Synthetic Data & Multi-Task Learning Challengescited by 110
  12. 2022Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognitioncited by 81
3 more
  1. 2021Facial expression and attributes recognition based on multi-task learning of lightweight neural networkscited by 40
  2. 2018Photorealistic Facial Synthesis in the Dimensional Affect Spacecited by 33
  3. 2022Frame-level Prediction of Facial Expressions, Valence, Arousal and Action Units for Mobile Devicescited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 0; 2026: 4.

8 papers.

  1. 2023A transformer-based approach to video frame-level prediction in Affective Behaviour Analysis In-the-wildcited by 8
  2. 2023Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detectioncited by 7
  3. 2024HSEmotion Team at the 7th ABAW Challenge: Multi-Task Learning and Compound Facial Expression Recognitioncited by 6
  4. 2023Spatial-temporal Transformer for Affective Behavior Analysiscited by 2
  5. 2026The Circumplex Degeneracy Behind the Rare-Class Limit in Affect Recognitioncited by 1
  6. 2026HSEmotion Team at the 11th ABAW Challenge: Multi-Task Learning and Ambivalence/Hesitancy Video Recognitioncited by 1
  7. 2026A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognitioncited by 1
  8. 2026Strength-Parity Ensembling with Parameter-Isolated Experts for Multi-Task Affect Recognitioncited by 0