# A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysis

arXiv: https://arxiv.org/abs/2107.04225 · HTML: https://mlsanity.com/paper/2107.04225/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 9 Jul 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace](https://mlsanity.com/paper/1910.04855/) (2019)
- [Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond](https://mlsanity.com/paper/1804.10938/) (2018)
- [Analysing Affective Behavior in the First ABAW 2020 Competition](https://mlsanity.com/paper/2001.11409/) (2020)
- [Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework](https://mlsanity.com/paper/2103.15792/) (2021)
- [Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Study](https://mlsanity.com/paper/2105.03790/) (2021)
- [Analysing Affective Behavior in the second ABAW2 Competition](https://mlsanity.com/paper/2106.15318/) (2021)
- [Suppressing Uncertainties for Large-Scale Facial Expression Recognition](https://mlsanity.com/paper/2002.10392/) (2020)
- [Face Behavior a la carte: Expressions, Affect and Action Units in a Single Network](https://mlsanity.com/paper/1910.11111/) (2019)
- [Two-Stream Aural-Visual Affect Analysis in the Wild](https://mlsanity.com/paper/2002.03399/) (2020)
- [Multitask Emotion Recognition with Incomplete Labels](https://mlsanity.com/paper/2002.03557/) (2020)
- [Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition](https://mlsanity.com/paper/2107.03708/) (2021)
- [MIMAMO Net: Integrating Micro- and Macro-motion for Video Emotion Recognition](https://mlsanity.com/paper/1911.09784/) (2019)
- [Technical Report for Valence-Arousal Estimation on Affwild2 Dataset](https://mlsanity.com/paper/2105.01502/) (2021)

## Built on by (most cited first, 19 of 19)

- [ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges](https://mlsanity.com/paper/2202.10659/) (2022)
- [ABAW: Learning from Synthetic Data & Multi-Task Learning Challenges](https://mlsanity.com/paper/2207.01138/) (2022)
- [ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges](https://mlsanity.com/paper/2303.01498/) (2023)
- [The 6th Affective Behavior Analysis in-the-wild (ABAW) Competition](https://mlsanity.com/paper/2402.19344/) (2024)
- [7th ABAW Competition: Multi-Task Learning and Compound Expression Recognition](https://mlsanity.com/paper/2407.03835/) (2024)
- [Transformer-based Multimodal Information Fusion for Facial Expression Analysis](https://mlsanity.com/paper/2203.12367/) (2022)
- [Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition](https://mlsanity.com/paper/2212.05463/) (2022)
- [A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition](https://mlsanity.com/paper/2203.14779/) (2022)
- [Multi-modal Facial Affective Analysis based on Masked Autoencoder](https://mlsanity.com/paper/2303.10849/) (2023)
- [Audio-Visual Fusion for Emotion Recognition in the Valence-Arousal Space Using Joint Cross-Attention](https://mlsanity.com/paper/2209.09068/) (2022)
- [Recursive Joint Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognition](https://mlsanity.com/paper/2403.13659/) (2024)
- [Facial Expression Classification using Fusion of Deep Neural Network in Video for the 3rd ABAW3 Competition](https://mlsanity.com/paper/2203.12899/) (2022)
- [Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation](https://mlsanity.com/paper/2403.12425/) (2024)
- [Analysis of Semi-Supervised Methods for Facial Expression Recognition](https://mlsanity.com/paper/2208.00544/) (2022)
- [A Survey of Historical Learning: Learning Models with Learning History](https://mlsanity.com/paper/2303.12992/) (2023)
- [Contrastive Learning of View-Invariant Representations for Facial Expressions Recognition](https://mlsanity.com/paper/2311.06852/) (2023)
- [A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognition](https://mlsanity.com/paper/2607.16285/) (2026)
- [Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations](https://mlsanity.com/paper/2107.04746/) (2021)
- [Strength-Parity Ensembling with Parameter-Isolated Experts for Multi-Task Affect Recognition](https://mlsanity.com/paper/2607.16290/) (2026)

## Abstract (arXiv)

Affective Behavior Analysis is an important part in human-computer interaction. Existing multi-task affective behavior recognition methods suffer from the problem of incomplete labeled datasets. To tackle this problem, this paper presents a semi-supervised model with a mean teacher framework to leverage additional unlabeled data. To be specific, a multi-task model is proposed to learn three different kinds of facial affective representations simultaneously. After that, the proposed model is assigned to be student and teacher networks. When training with unlabeled data, the teacher network is employed to predict pseudo labels for student network training, which allows it to learn from unlabeled data. Experimental results showed that our proposed method achieved much better performance than baseline model and ranked 4th in both competition track 1 and track 2, and 6th in track 3, which verifies that the proposed network can effectively learn from incomplete datasets.