# Self-Supervised Regional and Temporal Auxiliary Tasks for Facial Action Unit Recognition

arXiv: https://arxiv.org/abs/2107.14399 · HTML: https://mlsanity.com/paper/2107.14399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 30 Jul 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [Revisiting Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1901.09005/) (2019)
- [Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment](https://mlsanity.com/paper/1803.05588/) (2018)
- [Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition](https://mlsanity.com/paper/1904.09939/) (2019)
- [Self-supervised learning of a facial attribute embedding from video](https://mlsanity.com/paper/1808.06882/) (2018)
- [Deep Structure Inference Network for Facial Action Unit Recognition](https://mlsanity.com/paper/1803.05873/) (2018)
- [Action Unit Detection with Region Adaptation, Multi-labeling Learning and Optimal Temporal Fusing](https://mlsanity.com/paper/1704.03067/) (2017)
- [Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition](https://mlsanity.com/paper/1910.11012/) (2019)
- [Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection](https://mlsanity.com/paper/1910.10334/) (2019)
- [Multi-Level Adaptive Region of Interest and Graph Learning for Facial Action Unit Recognition](https://mlsanity.com/paper/2102.12154/) (2021)
- [Modeling Spatial and Temporal Cues for Multi-label Facial Action Unit Detection](https://mlsanity.com/paper/1608.00911/) (2016)

## Built on by (most cited first, 1 of 1)

- [Self-supervised Facial Action Unit Detection with Region and Relation Learning](https://mlsanity.com/paper/2303.05708/) (2023)

## Abstract (arXiv)

Automatic facial action unit (AU) recognition is a challenging task due to the scarcity of manual annotations. To alleviate this problem, a large amount of efforts has been dedicated to exploiting various methods which leverage numerous unlabeled data. However, many aspects with regard to some unique properties of AUs, such as the regional and relational characteristics, are not sufficiently explored in previous works. Motivated by this, we take the AU properties into consideration and propose two auxiliary AU related tasks to bridge the gap between limited annotations and the model performance in a self-supervised manner via the unlabeled data. Specifically, to enhance the discrimination of regional features with AU relation embedding, we design a task of RoI inpainting to recover the randomly cropped AU patches. Meanwhile, a single image based optical flow estimation task is proposed to leverage the dynamic change of facial muscles and encode the motion information into the global feature representation. Based on these two self-supervised auxiliary tasks, local features, mutual relation and motion cues of AUs are better captured in the backbone network with the proposed regional and temporal based auxiliary task learning (RTATL) framework. Extensive experiments on BP4D and DISFA demonstrate the superiority of our method and new state-of-the-art performances are achieved.