# Action Units Recognition by Pairwise Deep Architecture

arXiv: https://arxiv.org/abs/2010.00288 · HTML: https://mlsanity.com/paper/2010.00288/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competition](https://mlsanity.com/paper/2107.03708/) (2021)
- [Action Units Recognition Using Improved Pairwise Deep Architecture](https://mlsanity.com/paper/2107.03143/) (2021)
- [Multi-modal Affect Analysis using standardized data within subjects in the Wild](https://mlsanity.com/paper/2107.03009/) (2021)
- [An Attention-based Method for Action Unit Detection at the 3rd ABAW Competition](https://mlsanity.com/paper/2203.12428/) (2022)
- [Towards an objective characterization of an individual's facial movements using Self-Supervised Person-Specific-Models](https://mlsanity.com/paper/2211.08279/) (2022)

## Abstract (arXiv)

In this paper, we propose a new automatic Action Units (AUs) recognition method used in a competition, Affective Behavior Analysis in-the-wild (ABAW). Our method tackles a problem of AUs label inconsistency among subjects by using pairwise deep architecture. While the baseline score is 0.31, our method achieved 0.67 in validation dataset of the competition.