# Choose Settings Carefully: Comparing Action Unit detection at Different Settings Using a Large-Scale Dataset

arXiv: https://arxiv.org/abs/2111.08324 · HTML: https://mlsanity.com/paper/2111.08324/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 16 Nov 2021.

## Builds on (most cited first, 4 of 4)

- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [A Compact Embedding for Facial Expression Similarity](https://mlsanity.com/paper/1811.11283/) (2018)
- [EmoNets: Multimodal deep learning approaches for emotion recognition in video](https://mlsanity.com/paper/1503.01800/) (2015)
- [SchiNet: Automatic Estimation of Symptoms of Schizophrenia from Facial Behaviour Analysis](https://mlsanity.com/paper/1808.02531/) (2018)

## Built on by (most cited first, 2 of 2)

- [AFFDEX 2.0: A Real-Time Facial Expression Analysis Toolkit](https://mlsanity.com/paper/2202.12059/) (2022)
- [Automatic Detection of Sentimentality from Facial Expressions](https://mlsanity.com/paper/2209.04908/) (2022)

## Abstract (arXiv)

In this paper, we investigate the impact of some of the commonly used settings for (a) preprocessing face images, and (b) classification and training, on Action Unit (AU) detection performance and complexity. We use in our investigation a large-scale dataset, consisting of ~55K videos collected in the wild for participants watching commercial ads. The preprocessing settings include scaling the face to a fixed resolution, changing the color information (RGB to gray-scale), aligning the face, and cropping AU regions, while the classification and training settings include the kind of classifier (multi-label vs. binary) and the amount of data used for training models. To the best of our knowledge, no work had investigated the effect of those settings on AU detection. In our analysis we use CNNs as our baseline classification model.