# Linear Disentangled Representation Learning for Facial Actions

arXiv: https://arxiv.org/abs/1701.03102 · HTML: https://mlsanity.com/paper/1701.03102/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jan 2017.

## Built on by (most cited first, 6 of 6)

- [Stimuli-Aware Visual Emotion Analysis](https://mlsanity.com/paper/2109.01812/) (2021)
- [Facial Action Unit Detection and Intensity Estimation from Self-supervised Representation](https://mlsanity.com/paper/2210.15878/) (2022)
- [Are 3D Face Shapes Expressive Enough for Recognising Continuous Emotions and Action Unit Intensities?](https://mlsanity.com/paper/2207.01113/) (2022)
- [Video-based Cross-modal Auxiliary Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2208.13954/) (2022)
- [Learning Contrastive Feature Representations for Facial Action Unit Detection](https://mlsanity.com/paper/2402.06165/) (2024)
- [Global-to-local Expression-aware Embeddings for Facial Action Unit Detection](https://mlsanity.com/paper/2210.15160/) (2022)

## Abstract (arXiv)

Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features. However, a linear model with just several parameters normally is not demanding in terms of training data. In this paper, we propose an elegant linear model to untangle confounding factors in challenging realistic multichannel signals such as 2D face videos. The simple yet powerful model does not rely on huge training data and is natural for recognizing facial actions without explicitly disentangling the identity. Base on well-understood intuitive linear models such as Sparse Representation based Classification (SRC), previous attempts require a prepossessing of explicit decoupling which is practically inexact. Instead, we exploit the low-rank property across frames to subtract the underlying neutral faces which are modeled jointly with sparse representation on the action components with group sparsity enforced. On the extended Cohn-Kanade dataset (CK+), our one-shot automatic method on raw face videos performs as competitive as SRC applied on manually prepared action components and performs even better than SRC in terms of true positive rate. We apply the model to the even more challenging task of facial action unit recognition, verified on the MPI Face Video Database (MPI-VDB) achieving a decent performance. All the programs and data have been made publicly available.