Linear Disentangled Representation Learning for Facial Actions

TL;DR

This paper introduces a simple linear model that effectively disentangles facial action signals from face videos without extensive training data, achieving competitive results in facial expression and action unit recognition.

Contribution

The paper proposes a novel linear model leveraging low-rank and sparse representations to disentangle facial actions from neutral faces in videos, reducing data requirements.

Findings

Competitive performance on CK+ dataset

Outperforms SRC in true positive rate

Effective on challenging facial action unit recognition

Abstract

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.