Regression-based intensity estimation of facial action units

Savran, Arman; Sankur, B.; Bilge, M. Taha

doi:10.1016/j.imavis.2011.11.008

Cited by 123 publications

(82 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised Descent Regression (SDR) [6], Cascade Fern Regression (CFR) [7], and Random Forest Regression (RFR) [4] have been established to deal with face alignment on 2D face images. However, most regression-based methods [5,[8][9][10] refine an initial landmark location iteratively, and the performance under some challenging conditions such as illumination changes are not very satisfactory.…”

Section: Facial Landmarking On 2d Imagesmentioning

confidence: 99%

See 1 more Smart Citation

A Coarse-to-Fine Approach for 3D Facial Landmarking by Using Deep Feature Fusion

et al. 2018

View full text Add to dashboard Cite

Facial landmarking locates the key facial feature points on facial data, which provides not only information on semantic facial structures, but also prior knowledge for other kinds of facial analysis. However, most of the existing works still focus on the 2D facial image which may suffer from lighting condition variations. In order to address this limitation, this paper presents a coarse-to-fine approach to accurately and automatically locate the facial landmarks by using deep feature fusion on 3D facial geometry data. Specifically, the 3D data is converted to 2D attribute maps firstly. Then, the global estimation network is trained to predict facial landmarks roughly by feeding the fused CNN (Convolutional Neural Network) features extracted from facial attribute maps. After that, input the local fused CNN features extracted from the local patch around each landmark estimated previously, and other local models are trained separately to refine the locations. Tested on the Bosphorus and BU-3DFE datasets, the experimental results demonstrated effectiveness and accuracy of the proposed method for locating facial landmarks. Compared with existed methods, our results have achieved state-of-the-art performance.

show abstract

Section: Facial Landmarking On 2d Imagesmentioning

confidence: 99%

“…Recently, most studies on face alignment are still primarily conducted on texture images [1][2][3][4][5][6][7][8][9][10]. As known, 2D face images are rather sensitive to some condition changes such as arbitrary pose and illumination variations.…”

Section: Introductionmentioning

confidence: 99%

A Coarse-to-Fine Approach for 3D Facial Landmarking by Using Deep Feature Fusion

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Based on the modeling approach, these can be divided into static methods (Mahoor et al 2009, Mavadati et al 2013, Savrana et al 2012, Kaltwang et al 2012, Jeni et al 2013) and dynamic methods (Rudovic et al 2013b). The static methods can further be divided into classification-based methods (e.g., (Mahoor et al 2009, Mavadati et al 2013) and regression-based (e.g, (Savrana et al 2012, Kaltwang et al 2012, Jeni et al 2013). The static classification-based methods (Mahoor et al 2009, Mavadati et al 2013) perform multi-class classification of the intensity of AUs using the SVM classifier.…”

Section: Intensity Estimation Of Facial Expressionsmentioning

confidence: 99%

“…On the other hand, the static regression-based methods model the intensity of AUs on a continuous scale, using either logistic regression (Savrana et al 2012), RVM regression (Kaltwang et al 2012), or Support Vector Regression (SVR) (Jeni et al 2013). For instance, (Savrana et al 2012) used Logistic Regression for AU intensity estimation, where the input features were selected by applying an AdaBoost-based method to the Gabor wavelet magnitudes of 2D luminance and 3D geometry extracted from the target images. (Kaltwang et al 2012) used the RVM model for intensity estimation of 11 AUs using image features such as Local Binary Patterns (LBPs), Discrete Cosine Transform (DCT) and the geometric features (i.e.…”

Section: Intensity Estimation Of Facial Expressionsmentioning

confidence: 99%

Machine Learning Methods for Social Signal Processing

Rudovic

Nicolaou

Pavlović

2017

Social Signal Processing

View full text Add to dashboard Cite

“…Specifically, the authors defined the context covariate effects that encode the person's characteristics (extracted from the first neutral frame in an image sequence of the varying facial AU intensity), and context-free covariate effects (as those used in generic models and obtained by subtracting the first frame in the sequence from the rest). These were then jointly modeled in the cs-CORF model, outperforming generic CORF and other generic classification models [3,17,18]. However, a downside of this approach is that the identity features are derived from each sequence separately, thus, not capturing the commonalities of target person among multiple sequences of the same person.…”

Section: Introductionmentioning

confidence: 99%

Personalized Modeling of Facial Action Unit Intensity

Yang

Rudovic

Pavlović

et al. 2014

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. Facial expressions depend greatly on facial morphology and expressiveness of the observed person. Recent studies have shown great improvement of the personalized over non-personalized models in variety of facial expression related tasks, such as face and emotion recognition. However, in the context of facial action unit (AU) intensity estimation, personalized modeling has been scarcely investigated. In this paper, we propose a two-step approach for personalized modeling of facial AU intensity from spontaneously displayed facial expressions. In the first step, we perform facial feature decomposition using the proposed matrix decomposition algorithm that separates the person's identity from facial expression. These two are then jointly modeled using the framework of Conditional Ordinal Random Fields, resulting in a personalized model for intensity estimation of AUs. Our experimental results show that the proposed personalized model largely outperforms non-personalized models for intensity estimation of AUs.

show abstract

Regression-based intensity estimation of facial action units

Cited by 123 publications

References 10 publications

A Coarse-to-Fine Approach for 3D Facial Landmarking by Using Deep Feature Fusion

A Coarse-to-Fine Approach for 3D Facial Landmarking by Using Deep Feature Fusion

Machine Learning Methods for Social Signal Processing

Personalized Modeling of Facial Action Unit Intensity

Contact Info

Product

Resources

About