Painful data: The UNBC-McMaster shoulder pain expression archive database

Lucey, Patrick; Cohn, Jeffrey F.; Prkachin, Kenneth M.; Solomon, Patricia; Matthews, Iain

doi:10.1109/fg.2011.5771462

Cited by 480 publications

(572 citation statements)

References 16 publications

Supporting

Mentioning

540

Contrasting

Order By: Relevance

“…As input features we used locations of 66 facial landmarks (see Fig.2) provided by the database creators, and obtained using a 2D Active Appearance Model (2D-AAM) [27]. In the pre-processing step, the facial points were aligned to the corresponding reference face (the average face from the dataset) by applying an affine transform.…”

Section: Methodsmentioning

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

Section: Methodsmentioning

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

show abstract

“…Recent release of the pain-intensity coded data (Lucey et al 2011) has motivated research into automated estimation of the pain intensity levels (Hammal & Cohn 2012, Kaltwang et al 2012, Rudovic et al 2013a). For example, (Hammal & Cohn 2012) performed estimation of 4 pain intensity levels, with the levels greater than 3 on the 16-level scale being grouped together.…”

Section: Intensity Estimation Of Facial Expressionsmentioning

confidence: 99%

“…The frame-based methods for classification of facial expressions of six-basic emotion categories (Ekman et al 2002) typically employ static classifiers such as rule-based classifiers (Pantic & Rothkrantz 2004, Black & Yacoob 1997, Neural Networks (NN) (Padgett & Cottrell 1996, Tian 2004, Support Vector Machine (SVM) (Bartlett et al 2005, Shan et al 2009), and Bayesian Networks (BN) (Cohen et al 2003). SVMs and its probabilistic counterpart, Relevance Vector Machine (RVM), have been used for classification of facial expressions of pain (Lucey et al 2011, Gholami et al 2009). For instance, (Lucey et al 2011) addressed the problem of pain detection by applying SVMs either directly to the image features or by applying a two-step approach, where AUs were first detected using SVMs, the outputs of which were then fused using the Logistic Regression model.…”

Section: Facial Expression Analysismentioning

confidence: 99%

“…SVMs and its probabilistic counterpart, Relevance Vector Machine (RVM), have been used for classification of facial expressions of pain (Lucey et al 2011, Gholami et al 2009). For instance, (Lucey et al 2011) addressed the problem of pain detection by applying SVMs either directly to the image features or by applying a two-step approach, where AUs were first detected using SVMs, the outputs of which were then fused using the Logistic Regression model. Similarly, for the static classification of AUs, where the goal is to assign to each AU a binary label indicating the presence of an AU, the classifiers based on NN (Bazzo & Lamar 2004, Fasel & Luettin 2000, Ensemble Learning techniques (such as AdaBoost (Yang et al 2009a) and GentleBoost (Hamm et al 2011)), and SVM (Chew et al 2012, Bartlett et al 2006, are commonly employed.…”

Section: Facial Expression Analysismentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Methods for Social Signal Processing

Rudovic

Nicolaou

Pavlović

2017

Social Signal Processing

View full text Add to dashboard Cite

“…The latter are based on Prkachin and Solomons Pain Intensity Metric [11]. Ordinal pain scores are computed as the sum of specific AU intensities or directly from facial features [12]. These approaches all seek to detect ordinal level intensity.…”

Section: Introductionmentioning

confidence: 99%

Continuous AU intensity estimation using localized, sparse facial feature space

Jeni

Girard

Cohn

et al. 2013

2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

Self Cite

View full text Add to dashboard Cite

Abstract-Most work in automatic facial expression analysis seeks to detect discrete facial actions. Yet, the meaning and function of facial actions often depends in part on their intensity. We propose a part-based, sparse representation for automated measurement of continuous variation in AU intensity. We evaluated its effectiveness in two publically available databases, CK+ and the soon to be released Binghamton high-resolution spontaneous 3D dyadic facial expression database. The former consists of posed facial expressions and ordinal level intensity (absent, low, and high). The latter consists of spontaneous facial expression in response to diverse, well-validated emotion inductions, and 6 ordinal levels of AU intensity.In a preliminary test, we started from discrete emotion labels and ordinal-scale intensity annotation in the CK+ dataset. The algorithm achieved state-of-the-art performance. These preliminary results supported the utility of the part-based, sparse representation. Second, we applied the algorithm to the more demanding task of continuous AU intensity estimation in spontaneous facial behavior in the Binghamton database. Manual 6-point ordinal coding and continuous measurement were highly consistent. Visual analysis of the overlay of continuous measurement by the algorithm and manual ordinal coding strongly supported the representational power of the proposed method to smoothly interpolate across the full range of AU intensity.

show abstract

Painful data: The UNBC-McMaster shoulder pain expression archive database

Cited by 480 publications

References 16 publications

Personalized Modeling of Facial Action Unit Intensity

Personalized Modeling of Facial Action Unit Intensity

Machine Learning Methods for Social Signal Processing

Continuous AU intensity estimation using localized, sparse facial feature space

Contact Info

Product

Resources

About