Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles

Dibeklio, Hamdi; Lu, Chi-Jie; Salah, Albert Ali; Gevers, Theo

doi:10.1007/978-3-642-33712-3_38

Cited by 130 publications

(128 citation statements)

References 19 publications

Supporting

Mentioning

124

Contrasting

Unclassified

Order By: Relevance

“…-Detection of deceptive facial expressions Facial image analysis is an active topicnew research directions focus on facial dynamics recognition and understanding for deception detection, behavioral analysis and diagnosis of psychological disorders. Kawulok et al (2016) used fast smile intensity detectors to elaborate textural facial features that are fed into the SVM classification pipeline to distinguish between posed and spontaneous expressions in video sequences from the UvA-NEMO database containing 1240 sequences, including 643 posed and 597 spontaneous smiles (Dibeklioglu et al 2012)-see examples in Fig. 13.…”

Section: Datasets and Practical Applicationsmentioning

confidence: 99%

Selecting training sets for support vector machines: a review

2018

View full text Add to dashboard Cite

Support vector machines (SVMs) are a supervised classifier successfully applied in a plethora of real-life applications. However, they suffer from the important shortcomings of their high time and memory training complexities, which depend on the training set size. This issue is especially challenging nowadays, since the amount of data generated every second becomes tremendously large in many domains. This review provides an extensive survey on existing methods for selecting SVM training data from large datasets. We divide the state-of-the-art techniques into several categories. They help understand the underlying ideas behind these algorithms, which may be useful in designing new methods to deal with this important problem. The review is complemented with the discussion on the future research pathways which can make SVMs easier to exploit in practice.

show abstract

Section: Datasets and Practical Applicationsmentioning

confidence: 99%

Selecting training sets for support vector machines: a review

2018

View full text Add to dashboard Cite

show abstract

“…To this end, the change in facial surface deformations should be described effectively first. Since previous research [5,9] shows that facial landmark displacements can successfully describe expression dynamics, a shape-based representation is used in this study.…”

Section: Expression Matchingmentioning

confidence: 99%

“…To train and evaluate the proposed architecture for videobased kinship verification, the kinship partition [8] of the UvA-NEMO Smile Database [9] is used. It has spontaneous/posed enjoyment smiles of 95 subject pairs who have a kin relationship.…”

Section: Databasementioning

confidence: 99%

“…Since the UvA-NEMO Smile Database does not include per-frame annotations of expression intensity, following [9], the smile amplitude of each frame is estimated as the average distance of the right and left lip corners to the lip center, normalized by the length of the lip. The average correlation of smile amplitude between matched segments of each video pair is computed.…”

Section: Temporal Dynamics and Expression Matchingmentioning

confidence: 99%

See 1 more Smart Citation

Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification

Dibeklioğlu

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…Regarding real data, we employ the publicly available MMI database [32] and the UvA-Nemo Smile (UNS) [33] that display both posed and spontaneous expressions. The MMI consists of around 400 videos of 19 subjects annotated in terms of FAUs and their temporal phases, i.e., neutral, onset, apex, and offset.…”

Section: B Real Data 1: Unsupervised Au Temporal Phase Segmentationmentioning

confidence: 99%

Probabilistic Slow Features for Behavior Analysis

Zafeiriou

Nicolaou

Zafeiriou

et al. 2016

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Abstract-A recently introduced latent feature learning technique for time-varying dynamic phenomena analysis is the so-called slow feature analysis (SFA). SFA is a deterministic component analysis technique for multidimensional sequences that, by minimizing the variance of the first-order time derivative approximation of the latent variables, finds uncorrelated projections that extract slowly varying features ordered by their temporal consistency and constancy. In this paper, we propose a number of extensions in both the deterministic and the probabilistic SFA optimization frameworks. In particular, we derive a novel deterministic SFA algorithm that is able to identify linear projections that extract the common slowest varying features of two or more sequences. In addition, we propose an expectation maximization (EM) algorithm to perform inference in a probabilistic formulation of SFA and similarly extend it in order to handle two and more time-varying data sequences. Moreover, we demonstrate that the probabilistic SFA (EM-SFA) algorithm that discovers the common slowest varying latent space of multiple sequences can be combined with dynamic time warping techniques for robust sequence time-alignment. The proposed SFA algorithms were applied for facial behavior analysis, demonstrating their usefulness and appropriateness for this task. IndexTerms-Behavior analysis, linear dynamical system (LDS), slow feature analysis (SFA), temporal alignment.

show abstract

Are You Really Smiling at Me? Spontaneous versus Posed Enjoyment Smiles

Cited by 130 publications

References 19 publications

Selecting training sets for support vector machines: a review

Selecting training sets for support vector machines: a review

Visual Transformation Aided Contrastive Learning for Video-Based Kinship Verification

Probabilistic Slow Features for Behavior Analysis

Contact Info

Product

Resources

About