Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, we propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network. This leads to StarGAN's superior quality of translated images compared to existing models as well as the novel capability of flexibly translating an input image to any desired target domain. We empirically demonstrate the effectiveness of our approach on a facial attribute transfer and a facial expression synthesis tasks.

/pdf/stargan-unified-generative-adversarial-networks-for-multi-252sij7hgf.pdf

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

The RAVDESS is a validated multimodal database of emotional speech and song. The database is gender balanced consisting of 24 professional actors, vocalizing lexically-matched statements in a neutral North American accent. Speech includes calm, happy, sad, angry, fearful, surprise, and disgust expressions, and song contains calm, happy, sad, angry, and fearful emotions. Each expression is produced at two levels of emotional intensity, with an additional neutral expression. All conditions are available in face-and-voice, face-only, and voice-only formats. The set of 7356 recordings were each rated 10 times on emotional validity, intensity, and genuineness. Ratings were provided by 247 individuals who were characteristic of untrained research participants from North America. A further set of 72 participants provided test-retest data. High levels of emotional validity and test-retest intrarater reliability were reported. Corrected accuracy and composite "goodness" measures are presented to assist researchers in the selection of stimuli. All recordings are made freely available under a Creative Commons license and can be downloaded at https://doi.org/10.5281/zenodo.1188976.

/pdf/the-ryerson-audio-visual-database-of-emotional-speech-and-jx71tsx3ts.pdf

The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English

Eye tracking of attention in the affective disorders: a meta-analytic review and synthesis.

With the transition of facial expression recognition (FER) from laboratory-controlled to challenging in-the-wild conditions and the recent success of deep learning techniques in various fields, deep neural networks have increasingly been leveraged to learn discriminative representations for automatic FER. Recent deep FER systems generally focus on two important issues: overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias. In this paper, we provide a comprehensive survey on deep FER, including datasets and algorithms that provide insights into these intrinsic problems. First, we describe the standard pipeline of a deep FER system with the related background knowledge and suggestions of applicable implementations for each stage. We then introduce the available datasets that are widely used in the literature and provide accepted data selection and evaluation principles for these datasets. For the state of the art in deep FER, we review existing novel deep neural networks and related training strategies that are designed for FER based on both static images and dynamic image sequences, and discuss their advantages and limitations. Competitive performances on widely used benchmarks are also summarized in this section. We then extend our survey to additional related issues and application scenarios. Finally, we review the remaining challenges and corresponding opportunities in this field as well as future directions for the design of robust deep FER systems.

Deep Facial Expression Recognition: A Survey

Many research fields concerned with the processing of information contained in human faces would benefit from face stimulus sets in which specific facial characteristics are systematically varied while other important picture characteristics are kept constant. Specifically, a face database in which displayed expressions, gaze direction, and head orientation are parametrically varied in a complete factorial design would be highly useful in many research domains. Furthermore, these stimuli should be standardised in several important, technical aspects. The present article presents the freely available Radboud Faces Database offering such a stimulus set, containing both Caucasian adult and children images. This face database is described both procedurally and in terms of content, and a validation study concerning its most important characteristics is presented. In the validation study, all frontal images were rated with respect to the shown facial expression, intensity of expression, clarity of expression, genuineness of expression, attractiveness, and valence. The results show very high recognition of the intended facial expressions.

/pdf/presentation-and-validation-of-the-radboud-faces-database-4en3lkg4k6.pdf

Presentation and validation of the Radboud Faces Database

Prejudice biases cognition, affect, and behavior toward ethnic out-groups. We propose that prejudice also biases the way people conceptualize the facial appearance of out-group members. Popular belief holds that people's personality traits are reflected in their facial features. We hypothesized that prejudiced people also have more negatively stereotyped mental representations of faces of people in the out-group. To test this hypothesis, we conducted two studies involving the category of Moroccans, a highly stigmatized immigrant group in The Netherlands. The results of the first study suggested that highly prejudiced people have biased mental representations of Moroccan faces. We ran a second study using more trials in the image construction phase, but with an otherwise identical design, to enhance the quality of individual participants' classification images. This allowed us to replicate the findings of the first study on an individual rather than subgroup level.

Ethnic Out-Group Faces Are Biased in the Prejudiced Mind

We investigated the facial information that socially anxious and nonanxious individuals utilize to judge emotions. Using a reversed-correlation technique, we presented participants with face images that were masked with random bubble patterns. These patterns determined which parts of the face were visible in specific spatial-frequency bands. This masking allowed us to establish which locations and spatial frequencies were helping participants to successfully discriminate angry faces from neutral ones. Although socially anxious individuals performed as well as nonanxious individuals on the emotion-discrimination task, they did not utilize the same facial information for the task. The fine details (high spatial frequencies) around the eyes were discriminative for both groups, but only socially anxious participants additionally processed rough configural information (low spatial frequencies).

/pdf/social-anxiety-and-anger-identification-bubbles-reveal-27ghhbots7.pdf

Oliver Langner

Papers

Presentation and validation of the Radboud Faces Database

Ethnic Out-Group Faces Are Biased in the Prejudiced Mind

Social Anxiety and Anger Identification Bubbles Reveal Differential Use of Facial Information With Low Spatial Frequencies

Face value: Eye movements and the evaluation of facial crowds in social anxiety

Socially anxious individuals discriminate better between angry and neutral faces, particularly when using low spatial frequency information