A Preliminary Investigation of ERP Components of Attentional Bias in Anxious Adults Using Temporospatial Principal Component Analysis

Threat-related attention bias is thought to contribute to the development and maintenance of anxiety disorders. Dot-probe studies using event-related potentials (ERPs) have indicated that several early ERP components are modulated by threatening and emotional stimuli in anxious populations, suggesting enhanced allocation of attention to threat and emotion at earlier stages of processing. However, ERP components selected for examination and analysis in these studies vary widely and remain inconsistent. The present study used temporospatial principal component analysis (PCA) to systematically identify ERP components elicited to face pair cues and probes in a dot-probe task in anxious adults. Cue-locked components sensitive to emotion included an early occipital C1 component enhanced for happy versus angry face pair cues and an early parieto-occipital P1 component enhanced for happy versus angry face pair cues. Probe-locked components sensitive to congruency included a parieto-occipital P2 component enhanced for incongruent probes (probes replacing neutral faces) versus congruent probes (probes replacing emotional faces). Split-half correlations indicated that the mean value around the PCA-derived peaks was reliably measured in the ERP waveforms. These results highlight promising neurophysiological markers for attentional bias research that can be extended to designs comparing anxious and healthy comparison groups. Results from a secondary exploratory PCA analysis investigating the effects of emotional face position and analyses on behavioral reaction time data are also presented.

Predominance of eyes and surface information for face race categorization

Faces can be categorized in various ways, for example as male or female or as belonging to a specific biogeographic ancestry (race). Here we tested the importance of the main facial features for race perception. We exchanged inner facial features (eyes, mouth or nose), face contour (everything but those) or texture (surface information) between Asian and Caucasian faces. Features were exchanged one at a time, creating for each Asian/Caucasian face pair ten facial variations of the original face pair. German and Korean participants performed a race classification task on all faces presented in random order. The results show that eyes and texture are major determinants of perceived biogeographic ancestry for both groups of participants and for both face types. Inserting these features in a face of another race changed its perceived biogeographic ancestry. Contour, nose and mouth, in that order, had decreasing and much weaker influence on race perception for both participant groups. Exchanging those features did not induce a change of perceived biogeographic ancestry. In our study, all manipulated features were imbedded in natural looking faces, which were shown in an off-frontal view. Our findings confirm and extend previous studies investigating the importance of various facial features for race perception.

Learning face similarities for face verification using hybrid convolutional neural networks

<span>Face verification focuses on the task of determining whether two face images belong to the same identity or not. For unrestricted faces in the wild, this is a very challenging task. Besides significant degradation due to images that have large variations in pose, illumination, expression, aging, and occlusions, it also suffers from large-scale ever-expanding data needed to perform one-to-many recognition task. In this paper, we propose a face verification method by learning face similarities using a Convolutional Neural Networks (ConvNet). Instead of extracting features from each face image separately, our ConvNet model jointly extracts relational visual features from two face images in comparison. We train four hybrid ConvNet models to learn how to distinguish similarities between the face pair of four different face portions and join them at top-layer classifier level. We use binary-class classifier at top-layer level to identify the similarity of face pairs which includes a conventional Multi-Layer Perceptron (MLP), Support Vector Machines (SVM), Native Bayes, and another ConvNet. There are 3 face pairing configurations discussed in this paper. Results from experiments using Labeled face in the Wild (LFW) and CelebA datasets indicate that our hybrid ConvNet increases the face verification accuracy by as much as 27% when compared to individual ConvNet approach. We also found that Lateral face pair configuration yields the best LFW test accuracy on a very strict test protocol without any face alignment using MLP as top-layer classifier at 87.89%, which on-par with the state-of-the-arts. We showed that our approach is more flexible in terms of inferencing the learned models on out-of-sample data by testing LFW and CelebA on either model.</span>

A Novel Approach to Face Verification Based on Second-Order Face-Pair Representation

Face representation and matching are two essential issues in face verification task. Various approaches have been proposed focusing on these two issues. However, few of them addressed the joint optimal solutions of these two issues in a unified framework. In this paper, we present a second-order face representation method for face pair and a unified face verification framework, in which the feature extractors and the subsequent binary classification model design can be selected flexibly. Our contributions can be summarized in the following aspects. First, a novel face-pair representation method that employs the second-order statistical property of the face pairs is proposed, which retains more information compared to the existing methods. Second, a flexible binary classification model, which differs from the conventionally used metric learning, is constructed based on the new face-pair representation. Finally, we verify that our proposed face-pair representation can benefit from large training datasets. All the experiments are carried out on Labeled Face in the Wild (LFW) to verify the algorithm’s effectiveness against challenging uncontrolled conditions.