Video-Based Elevated Skin Temperature Detection.

In this work, we propose a non-contact video-based approach that detects when an individual's skin temperature is elevated beyond the normal range. The detection of elevated skin temperature is critical as a diagnostic tool to infer the presence of an infection or an abnormal health condition. Detection of elevated skin temperature is typically achieved using contact thermometers or non-contact infrared-based sensors. The ubiquity of video data acquisition devices such as mobile phones and computers motivates the development of a binary classification approach, the Video-based TEMPerature (V-TEMP) to classify subjects with non-elevated/elevated skin temperature. We leverage the correlation between the skin temperature and the angular reflectance distribution of light, to empirically differentiate between skin at non-elevated temperature and skin at elevated temperature. We demonstrate the uniqueness of this correlation by 1) revealing the existence of a difference in the angular reflectance distribution of light from skin-like and non-skin like material and 2) exploring the consistency of the angular reflectance distribution of light in materials exhibiting optical properties similar to human skin. Finally, we demonstrate the robustness of V-TEMP by evaluating the efficacy of elevated skin temperature detection on subject videos recorded in 1) laboratory controlled environments and 2) outside-the-lab environments. V-TEMP is beneficial in two ways; 1) it is non-contact-based, reducing the possibility of infection due to contact and 2) it is scalable, given the ubiquity of video-recording devices.

3D Human Pose, Shape and Texture From Low-Resolution Images and Videos.

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many scenarios such as video surveillance and sports broadcasting. Two common approaches to deal with low-resolution images are applying super-resolution techniques to the input, which may result in unpleasant artifacts, or simply training one model for each resolution, which is impractical in many realistic applications. To address the above issues, this paper proposes a novel algorithm called RSC-Net, which consists of a Resolution-aware network, a Self-supervision loss, and a Contrastive learning scheme. The proposed method is able to learn 3D body pose and shape across different resolutions with one single model. The self-supervision loss enforces scale-consistency of the output, and the contrastive learning scheme enforces scale-consistency of the deep features. We show that both these new losses provide robustness when learning in a weakly-supervised manner. Moreover, we extend the RSC-Net to handle low-resolution videos and apply it to reconstruct textured 3D pedestrians from low-resolution input. Extensive experiments demonstrate that the RSC-Net can achieve consistently better results than the state-of-the-art methods for challenging low-resolution images.

Long-term ecological assessment of intracranial electrophysiology synchronized to behavioral markers in obsessive-compulsive disorder.

Detection of neural signatures related to pathological behavioral states could enable adaptive deep brain stimulation (DBS), a potential strategy for improving efficacy of DBS for neurological and psychiatric disorders. This approach requires identifying neural biomarkers of relevant behavioral states, a task best performed in ecologically valid environments. Here, in human participants with obsessive-compulsive disorder (OCD) implanted with recording-capable DBS devices, we synchronized chronic ventral striatum local field potentials with relevant, disease-specific behaviors. We captured over 1,000 h of local field potentials in the clinic and at home during unstructured activity, as well as during DBS and exposure therapy. The wide range of symptom severity over which the data were captured allowed us to identify candidate neural biomarkers of OCD symptom intensity. This work demonstrates the feasibility and utility of capturing chronic intracranial electrophysiology during daily symptom fluctuations to enable neural biomarker identification, a prerequisite for future development of adaptive DBS for OCD and other psychiatric disorders.

Evaluation of biases in remote photoplethysmography methods.

This work investigates the estimation biases of remote photoplethysmography (rPPG) methods for pulse rate measurement across diverse demographics. Advances in photoplethysmography (PPG) and rPPG methods have enabled the development of contact and noncontact approaches for continuous monitoring and collection of patient health data. The contagious nature of viruses such as COVID-19 warrants noncontact methods for physiological signal estimation. However, these approaches are subject to estimation biases due to variations in environmental conditions and subject demographics. The performance of contact-based wearable sensors has been evaluated, using off-the-shelf devices across demographics. However, the measurement uncertainty of rPPG methods that estimate pulse rate has not been sufficiently tested across diverse demographic populations or environments. Quantifying the efficacy of rPPG methods in real-world conditions is critical in determining their potential viability as health monitoring solutions. Currently, publicly available face datasets accompanied by physiological measurements are typically captured in controlled laboratory settings, lacking diversity in subject skin tones, age, and cultural artifacts (e.g, bindi worn by Indian women). In this study, we collect pulse rate and facial video data from human subjects in India and Sierra Leone, in order to quantify the uncertainty in noncontact pulse rate estimation methods. The video data are used to estimate pulse rate using state-of-the-art rPPG camera-based methods, and compared against ground truth measurements captured using an FDA-approved contact-based pulse rate measurement device. Our study reveals that rPPG methods exhibit similar biases when compared with a contact-based device across demographic groups and environmental conditions. The mean difference between pulse rates measured by rPPG methods and the ground truth is found to be ~2% (1 beats per minute (b.p.m.)), signifying agreement of rPPG methods with the ground truth. We also find that rPPG methods show pulse rate variability of ~15% (11 b.p.m.), as compared to the ground truth. We investigate factors impacting rPPG methods and discuss solutions aimed at mitigating variance.

Synthetic Expressions are Better Than Real for Learning to Detect Facial Actions.

Critical obstacles in training classifiers to detect facial actions are the limited sizes of annotated video databases and the relatively low frequencies of occurrence of many actions. To address these problems, we propose an approach that makes use of facial expression generation. Our approach reconstructs the 3D shape of the face from each video frame, aligns the 3D mesh to a canonical view, and then trains a GAN-based network to synthesize novel images with facial action units of interest. To evaluate this approach, a deep neural network was trained on two separate datasets: One network was trained on video of synthesized facial expressions generated from FERA17; the other network was trained on unaltered video from the same database. Both networks used the same train and validation partitions and were tested on the test partition of actual video from FERA17. The network trained on synthesized facial expressions outperformed the one trained on actual facial expressions and surpassed current state-of-the-art approaches.

Crossing Domains for AU Coding: Perspectives, Approaches, and Measures.

Facial action unit (AU) detectors have performed well when trained and tested within the same domain. How well do AU detectors transfer to domains in which they have not been trained? We review literature on cross-domain transfer and conduct experiments to address limitations of prior research. We evaluate generalizability in four publicly available databases. EB+ (an expanded version of BP4D+), Sayette GFT, DISFA and UNBC Shoulder Pain (SP). The databases differ in observational scenarios, context, participant diversity, range of head pose, video resolution, and AU base rates. In most cases performance decreased with change in domain, often to below the threshold needed for behavioral research. However, exceptions were noted. Deep and shallow approaches generally performed similarly and average results were slightly better for deep model compared to shallow one. Occlusion sensitivity maps revealed that local specificity was greater for AU detection within than cross domains. The findings suggest that more varied domains and deep learning approaches may be better suited for generalizability and suggest the need for more attention to characteristics that vary between domains. Until further improvement is realized, caution is warranted when applying AU classifiers from one domain to another.

Automated Detection of Enhanced DBS Device Settings.

Continuous deep brain stimulation (DBS) of the ventral striatum (VS) is an effective treatment for severe, treatment-refractory obsessive-compulsive disorder (OCD). Optimal parameter settings are signaled by a mirth response of intense positive affect, which are subjectively identified by clinicians. Subjective judgments are idiosyncratic and difficult to standardize. To objectively measure mirth responses, we used Automatic Facial Affect Recognition (AFAR) in a series of longitudinal assessments of a patient treated with DBS. Pre- and post-adjustment DBS were compared using both statistical and machine learning approaches. Positive affect was significantly higher post-DBS adjustment. Using SVM and XGBoost, participant's pre- and post-adjustment appearances were differentiated with F1 of 0.76, which suggests feasibility of objective measurement of mirth response.

Cross-domain AU Detection: Domains, Learning Approaches, and Measures.

Facial action unit (AU) detectors have performed well when trained and tested within the same domain. Do AU detectors transfer to new domains in which they have not been trained? To answer this question, we review literature on cross-domain transfer and conduct experiments to address limitations of prior research. We evaluate both deep and shallow approaches to AU detection (CNN and SVM, respectively) in two large, well-annotated, publicly available databases, Expanded BP4D+ and GFT. The databases differ in observational scenarios, participant characteristics, range of head pose, video resolution, and AU base rates. For both approaches and databases, performance decreased with change in domain, often to below the threshold needed for behavioral research. Decreases were not uniform, however. They were more pronounced for GFT than for Expanded BP4D+ and for shallow relative to deep learning. These findings suggest that more varied domains and deep learning approaches may be better suited for promoting generalizability. Until further improvement is realized, caution is warranted when applying AU classifiers from one domain to another.

Unmasking the Devil in the Details: What Works for Deep Facial Action Coding?

The performance of automated facial expression coding has improving steadily as evidenced by results of the latest Facial Expression Recognition and Analysis (FERA 2017) Challenge. Advances in deep learning techniques have been key to this success. Yet the contribution of critical design choices remains largely unknown. Using the FERA 2017 database, we systematically evaluated design choices in pre-training, feature alignment, model size selection, and optimizer details. Our findings vary from the counter-intuitive (e.g., generic pre-training outperformed face-specific models) to best practices in tuning optimizers. Informed by what we found, we developed an architecture that exceeded state-of-the-art on FERA 2017. We achieved a 3.5% increase in F1 score for occurrence detection and a 5.8% increase in ICC for intensity estimation.

D-PAttNet: Dynamic Patch-Attentive Deep Network for Action Unit Detection.

Facial action units (AUs) relate to specific local facial regions. Recent efforts in automated AU detection have focused on learning the facial patch representations to detect specific AUs. These efforts have encountered three hurdles. First, they implicitly assume that facial patches are robust to head rotation; yet non-frontal rotation is common. Second, mappings between AUs and patches are defined a priori, which ignores co-occurrences among AUs. And third, the dynamics of AUs are either ignored or modeled sequentially rather than simultaneously as in human perception. Inspired by recent advances in human perception, we propose a dynamic patch-attentive deep network, called D-PAttNet, for AU detection that (i) controls for 3D head and face rotation, (ii) learns mappings of patches to AUs, and (iii) models spatiotemporal dynamics. D-PAttNet approach significantly improves upon existing state of the art.

Automated Affect Detection in Deep Brain Stimulation for Obsessive-Compulsive Disorder: A Pilot Study.

Automated measurement of affective behavior in psychopathology has been limited primarily to screening and diagnosis. While useful, clinicians more often are concerned with whether patients are improving in response to treatment. Are symptoms abating, is affect becoming more positive, are unanticipated side effects emerging? When treatment includes neural implants, need for objective, repeatable biometrics tied to neurophysiology becomes especially pressing. We used automated face analysis to assess treatment response to deep brain stimulation (DBS) in two patients with intractable obsessive-compulsive disorder (OCD). One was assessed intraoperatively following implantation and activation of the DBS device. The other was assessed three months post-implantation. Both were assessed during DBS on and o conditions. Positive and negative valence were quantified using a CNN trained on normative data of 160 non-OCD participants. Thus, a secondary goal was domain transfer of the classifiers. In both contexts, DBS-on resulted in marked positive affect. In response to DBS-off, affect flattened in both contexts and alternated with increased negative affect in the outpatient setting. Mean AUC for domain transfer was 0.87. These findings suggest that parametric variation of DBS is strongly related to affective behavior and may introduce vulnerability for negative affect in the event that DBS is discontinued.

Viewpoint-Consistent 3D Face Alignment.

Most approaches to face alignment treat the face as a 2D object, which fails to represent depth variation and is vulnerable to loss of shape consistency when the face rotates along a 3D axis. Because faces commonly rotate three dimensionally, 2D approaches are vulnerable to significant error. 3D morphable models, employed as a second step in 2D+3D approaches are robust to face rotation but are computationally too expensive for many applications, yet their ability to maintain viewpoint consistency is unknown. We present an alternative approach that estimates 3D face landmarks in a single face image. The method uses a regression forest-based algorithm that adds a third dimension to the common cascade pipeline. 3D face landmarks are estimated directly, which avoids fitting a 3D morphable model. The proposed method achieves viewpoint consistency in a computationally efficient manner that is robust to 3D face rotation. To train and test our approach, we introduce the Multi-PIE Viewpoint Consistent database. In empirical tests, the proposed method achieved simple yet effective head pose estimation and viewpoint consistency on multiple measures relative to alternative approaches.

Sayette Group Formation Task (GFT) Spontaneous Facial Expression Database.

Despite the important role that facial expressions play in interpersonal communication and our knowledge that interpersonal behavior is influenced by social context, no currently available facial expression database includes multiple interacting participants. The Sayette Group Formation Task (GFT) database addresses the need for well-annotated video of multiple participants during unscripted interactions. The database includes 172,800 video frames from 96 participants in 32 three-person groups. To aid in the development of automated facial expression analysis systems, GFT includes expert annotations of FACS occurrence and intensity, facial landmark tracking, and baseline results for linear SVM, deep learning, active patch learning, and personalized classification. Baseline performance is quantified and compared using identical partitioning and a variety of metrics (including means and confidence intervals). The highest performance scores were found for the deep learning and active patch learning methods. Learn more at http://osf.io/7wcyz.

FERA 2017 - Addressing Head Pose in the Third Facial Expression Recognition and Analysis Challenge.

The field of Automatic Facial Expression Analysis has grown rapidly in recent years. However, despite progress in new approaches as well as benchmarking efforts, most evaluations still focus on either posed expressions, near-frontal recordings, or both. This makes it hard to tell how existing expression recognition approaches perform under conditions where faces appear in a wide range of poses (or camera views), displaying ecologically valid expressions. The main obstacle for assessing this is the availability of suitable data, and the challenge proposed here addresses this limitation. The FG 2017 Facial Expression Recognition and Analysis challenge (FERA 2017) extends FERA 2015 to the estimation of Action Units occurrence and intensity under different camera views. In this paper we present the third challenge in automatic recognition of facial expressions, to be held in conjunction with the 12th IEEE conference on Face and Gesture Recognition, May 2017, in Washington, United States. Two sub-challenges are defined: the detection of AU occurrence, and the estimation of AU intensity. In this work we outline the evaluation protocol, the data used, and the results of a baseline method for both sub-challenges.

Dense 3D Face Alignment from 2D Video for Real-Time Use.

To enable real-time, person-independent 3D registration from 2D video, we developed a 3D cascade regression approach in which facial landmarks remain invariant across pose over a range of approximately 60 degrees. From a single 2D image of a person's face, a dense 3D shape is registered in real time for each frame. The algorithm utilizes a fast cascade regression framework trained on high-resolution 3D face-scans of posed and spontaneous emotion expression. The algorithm first estimates the location of a dense set of landmarks and their visibility, then reconstructs face shapes by fitting a part-based 3D model. Because no assumptions are required about illumination or surface properties, the method can be applied to a wide range of imaging conditions that include 2D video and uncalibrated multi-view video. The method has been validated in a battery of experiments that evaluate its precision of 3D reconstruction, extension to multi-view reconstruction, temporal integration for videos and 3D head-pose estimation. Experimental findings strongly support the validity of real-time, 3D registration and reconstruction from 2D video. The software is available online at http://zface.org.

How much training data for facial action unit detection?

By systematically varying the number of subjects and the number of frames per subject, we explored the influence of training set size on appearance and shape-based approaches to facial action unit (AU) detection. Digital video and expert coding of spontaneous facial activity from 80 subjects (over 350,000 frames) were used to train and test support vector machine classifiers. Appearance features were shape-normalized SIFT descriptors and shape features were 66 facial landmarks. Ten-fold cross-validation was used in all evaluations. Number of subjects and number of frames per subject differentially affected appearance and shape-based classifiers. For appearance features, which are high-dimensional, increasing the number of training subjects from 8 to 64 incrementally improved performance, regardless of the number of frames taken from each subject (ranging from 450 through 3600). In contrast, for shape features, increases in the number of training subjects and frames were associated with mixed results. In summary, maximal performance was attained using appearance features from large numbers of subjects with as few as 450 frames per subject. These findings suggest that variation in the number of subjects rather than number of frames per subject yields most efficient performance.

Dense 3D Face Alignment from 2D Videos in Real-Time.

To enable real-time, person-independent 3D registration from 2D video, we developed a 3D cascade regression approach in which facial landmarks remain invariant across pose over a range of approximately 60 degrees. From a single 2D image of a person's face, a dense 3D shape is registered in real time for each frame. The algorithm utilizes a fast cascade regression framework trained on high-resolution 3D face-scans of posed and spontaneous emotion expression. The algorithm first estimates the location of a dense set of markers and their visibility, then reconstructs face shapes by fitting a part-based 3D model. Because no assumptions are required about illumination or surface properties, the method can be applied to a wide range of imaging conditions that include 2D video and uncalibrated multi-view video. The method has been validated in a battery of experiments that evaluate its precision of 3D reconstruction and extension to multi-view reconstruction. Experimental findings strongly support the validity of real-time, 3D registration and reconstruction from 2D video. The software is available online at http://zface.org.

Spontaneous facial expression in unscripted social interactions can be measured automatically.

Methods to assess individual facial actions have potential to shed light on important behavioral phenomena ranging from emotion and social interaction to psychological disorders and health. However, manual coding of such actions is labor intensive and requires extensive training. To date, establishing reliable automated coding of unscripted facial actions has been a daunting challenge impeding development of psychological theories and applications requiring facial expression assessment. It is therefore essential that automated coding systems be developed with enough precision and robustness to ease the burden of manual coding in challenging data involving variation in participant gender, ethnicity, head pose, speech, and occlusion. We report a major advance in automated coding of spontaneous facial actions during an unscripted social interaction involving three strangers. For each participant (n = 80, 47 % women, 15 % Nonwhite), 25 facial action units (AUs) were manually coded from video using the Facial Action Coding System. Twelve AUs occurred more than 3 % of the time and were processed using automated FACS coding. Automated coding showed very strong reliability for the proportion of time that each AU occurred (mean intraclass correlation = 0.89), and the more stringent criterion of frame-by-frame reliability was moderate to strong (mean Matthew's correlation = 0.61). With few exceptions, differences in AU detection related to gender, ethnicity, pose, and average pixel intensity were small. Fewer than 6 % of frames could be coded manually but not automatically. These findings suggest automated FACS coding has progressed sufficiently to be applied to observational research in emotion and related areas of study.

Spatio-temporal Event Classification using Time-series Kernel based Structured Sparsity.

In many behavioral domains, such as facial expression and gesture, sparse structure is prevalent. This sparsity would be well suited for event detection but for one problem. Features typically are confounded by alignment error in space and time. As a consequence, high-dimensional representations such as SIFT and Gabor features have been favored despite their much greater computational cost and potential loss of information. We propose a Kernel Structured Sparsity (KSS) method that can handle both the temporal alignment problem and the structured sparse reconstruction within a common framework, and it can rely on simple features. We characterize spatio-temporal events as time-series of motion patterns and by utilizing time-series kernels we apply standard structured-sparse coding techniques to tackle this important problem. We evaluated the KSS method using both gesture and facial expression datasets that include spontaneous behavior and differ in degree of difficulty and type of ground truth coding. KSS outperformed both sparse and non-sparse methods that utilize complex image features and their temporal extensions. In the case of early facial event classification KSS had 10% higher accuracy as measured by F1 score over kernel SVM methods.