Action Unit Detection Research Articles

Dual Learning for Facial Action Unit Detection Under Nonfull Annotation.

Most methods for facial action unit (AU) recognition typically require training images that are fully AU labeled. Manual AU annotation is time intensive. To alleviate this, we propose a novel dual learning framework and apply it to AU detection under two scenarios, that is, semisupervised AU detection with partially AU-labeled and fully expression-labeled samples, and weakly supervised AU detection with fully expression-labeled samples alone. We leverage two forms of auxiliary information. The first is the probabilistic duality between the AU detection task and its dual task, in this case, the face synthesis task given AU labels. We also take advantage of the dependencies among multiple AUs, the dependencies between expression and AUs, and the dependencies between facial features and AUs. Specifically, the proposed method consists of a classifier, an image generator, and a discriminator. The classifier and generator yield face-AU-expression tuples, which are forced to coverage of the ground-truth distribution. This joint distribution also includes three kinds of inherent dependencies: 1) the dependencies among multiple AUs; 2) the dependencies between expression and AUs; and 3) the dependencies between facial features and AUs. We reconstruct the inputted face and AU labels and introduce two reconstruction losses. In a semisupervised scenario, the supervised loss is also incorporated into the full objective for AU-labeled samples. In a weakly supervised scenario, we generate pseudo paired data according to the domain knowledge about expression and AUs. Semisupervised and weakly supervised experiments on three widely used datasets demonstrate the superiority of the proposed method for AU detection and facial synthesis tasks over current works.

Can Facial Pose and Expression Be Separated with Weak Perspective Camera?

Separating facial pose and expression within images requires a camera model for 3D-to-2D mapping. The weak perspective (WP) camera has been the most popular choice; it is the default, if not the only option, in state-of-the-art facial analysis methods and software. WP camera is justified by the supposition that its errors are negligible when the subjects are relatively far from the camera, yet this claim has never been tested despite nearly 20 years of research. This paper critically examines the suitability of WP camera for separating facial pose and expression. First, we theoretically show that WP causes pose-expression ambiguity, as it leads to estimation of spurious expressions. Next, we experimentally quantify the magnitude of spurious expressions. Finally, we test whether spurious expressions have detrimental effects on a common facial analysis application, namely Action Unit (AU) detection. Contrary to conventional wisdom, we find that severe pose-expression ambiguity exists even when subjects are not close to the camera, leading to large false positive rates in AU detection. We also demonstrate that the magnitude and characteristics of spurious expressions depend on the point distribution model used to model the expressions. Our results suggest that common assumptions about WP need to be revisited in facial expression modeling, and that facial analysis software should encourage and facilitate the use of the true camera model whenever possible.

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.

Progress and challenges in facial action unit detection

Progress and challenges in facial action unit detection

Facial Action Unit Detection with Multilayer Fused Multi-Task and Multi-Label Deep Learning Network

Facial Action Unit Detection with Multilayer Fused Multi-Task and Multi-Label Deep Learning Network

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.

Can a building read your mind? Results from a small trial in facial action unit detection

In the last few decades, the energy consumption of individual buildings has been steadily improving. As a result, research efforts are shifting towards acquiring a deeper understanding of occupant comfort, health, and well-being in the built environment. However, existing techniques used to measure and predict the comfort of occupants have seen little change since Fanger. New research attempts are hence focusing on methods to gather more data, more frequently, and less intrusively. A little explored source of data is the one gathered from real-time videos of occupants, the so-called facial action units (FAU), which is the focus of this paper. These are the facial movements and positions that constitute the basic elements of emotions. Using software developed in the realm of affective computing, seven building occupants were monitored for a period of 2 weeks, whilst also completing surveys that gathered information about the office environment, and their work and personal life. Results found that participants that were happy with their office space showed significantly higher average values of the Cheek Raiser (AU06) and Lid Tightener (AU07) facial action units. These findings show the potential of using FAUs to assist in the control and design of buildings in a human-centric manner.

A comprehensive survey on automatic facial action unit analysis

Facial Action Coding System is the most influential sign judgment method for facial behavior, and it is a comprehensive and anatomical system which could encode various facial movements by the combination of basic AUs (Action Units). AUs define certain facial configurations caused by contraction of one or more facial muscles, and they are independent of interpretation of emotions. However, automatic facial action unit recognition remains challenging due to several open questions such as rigid and non-rigid facial motions, multiple AUs detection, intensity estimation and naturalistic context application. This paper introduces recent advances in automatic facial action unit recognition, focusing on the fundamental components of face detection and registration, facial action representation, feature selection and classification. The comprehensive analysis of facial representations is presented according to the facial data properties (image and video, 2D and 3D) and characteristics of facial features (predesign and learning, appearance and geometry, hybrid and fusion). Facial action unit recognition involves AUs occurrence detection, AUs temporal segment detection and AUs intensity estimation. We discussed the role of each component, main techniques with their characteristics, challenges and potential directions of facial action unit analysis.

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.

AU R-CNN: Encoding expert prior knowledge into R-CNN for action unit detection

Detecting action units (AUs) on human faces is challenging because various AUs make subtle facial appearance change over various regions at different scales. Current works have attempted to recognize AUs by emphasizing important regions. However, the incorporation of expert prior knowledge into region definition remains under-exploited, and current AU detection approaches do not use regional convolutional neural networks (R-CNN) with expert prior knowledge to directly focus on AU-related regions adaptively. By incorporating expert prior knowledge, we propose a novel R-CNN based model named AU R-CNN. The proposed solution offers two main contributions: (1) AU R-CNN directly observes different facial regions, where various AUs are located. Expert prior knowledge is encoded in the region and the RoI-level label definition. This design produces considerably better detection performance than existing approaches. (2) We integrate various dynamic models (including convolutional long short-term memory, two stream network, conditional random field, and temporal action localization network) into AU R-CNN and then investigate and analyze the reason behind the performance of dynamic models. Experiment results demonstrate that only static RGB image information and no optical flow-based AU R-CNN surpasses the one fused with dynamic models. AU R-CNN is also superior to traditional CNNs that use the same backbone on varying image resolutions. State-of-the-art recognition performance of AU detection is achieved. The complete network is end-to-end trainable. Experiments on BP4D and DISFA datasets show the effectiveness of our approach. Code will be made available.

P_VggNet: A convolutional neural network (CNN) with pixel-based attention map.

Attention maps have been fused in the VggNet structure (EAC-Net) [1] and have shown significant improvement compared to that of the VggNet structure. However, in [1], E-Net was designed based on the facial action unit (AU) center and for facial AU detection only. Thus, for the use of attention maps in every image type, this paper proposed a new convolutional neural network (CNN) structure, P_VggNet, comprising the following parts: P_Net and VggNet with 16 layers (VggNet-16). The generation approach of P_Net was designed, and the P_VggNet structure was proposed. To prove the efficiency of P_VggNet, we designed two experiments, which indicated that P_VggNet could more efficiently extract image features than VggNet-16.

Learning facial action units with spatiotemporal cues and multi-label sampling

Facial action units (AUs) can be represented spatially, temporally, and in terms of their correlation. Previous research focuses on one or another of these aspects or addresses them disjointly. We propose a hybrid network architecture that jointly models spatial and temporal representations and their correlation. In particular, we use a Convolutional Neural Network (CNN) to learn spatial representations, and a Long Short-Term Memory (LSTM) to model temporal dependencies among them. The outputs of CNNs and LSTMs are aggregated into a fusion network to produce per-frame prediction of multiple AUs. The hybrid network was compared to previous state-of-the-art approaches in two large FACS-coded video databases, GFT and BP4D, with over 400,000 AU-coded frames of spontaneous facial behavior in varied social contexts. Relative to standard multi-label CNN and feature-based state-of-the-art approaches, the hybrid system reduced person-specific biases and obtained increased accuracy for AU detection. To address class imbalance within and between batches during network training, we introduce multi-labeling sampling strategies that further increase accuracy when AUs are relatively sparse. Finally, we provide visualization of the learned AU models, which, to the best of our best knowledge, reveal for the first time how machines see AUs.

Multi-view dynamic facial action unit detection

We propose a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection. We leverage recent gains in large-scale object recognition by formulating the task of predicting the presence or absence of a specific action unit in a still image of a human face as holistic classification. We then explore the design space of our approach by considering both shared and independent representations for separate action units, and also different CNN architectures for combining color and motion information. We then move to the novel setup of the FERA 2017 Challenge, in which we propose a multi-view extension of our approach that operates by first predicting the viewpoint from which the video was taken, and then evaluating an ensemble of action unit detectors that were trained for that specific viewpoint. Our approach is holistic, efficient, and modular, since new action units can be easily included in the overall system. Our approach significantly outperforms the baseline of the FERA 2017 Challenge, with an absolute improvement of 14% on the F1-metric. Additionally, it compares favorably against the winner of the FERA 2017 Challenge.

Action unit detection and key frame selection for human activity prediction

Abstract Human activity prediction aims to recognize an unfinished activity with limited appearance and motion information. In this paper, we propose to predict an incomplete activity by combining the mid-level action units and the discriminative key frames exploited from each activity class. Specifically, we extract a great deal of action-related volumes from activity videos. Based on a set of low-level powerful features, similar volumes are aggregated into a mid-level feature, named action unit. Then, we detect these action units in each activity video and generate the frame feature by computing the distribution of concurrent action units in a single frame. Notice that human can easily recognize an incomplete activity using scanty key frames composed of representative interrelated action units together. The key frames in each activity class are selected by computing the entropy of each single frame feature. Finally, a structured SVM is trained to recognize activities with different observation ratios. The proposed approach is evaluated on several publicly available datasets in comparison with state-of-the-art approaches. The experimental results and analysis clearly demonstrate the effectiveness of the proposed approach.

FACSCaps: Pose-Independent Facial Action Coding with Capsules.

Most automated facial expression analysis methods treat the face as a 2D object, flat like a sheet of paper. That works well provided images are frontal or nearly so. In real- world conditions, moderate to large head rotation is common and system performance to recognize expression degrades. Multi-view Convolutional Neural Networks (CNNs) have been proposed to increase robustness to pose, but they require greater model sizes and may generalize poorly across views that are not included in the training set. We propose FACSCaps architecture to handle multi-view and multi-label facial action unit (AU) detection within a single model that can generalize to novel views. Additionally, FACSCaps's ability to synthesize faces enables insights into what is leaned by the model. FACSCaps models video frames using matrix capsules, where hierarchical pose relationships between face parts are built into internal representations. The model is trained by jointly optimizing a multi-label loss and the reconstruction accuracy. FACSCaps was evaluated using the FERA 2017 facial expression dataset that includes spontaneous facial expressions in a wide range of head orientations. FACSCaps outperformed both state-of-the-art CNNs and their temporal extensions.

Action unit detection in 3D facial videos with application in facial expression retrieval and recognition

This work introduces a new scheme for action unit detection in 3D facial videos. Sets of features that define action unit activation in a robust manner are proposed. These features are computed based on eight detected facial landmarks on each facial mesh that involve angles, areas and distances. Support vector machine classifiers are then trained using the above features in order to perform action unit detection. The proposed AU detection scheme is used in a dynamic 3D facial expression retrieval and recognition pipeline, highlighting the most important AU s, in terms of providing facial expression information, and at the same time, resulting in better performance than state-of-the-art methodologies.

Learning with privileged information for multi-Label classification

In this paper, we propose a novel approach for learning multi-label classifiers with the help of privileged information. Specifically, we use similarity constraints to capture the relationship between available information and privileged information, and use ranking constraints to capture the dependencies among multiple labels. By integrating similarity constraints and ranking constraints into the learning process of classifiers, the privileged information and the dependencies among multiple labels are exploited to construct better classifiers during training. A maximum margin classifier is adopted, and an efficient learning algorithm of the proposed method is also developed. We evaluate the proposed method on two applications: multiple object recognition from images with the help of implicit information about object importance conveyed by the list of manually annotated image tags; and multiple facial action unit detection from low-resolution images augmented by high-resolution images. Experimental results demonstrate that the proposed method can effectively take full advantage of privileged information and dependencies among multiple labels for better object recognition and better facial action unit detection.

EAC-Net: Deep Nets with Enhancing and Cropping for Facial Action Unit Detection.

In this paper, we propose a deep learning based approach for facial action unit (AU) detection by enhancing and cropping regions of interest of face images. The approach is implemented by adding two novel nets (a.k.a. layers): the enhancing layers and the cropping layers, to a pretrained convolutional neural network (CNN) model. For the enhancing layers (noted as E-Net), we have designed an attention map based on facial landmark features and apply it to a pretrained neural network to conduct enhanced learning. For the cropping layers (noted as C-Net ), we crop facial regions around the detected landmarks and design individual convolutional layers to learn deeper features for each facial region. We then combine the E-Net and the C-Net to construct a so-called Enhancing and Cropping Net (EAC-Net), which can learn both features enhancing and region cropping functions effectively. The EAC-Net integrates three important elements, i.e., learning transfer, attention coding, and regions of interest processing, making our AU detection approach more efficient and more robust to facial position and orientation changes. Our approach shows a significant performance improvement over the state-of-the-art methods when tested on the BP4D and DISFA AU datasets. The EAC-Net with a slight modification also shows its potentials in estimating accurate AU intensities. We have also studied the performance of the proposed EAC-Net under two very challenging conditions: (1) faces with partial occlusion and (2) faces with large head pose variations. Experimental results show that (1) the EAC-Net learns facial AUs correlation effectively and predicts AUs reliably even with only half of a face being visible, especially for the lower half; (2) Our EAC-Net model also works well under very large head poses, which outperforms significantly a compared baseline approach. It further shows that the EAC-Net works much better without a face frontalization than with face frontalization through image warping as pre-processing, in terms of computational efficiency and AU detection accuracy.

A Dictionary Learning-Based 3D Morphable Shape Model

Face analysis from 2D images and videos is a central task in many multimedia applications. Methods developed to this end perform either face recognition or facial expression recognition, and in both cases results are negatively influenced by variations in pose, illumination, and resolution of the face. Such variations have a lower impact on 3D face data, which has given the way to the idea of using a 3D morphable model as an intermediate tool to enhance face analysis on 2D data. In this paper, we propose a new approach for constructing a 3D morphable shape model (called DL-3DMM) and show our solution can reach the accuracy of deformation required in applications where fine details of the face are concerned. For constructing the model, we start from a set of 3D face scans with large variability in terms of ethnicity and expressions. Across these training scans, we compute a point-to-point dense alignment, which is accurate also in the presence of topological variations of the face. The DL-3DMM is constructed by learning a dictionary of basis components on the aligned scans. The model is then fitted to 2D target faces using an efficient regularized ridge-regression guided by 2D/3D facial landmark correspondences in order to generate pose-normalized face images. Comparison between the DL-3DMM and the standard PCA-based 3DMM demonstrates that in general a lower reconstruction error can be obtained with our solution. Application to action unit detection and emotion recognition from 2D images and videos shows competitive results with state of the art methods on two benchmark datasets.

Automatic Action Unit Detection in Infants Using Convolutional Neural Network.

Action unit detection in infants relative to adults presents unique challenges. Jaw contour is less distinct, facial texture is reduced, and rapid and unusual facial movements are common. To detect facial action units in spontaneous behavior of infants, we propose a multi-label Convolutional Neural Network (CNN). Eighty-six infants were recorded during tasks intended to elicit enjoyment and frustration. Using an extension of FACS for infants (Baby FACS), over 230,000 frames were manually coded for ground truth. To control for chance agreement, inter-observer agreement between Baby-FACS coders was quantified using free-margin kappa. Kappa coefficients ranged from 0.79 to 0.93, which represents high agreement. The multi-label CNN achieved comparable agreement with manual coding. Kappa ranged from 0.69 to 0.93. Importantly, the CNN-based AU detection revealed the same change in findings with respect to infant expressiveness between tasks. While further research is needed, these findings suggest that automatic AU detection in infants is a viable alternative to manual coding of infant facial expression.