Human affective behavior analysis aims to delve into human expressions and behaviors to deepen our understanding of human emotions. Basic expression categories (EXPR) and Action Units (AUs) are two essential components in this analysis, which categorize emotions and break down facial movements into elemental units, respectively. Despite advancements, existing approaches in expression classification and AU detection often necessitate complex models and substantial computational resources, limiting their applicability in everyday settings. In this work, we introduce the first lightweight framework adept at efficiently tackling both expression classification and AU detection. This framework employs a frozen CLIP image encoder alongside a trainable multilayer perceptron (MLP), enhanced with Conditional Value at Risk (CVaR) for robustness and a loss landscape flattening strategy for improved generalization. Experimental results on the Aff-wild2 dataset demonstrate superior performance in comparison to the baseline while maintaining minimal computational demands, offering a practical solution for affective behavior analysis. The code is available at https://github.com/Purdue-M2/Affective_Behavior_Analysis_M2_PURDUE
In recent years, deep learning has achieved innovative advancements in various fields, including the analysis of human emotions and behaviors. Initiatives such as the Affective Behavior Analysis in-the-wild (ABAW) competition have been particularly instrumental in driving research in this area by providing diverse and challenging datasets that enable precise evaluation of complex emotional states. This study leverages the Vision Transformer (ViT) and Transformer models to focus on the estimation of Valence-Arousal (VA), which signifies the positivity and intensity of emotions, recognition of various facial expressions, and detection of Action Units (AU) representing fundamental muscle movements. This approach transcends traditional Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) based methods, proposing a new Transformer-based framework that maximizes the understanding of temporal and spatial features. The core contributions of this research include the introduction of a learning technique through random frame masking and the application of Focal loss adapted for imbalanced data, enhancing the accuracy and applicability of emotion and behavior analysis in real-world settings. This approach is expected to contribute to the advancement of emotional computing and deep learning methodologies.
Point clouds and meshes are widely used 3D data structures for many computer vision applications. While the meshes represent the surfaces of an object, point cloud represents sampled points from the surface which is also the output of modern sensors such as LiDAR and RGB-D cameras. Due to the wide application area of point clouds and the recent advancements in deep neural networks, studies focusing on robust classification of the 3D point cloud data emerged. To evaluate the robustness of deep classifier networks, a common method is to use adversarial attacks where the gradient direction is followed to change the input slightly. The previous studies on adversarial attacks are generally evaluated on point clouds of daily objects. However, considering 3D faces, these adversarial attacks tend to affect the person's facial structure more than the desired amount and cause malformation. Specifically for facial expressions, even a small adversarial attack can have a significant effect on the face structure. In this paper, we suggest an adversarial attack called $\epsilon$-Mesh Attack, which operates on point cloud data via limiting perturbations to be on the mesh surface. We also parameterize our attack by $\epsilon$ to scale the perturbation mesh. Our surface-based attack has tighter perturbation bounds compared to $L_2$ and $L_\infty$ norm bounded attacks that operate on unit-ball. Even though our method has additional constraints, our experiments on CoMA, Bosphorus and FaceWarehouse datasets show that $\epsilon$-Mesh Attack (Perpendicular) successfully confuses trained DGCNN and PointNet models $99.72\%$ and $97.06\%$ of the time, with indistinguishable facial deformations. The code is available at https://github.com/batuceng/e-mesh-attack.
Background: Pain assessment in individuals with neurological conditions, especially those with limited self-report ability and altered facial expressions, presents challenges. Existing measures, relying on direct observation by caregivers, lack sensitivity and specificity. In cerebral palsy, pain is a common comorbidity and a reliable evaluation protocol is crucial. Thus, having an automatic system that recognizes facial expressions could be of enormous help when diagnosing pain in this type of patient. Objectives: 1) to build a dataset of facial pain expressions in individuals with cerebral palsy, and 2) to develop an automated facial recognition system based on deep learning for pain assessment addressed to this population. Methods: Ten neural networks were trained on three pain image databases, including the UNBC-McMaster Shoulder Pain Expression Archive Database, the Multimodal Intensity Pain Dataset, and the Delaware Pain Database. Additionally, a curated dataset (CPPAIN) was created, consisting of 109 preprocessed facial pain expression images from individuals with cerebral palsy, categorized by two physiotherapists using the Facial Action Coding System observational scale. Results: InceptionV3 exhibited promising performance on the CP-PAIN dataset, achieving an accuracy of 62.67% and an F1 score of 61.12%. Explainable artificial intelligence techniques revealed consistent essential features for pain identification across models. Conclusion: This study demonstrates the potential of deep learning models for robust pain detection in populations with neurological conditions and communication disabilities. The creation of a larger dataset specific to cerebral palsy would further enhance model accuracy, offering a valuable tool for discerning subtle and idiosyncratic pain expressions. The insights gained could extend to other complex neurological conditions.
Depression Recognition (DR) poses a considerable challenge, especially in the context of the growing concerns surrounding privacy. Traditional automatic diagnosis of DR technology necessitates the use of facial images, undoubtedly expose the patient identity features and poses privacy risks. In order to mitigate the potential risks associated with the inappropriate disclosure of patient facial images, we design a new imaging system to erase the identity information of captured facial images while retain disease-relevant features. It is irreversible for identity information recovery while preserving essential disease-related characteristics necessary for accurate DR. More specifically, we try to record a de-identified facial image (erasing the identifiable features as much as possible) by a learnable lens, which is optimized in conjunction with the following DR task as well as a range of face analysis related auxiliary tasks in an end-to-end manner. These aforementioned strategies form our final Optical deep Depression Recognition network (OpticalDR). Experiments on CelebA, AVEC 2013, and AVEC 2014 datasets demonstrate that our OpticalDR has achieved state-of-the-art privacy protection performance with an average AUC of 0.51 on popular facial recognition models, and competitive results for DR with MAE/RMSE of 7.53/8.48 on AVEC 2013 and 7.89/8.82 on AVEC 2014, respectively.
Recent advances in machine learning and computer vision have led to reported facial recognition accuracies surpassing human performance. We question if these systems will translate to real-world forensic scenarios in which a potentially low-resolution, low-quality, partially-occluded image is compared against a standard facial database. We describe the construction of a large-scale synthetic facial dataset along with a controlled facial forensic lineup, the combination of which allows for a controlled evaluation of facial recognition under a range of real-world conditions. Using this synthetic dataset, and a popular dataset of real faces, we evaluate the accuracy of two popular neural-based recognition systems. We find that previously reported face recognition accuracies of more than 95% drop to as low as 65% in this more challenging forensic scenario.
In daily life, we tend to present the front of our faces by staring squarely at a facial recognition machine, instead of facing it sideways, in order to increase the chance of being correctly recognised. Few-shot-learning (FSL) classification is challenging in itself because a model has to identify images that belong to classes previously unseen during training. Therefore, a warped and non-typical query or support image during testing can make it even more challenging for a model to predict correctly. In our work, to increase the chance of correct prediction during testing, we aim to rectify the test input of a trained FSL model by generating new samples of the tested classes through image-to-image translation. An FSL model is usually trained on classes with sufficient samples, and then tested on classes with few-shot samples. Our proposed method first captures the style or shape of the test image, and then identifies a suitable trained class sample. It then transfers the style or shape of the test image to the train-class images for generation of more test-class samples, before performing classification based on a set of generated samples instead of just one sample. Our method has potential in empowering a trained FSL model to score higher during the testing phase without any extra training nor dataset. According to our experiments, by augmenting the support set with just 1 additional generated sample, we can achieve around 2% improvement for trained FSL models on datasets consisting of either animal faces or traffic signs. By augmenting both the support set and the queries, we can achieve even more performance improvement. Our Github Repository is publicly available.
Multi-modal emotion recognition has recently gained a lot of attention since it can leverage diverse and complementary relationships over multiple modalities, such as audio, visual, and text. Most state-of-the-art methods for multimodal fusion rely on recurrent networks or conventional attention mechanisms that do not effectively leverage the complementary nature of the modalities. In this paper, we focus on dimensional emotion recognition based on the fusion of facial, vocal, and text modalities extracted from videos. Specifically, we propose a recursive cross-modal attention (RCMA) to effectively capture the complementary relationships across the modalities in a recursive fashion. The proposed model is able to effectively capture the inter-modal relationships by computing the cross-attention weights across the individual modalities and the joint representation of the other two modalities. To further improve the inter-modal relationships, the obtained attended features of the individual modalities are again fed as input to the cross-modal attention to refine the feature representations of the individual modalities. In addition to that, we have used Temporal convolution networks (TCNs) to capture the temporal modeling (intra-modal relationships) of the individual modalities. By deploying the TCNs as well cross-modal attention in a recursive fashion, we are able to effectively capture both intra- and inter-modal relationships across the audio, visual, and text modalities. Experimental results on validation-set videos from the AffWild2 dataset indicate that our proposed fusion model is able to achieve significant improvement over the baseline for the sixth challenge of Affective Behavior Analysis in-the-Wild 2024 (ABAW6) competition.
Ensuring robustness in face recognition systems across various challenging conditions is crucial for their versatility. State-of-the-art methods often incorporate additional information, such as depth, thermal, or angular data, to enhance performance. However, light field-based face recognition approaches that leverage angular information face computational limitations. This paper investigates the fundamental trade-off between spatio-angular resolution in light field representation to achieve improved face recognition performance. By utilizing macro-pixels with varying angular resolutions while maintaining the overall image size, we aim to quantify the impact of angular information at the expense of spatial resolution, while considering computational constraints. Our experimental results demonstrate a notable performance improvement in face recognition systems by increasing the angular resolution, up to a certain extent, at the cost of spatial resolution.