Facial expressions recognition (FER) of 3D face scans has received a significant amount of attention in recent years. Most of the facial expression recognition methods have been proposed using mainly 2D images. These methods suffer from several issues like illumination changes and pose variations. Moreover, 2D mapping from 3D images may lack some geometric and topological characteristics of the face. Hence, to overcome this problem, a multi-modal 2D + 3D feature-based method is proposed. We extract shallow features from the 3D images, and deep features using Convolutional Neural Networks (CNN) from the transformed 2D images. Combining these features into a compact representation uses covariance matrices as descriptors for both features instead of single-handedly descriptors. A covariance matrix learning is used as a manifold layer to reduce the deep covariance matrices size and enhance their discrimination power while preserving their manifold structure. We then use the Bag-of-Features (BoF) paradigm to quantize the covariance matrices after flattening. Accordingly, we obtained two codebooks using shallow and deep features. The global codebook is then used to feed an SVM classifier. High classification performances have been achieved on the BU-3DFE and Bosphorus datasets compared to the state-of-the-art methods.
Mohammed V University in Rabat（拉巴特穆罕默德五世大学）；IMT Lille-Douai（里尔-杜埃国立高等矿业电信学校）；CNRS（法国国家科学研究中心）；University of Florence（佛罗伦萨大学）
In this paper, covariance matrices are exploited to encode the deep convolutional neural networks (DCNN) features for facial expression recognition. The space geometry of the covariance matrices is that of Symmetric Positive Definite (SPD) matrices. By performing the classification of the facial expressions using Gaussian kernel on SPD manifold, we show that the covariance descriptors computed on DCNN features are more efficient than the standard classification with fully connected layers and softmax. By implementing our approach using the VGG-face and ExpNet architectures with extensive exper…
Classifying facial expressions into different categories requires capturing regional distortions of facial landmarks. We believe that second-order statistics such as covariance is better able to capture such distortions in regional facial fea- tures. In this work, we explore the benefits of using a man- ifold network structure for covariance pooling to improve facial expression recognition. In particular, we first employ such kind of manifold networks in conjunction with tradi- tional convolutional networks for spatial pooling within in- dividual image feature maps in an end-to-end deep learni…
Mohammed V University in Rabat（拉巴特穆罕默德五世大学）；University of Luxembourg（卢森堡大学）；IMT Lille-Douai（法国里尔-杜埃国立高等矿业电信学校）；University of Lille（里尔大学）；CNRS（法国国家科学研究中心）；University of Florence（佛罗伦萨大学）
In this paper, we propose a new approach for facial expression recognition using deep covariance descriptors. The solution is based on the idea of encoding local and global Deep Convolutional Neural Network (DCNN) features extracted from still images, in compact local and global covariance descriptors. The space geometry of the covariance matrices is that of Symmetric Positive Definite (SPD) matrices. By conducting the classification of static facial expressions using Support Vector Machine (SVM) with a valid Gaussian kernel on the SPD manifold, we show that deep covariance descriptors are mor…
School of Electrical Engineering, KAIST（韩国科学技术院电气工程学院）
In convolutional neural networks (CNNs), the filter grouping in convolution layers is known to be useful to reduce the network parameter size. In this paper, we propose a new logarithmic filter grouping which can capture the nonlinearity of filter distribution in CNNs. The proposed logarithmic filter grouping is installed in shallow CNNs applicable in a mobile application. Experiments were performed with the shallow CNNs for classification tasks. Our classification results on Multi-PIE dataset for facial expression recognition and CIFAR-10 dataset for object classification reveal that the comp…
Residual-based neural networks have shown remarkable results in various visual recognition tasks including Facial Expression Recognition (FER). Despite the tremendous efforts have been made to improve the performance of FER systems using DNNs, existing methods are not generalizable enough for practical applications. This paper introduces Bounded Residual Gradient Networks (BReG-Net) for facial expression recognition, in which the shortcut connection between the input and the output of the ResNet module is replaced with a differentiable function with a bounded gradient. This configuration preve…
IMT Lille Douai（里尔杜埃高等电信学院）；Univ. Lille（里尔大学）；CNRS（法国国家科学研究中心）；CRIStAL（里尔计算机、信号与自动化研究中心）；Laboratoire Paul Painlevé（保罗·潘勒韦实验室）
In this paper, we study the problem of facial expression recognition using a novel space-time geometric representation. We describe the temporal evolution of facial landmarks as parametrized trajectories on the Riemannian manifold of positive semidefinite matrices of fixed-rank. Our representation has the advantage to bring naturally a second desirable quantity when comparing shapes -- the spatial covariance -- in addition to the conventional affine-shape representation. We derive then geometric and computational tools for rate-invariant analysis and adaptive re-sampling of trajectories, groun…
This paper introduces BReG-NeXt, a residual-based network architecture using a function wtih bounded derivative instead of a simple shortcut path (a.k.a. identity mapping) in the residual units for automatic recognition of facial expressions based on the categorical and dimensional models of affect. Compared to ResNet, our proposed adaptive complex mapping results in a shallower network with less numbers of training parameters and floating point operations per second (FLOPs). Adding trainable parameters to the bypass function further improves fitting and training the network and hence recogniz…
Beijing University of Posts and Telecommunications（北京邮电大学）
Datasets play an important role in the progress of facial expression recognition algorithms, but they may suffer from obvious biases caused by different cultures and collection conditions. To look deeper into this bias, we first conduct comprehensive experiments on dataset recognition and crossdataset generalization tasks, and for the first time explore the intrinsic causes of the dataset discrepancy. The results quantitatively verify that current datasets have a strong buildin bias and corresponding analyses indicate that the conditional probability distributions between source and target dat…
Generic face detection algorithms do not perform very well in the mobile domain due to significant presence of occluded and partially visible faces. One promising technique to handle the challenge of partial faces is to design face detectors based on facial segments. In this paper two such face detectors namely, SegFace and DeepSegFace, are proposed that detect the presence of a face given arbitrary combinations of certain face segments. Both methods use proposals from facial segments as input that are found using weak boosted classifiers. SegFace is a shallow and fast algorithm using traditio…
Facial Expression Recognition in the Deep Learning Era: A Systematic Multi-Criteria Review of Methods, Models, Datasets, Performance, Challenges, and Future Research Directions
International Hellenic University（国际希腊大学）；University of Thessaly（色萨利大学）；Democritus University of Thrace（德谟克利特大学）；University of Peloponnese（伯罗奔尼撒大学）；Harokopio University of Athens（哈罗科皮奥大学）
Video Joint-Embedding Predictive Architectures for Facial Expression Recognition
Chair for Human-Centered Artificial Intelligence（人中心人工智能教研室）；University of Augsburg（奥斯特拉赫大学）；Faculty of Computer Science（计算机科学学院）；Technical University of Applied Sciences Augsburg（应用科学大学奥斯特拉赫）
Centre de Développement des Technologies Avancées（先进技术发展中心）；University of Oulu（奥卢大学）；Ecole Nationale Supèrieure d’Informatique（国立高等信息学学院）；Northwestern Polytechnical University（西北工业大学）
Automatic kinship verification using facial images is a relatively new and challenging research problem in computer vision. It consists in automatically predicting whether two persons have a biological kin relation by examining their facial attributes. While most of the existing works extract shallow handcrafted features from still face images, we approach this problem from spatio-temporal point of view and explore the use of both shallow texture features and deep features for characterizing faces. Promising results, especially those of deep features, are obtained on the benchmark UvA-NEMO Smi…
QuIC: A Quantum-Inspired Interaction Classifier for Revitalizing Shallow CNNs in Fine-Grained Recognition
Big Data Chung Yuan Christian University Taoyuan City, Taiwan（大数据 Chung Yuan Christian 大学 台中市 台湾）；Big Data Quantum Information Center Chung Yuan Christian University Taoyuan City, Taiwan（大数据 量子信息中心 Chung Yuan Christian 大学 台中市 台湾）
As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no clear definition nor sufficient analysis for bias assessment metrics. We propose an information-theoretic, independent bias assessment metric to identify degree of bias against protected demographic attributes from learned representations of pretrained facial recognition systems. Our metric differs from other methods that rely on classification accuracy or examine the differences …
Automated affective computing in the wild is a challenging task in the field of computer vision. This paper presents three neural network-based methods proposed for the task of facial affect estimation submitted to the First Affect-in-the-Wild challenge. These methods are based on Inception-ResNet modules redesigned specifically for the task of facial affect estimation. These methods are: Shallow Inception-ResNet, Deep Inception-ResNet, and Inception-ResNet with LSTMs. These networks extract facial features in different scales and simultaneously estimate both the valence and arousal in each fr…
University of Miami（迈阿密大学）；Indian Institute of Technology, Guwahati（印度理工学院古瓦哈提分校）
Inspired from the assets of handcrafted and deep learning approaches, we proposed a RARITYNet: RARITY guided affective emotion learning framework to learn the appearance features and identify the emotion class of facial expressions. The RARITYNet framework is designed by combining the shallow (RARITY) and deep (AffEmoNet) features to recognize the facial expressions from challenging images as spontaneous expressions, pose variations, ethnicity changes, and illumination conditions. The RARITY is proposed to encode the inter-radial transitional patterns in the local neighbourhood. The AffEmoNet:…
IMT Lille Douai（里尔-杜埃国立高等矿业电信学院）；University of Florence（佛罗伦萨大学）；University of Lille（里尔大学）
In this paper, we propose a novel space-time geometric representation of human landmark configurations and derive tools for comparison and classification. We model the temporal evolution of landmarks as parametrized trajectories on the Riemannian manifold of positive semidefinite matrices of fixed-rank. Our representation has the benefit to bring naturally a second desirable quantity when comparing shapes, the spatial covariance, in addition to the conventional affine-shape representation. We derived then geometric and computational tools for rate-invariant analysis and adaptive re-sampling of…
Feng Chia University（逢甲大学）；National Taipei University of Nursing and Health Sciences（台北护理健康大学）；Multimedia University（多媒体大学）；Xinyang Normal University（信阳师范大学）
In the recent year, state-of-the-art for facial micro-expression recognition have been significantly advanced by deep neural networks. The robustness of deep learning has yielded promising performance beyond that of traditional handcrafted approaches. Most works in literature emphasized on increasing the depth of networks and employing highly complex objective functions to learn more features. In this paper, we design a Shallow Triple Stream Three-dimensional CNN (STSTNet) that is computationally light whilst capable of extracting discriminative high level features and details of micro-express…
University of Biskra（比斯克拉大学）；Univ. Polytechnique Hauts-de-France（上法兰西理工大学）；University of Oulu（奥卢大学）
Automatic kinship verification from facial images is an emerging research topic in machine learning community. In this paper, we proposed an effective facial features extraction model based on multi-view deep features. Thus, we used four pre-trained deep learning models using eight features layers (FC6 and FC7 layers of each VGG-F, VGG-M, VGG-S and VGG-Face models) to train the proposed Multilinear Side-Information based Discriminant Analysis integrating Within Class Covariance Normalization (MSIDA+WCCN) method. Furthermore, we show that how can metric learning methods based on WCCN method int…
We propose a scheme for multi-layer representation of images. The problem is first treated from an information-theoretic viewpoint where we analyze the behavior of different sources of information under a multi-layer data compression framework and compare it with a single-stage (shallow) structure. We then consider the image data as the source of information and link the proposed representation scheme to the problem of multi-layer dictionary learning for visual data. For the current work we focus on the problem of image compression for a special class of images where we report a considerable p…
In this paper, a novel method for representation and recognition of the facial expressions in two-dimensional image sequences is presented. We apply a variation of two-dimensional heteroscedastic linear discriminant analysis (2DHLDA) algorithm, as an efficient dimensionality reduction technique, to Gabor representation of the input sequence. 2DHLDA is an extension of the two-dimensional linear discriminant analysis (2DLDA) approach and it removes the equal within-class covariance. By applying 2DHLDA in two directions, we eliminate the correlations between both image columns and image rows. The…
Istituto Italiano di Tecnologia（意大利技术研究院）；Università degli Studi di Genova（热那亚大学）；Università di Verona（维罗纳大学）
Human action recognition from skeletal data is a hot research topic and important in many open domain applications of computer vision, thanks to recently introduced 3D sensors. In the literature, naive methods simply transfer off-the-shelf techniques from video to the skeletal representation. However, the current state-of-the-art is contended between to different paradigms: kernel-based methods and feature learning with (recurrent) neural networks. Both approaches show strong performances, yet they exhibit heavy, but complementary, drawbacks. Motivated by this fact, our work aims at combining …
Multimedia University（多媒体大学）；Heriot-Watt University Malaysia（赫瑞-瓦特大学马来西亚校区）
Facial expressions vary from the visible to the subtle. In recent years, the analysis of micro-expressions $-$ a natural occurrence resulting from the suppression of one's true emotions, has drawn the attention of researchers with a broad range of potential applications. However, spotting microexpressions in long videos becomes increasingly challenging when intertwined with normal or macro-expressions. In this paper, we propose a shallow optical flow three-stream CNN (SOFTNet) model to predict a score that captures the likelihood of a frame being in an expression interval. By fashioning the sp…
We propose a new action and gesture recognition method based on spatio-temporal covariance descriptors and a weighted Riemannian locality preserving projection approach that takes into account the curved space formed by the descriptors. The weighted projection is then exploited during boosting to create a final multiclass classification algorithm that employs the most useful spatio-temporal regions. We also show how the descriptors can be computed quickly through the use of integral video representations. Experiments on the UCF sport, CK+ facial expression and Cambridge hand gesture datasets i…
Malaviya National Institute of Technology（马拉维亚国家理工学院）
Micro expression recognition (MER)is a very challenging task as the expression lives very short in nature and demands feature modeling with the involvement of both spatial and temporal dynamics. Existing MER systems exploit CNN networks to spot the significant features of minor muscle movements and subtle changes. However, existing networks fail to establish a relationship between spatial features of facial appearance and temporal variations of facial dynamics. Thus, these networks were not able to effectively capture minute variations and subtle changes in expressive regions. To address these…
Identity-Preserving Text-to-Video Generation by Frequency Decomposition
Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）；University of Rochester（罗切斯特大学）；Rabbitpre Intelligence（睿兔智算）；National University of Singapore（新加坡国立大学）
IMT Lille Douai（里尔杜埃IMT商学院）；Univ. Lille（里尔大学）；CNRS（法国国家科学研究中心）；University of Florence（佛罗伦萨大学）
Emotion recognition is attracting great interest for its potential application in a multitude of real-life situations. Much of the Computer Vision research in this field has focused on relating emotions to facial expressions, with investigations rarely including more than upper body. In this work, we propose a new scenario, for which emotional states are related to 3D dynamics of the whole body motion. To address the complexity of human body movement, we used covariance descriptors of the sequence of the 3D skeleton joints, and represented them in the non-linear Riemannian manifold of Symmetri…
Harbin Institute of Technology（哈尔滨工业大学）；National Institute of Informatics（国立信息学研究所）；The Smart City Research Institute of CETC（中国电子科技集团智慧城市研究院）；The University of Electro-Communications（电气通信大学）；Wuhan University（武汉大学）
Most of the current face hallucination methods, whether they are shallow learning-based or deep learning-based, all try to learn a relationship model between Low-Resolution (LR) and High-Resolution (HR) spaces with the help of a training set. They mainly focus on modeling image prior through either model-based optimization or discriminative inference learning. However, when the input LR face is tiny, the learned prior knowledge is no longer effective and their performance will drop sharply. To solve this problem, in this paper we propose a general face hallucination method that can integrate m…
New York University（纽约大学）；Flatiron Institute（弗莱隆研究所）；Johns Hopkins University（约翰斯·霍普金斯大学）；École Normale Supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL University（巴黎文理研究大学）；Collège de France（法兰西学院）
