#### Learning Emotional Blinded Face Representations

Alejandro Peña Almansa, Julian Fierrez, Agata Lapedriza, Aythami Morales
Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; Blind Face Representations for Emotion Recognition

This work proposes two new face representations that are blind to the expressions associated to emotional responses. This work is in part motivated by new international regulations for personal data protection, which force data controllers to protect any kind of sensitive information involved in automatic processes. The advances in affective computing have contributed to improve human-machine interfaces, but at the same time, the capacity to monitorize emotional responses trigger potential risks for humans, both in terms of fairness and privacy. We propose two different methods to learn these facial expression blinded features. We show that it is possible to eliminate information related to emotion recognition tasks, while the performance of subject verification, gender recognition, and ethnicity classification are just slightly affected. We also present an application to train fairer classifiers over a protected facial expression attribute. The results demonstrate that it is possible to reduce emotional information in the face representation while retaining competitive performance in other face-based artificial intelligence tasks.

## Similar papers

#### InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics

Ignacio Serna, Alejandro Peña Almansa, Aythami Morales, Julian Fierrez
Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; InsideBias: Detecting Bias in Deep Neural Networks from Face Images

This work explores the biases in learning processes based on deep neural network architectures. We analyze how bias affects deep learning processes through a toy example using the MNIST database and a case study in gender detection from face images. We employ two gender detection models based on popular deep neural networks. We present a comprehensive analysis of bias effects when using an unbalanced training dataset on the features learned by the models. We show how bias impacts in the activations of gender detection models based on face images. We finally propose InsideBias, a novel method to detect biased models. InsideBias is based on how the models represent the information instead of how they perform, which is the normal practice in other existing methods for bias detection. Our strategy with InsideBias allows to detect biased models with very few samples (only 15 images in our case study). Our experiments include 72K face images from 24K identities and 3 ethnic groups.

#### Automatic Annotation of Corpora for Emotion Recognition through Facial Expressions Analysis

Alex Mircoli, Claudia Diamantini, Domenico Potena, Emanuele Storti
Track 5: Image and Signal Processing
Fri 15 Jan 2021 at 16:00 in session PS T5.8

Auto-TLDR; Automatic annotation of video subtitles on the basis of facial expressions using machine learning algorithms

The recent diffusion of social networks has made available an unprecedented amount of user-generated content, which may be analyzed in order to determine people's opinions and emotions about a large variety of topics. Research has made many efforts in defining accurate algorithms for analyzing emotions expressed by users in texts; however, their performance often rely on the existence of large annotated datasets, whose current scarcity represents a major issue. The manual creation of such datasets represents a costly and time-consuming activity and hence there is an increasing demand for techniques for the automatic annotation of corpora. In this work we present a methodology for the automatic annotation of video subtitles on the basis of the analysis of facial expressions of people in videos, with the goal of creating annotated corpora that may be used to train emotion recognition algorithms. Facial expressions are analyzed through machine learning algorithms, on the basis of a set of manually-engineered facial features that are extracted from video frames. The soundness of the proposed methodology has been evaluated through an extensive experimentation aimed at determining the performance on real datasets of each methodological step.

#### A Quantitative Evaluation Framework of Video De-Identification Methods

Sathya Bursic, Alessandro D'Amelio, Marco Granato, Giuliano Grossi, Raffaella Lanzarotti
Track 4: Document and Media Analysis
Thu 14 Jan 2021 at 14:00 in session PS T1.11

Auto-TLDR; Face de-identification using photo-reality and facial expressions

We live in an era of privacy concerns, motivating a large research effort in face de-identification. As in other fields, we are observing a general movement from hand-crafted methods to deep learning methods, mainly involving generative models. Although these methods produce more natural de-identified images or videos, we claim that the mere evaluation of the de-identification is not sufficient, especially when it comes to processing the images/videos further. In this note, we take into account the issue of preserving privacy, facial expressions, and photo-reality simultaneously, proposing a general testing framework. The method is applied to four open-source tools, producing a baseline for future de-identification methods.

#### End-To-End Triplet Loss Based Emotion Embedding System for Speech Emotion Recognition

Puneet Kumar, Sidharth Jain, Balasubramanian Raman, Partha Pratim Roy, Masakazu Iwamura
Track 5: Image and Signal Processing
Wed 13 Jan 2021 at 16:30 in session PS T5.4

Auto-TLDR; End-to-End Neural Embedding System for Speech Emotion Recognition

In this paper, an end-to-end neural embedding system based on triplet loss and residual learning has been proposed for speech emotion recognition. The proposed system learns the embeddings from the emotional information of the speech utterances. The learned embeddings are used to recognize the emotions portrayed by given speech samples of various lengths. The proposed system implements Residual Neural Network architecture. It is trained using softmax pre-training and triplet loss function. The weights between the fully connected and embedding layers of the trained network are used to calculate the embedding values. The embedding representations of various emotions are mapped onto a hyperplane, and the angles among them are computed using the cosine similarity. These angles are utilized to classify a new speech sample into its appropriate emotion class. The proposed system has demonstrated 91.67\% and 64.44\% accuracy while recognizing emotions for RAVDESS and IEMOCAP dataset, respectively.

#### Age Gap Reducer-GAN for Recognizing Age-Separated Faces

Daksha Yadav, Naman Kohli, Mayank Vatsa, Richa Singh, Afzel Noore
Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; Generative Adversarial Network for Age-separated Face Recognition

In this paper, we propose a novel algorithm for matching faces with temporal variations caused due to age progression. The proposed generative adversarial network algorithm is a unified framework which combines facial age estimation and age-separated face verification. The key idea of this approach is to learn the age variations across time by conditioning the input image on the subject's gender and the target age group to which the face needs to be progressed. The loss function accounts for reducing the age gap between the original image and generated face image as well as preserving the identity. Both visual fidelity and quantitative evaluations demonstrate the efficacy of the proposed architecture on different facial age databases for age-separated face recognition.

#### Siamese-Structure Deep Neural Network Recognizing Changes in Facial Expression According to the Degree of Smiling

Kazuaki Kondo, Taichi Nakamura, Yuichi Nakamura, Shin'Ichi Satoh
Track 2: Biometrics, Human Analysis and Behavior Understanding
Thu 14 Jan 2021 at 12:00 in session PS T2.4

Auto-TLDR; A Siamese-Structure Deep Neural Network for Happiness Recognition

A smile is a representative expression of happiness or high quality-of-life; however, automatic recognition of a smile according to happiness remains a challenging task. Because expressions of happiness are strongly dependent upon physical condition and occurrence of other emotions, and similar facial expression often occur under different emotions, we consider that there is no absolute visual pattern of a smile corresponding to happiness. Therefore, in this study, we assumed that a smile with happiness'' is observed as the temporal ascent in the degree of smiling and attempted to recognize this by capturing changes in facial expression within temporally sequential images. As an implementation of this scheme, we proposed a Siamese-structure deep neural network to compare facial expressions in two input images and estimate the existence of smile ascension or descension. For primal analysis of the proposed network, we developed a unique smiling dataset containing image pairs with various changes in smiling degree, including slight changes. The results demonstrated that the proposed method achieved nearly perfect recognition with >0.95 accuracy when recognizing changes in the degree of smiling that humans certainly recognize. Attention regions that contributed to the predicted labels were concentrated on the mouth, cheeks, and tail of the eyes, which indicates a reasonable function for recognizing changes in smiling degree was constructed by the proposed method.

#### Facial Expression Recognition Using Residual Masking Network

Luan Pham, Vu Huynh, Tuan Anh Tran
Track 5: Image and Signal Processing
Thu 14 Jan 2021 at 16:00 in session PS T5.6

Auto-TLDR; Deep Residual Masking for Automatic Facial Expression Recognition

Automatic facial expression recognition (FER) has gained much attention due to its applications in human-computer interaction. Among the approaches to improve FER tasks, this paper focuses on deep architecture with the attention mechanism. We propose a novel Masking idea to boost the performance of CNN in facial expression task. It uses a segmentation network to refine feature maps, enabling the network to focus on relevant information to make correct decisions. In experiments, we combine the ubiquitous Deep Residual Network and Unet-like architecture to produce a Residual Masking Network. The proposed method holds state-of-the-art (SOTA) accuracy on the well-known FER2013 and private VEMO datasets. Our works are available on Github.

#### Deep Multi-Task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing

Rui Zhao, Tianshan Liu, Jun Xiao, P. K. Daniel Lun, Kin-Man Lam
Track 2: Biometrics, Human Analysis and Behavior Understanding
Thu 14 Jan 2021 at 12:00 in session PS T2.4

Auto-TLDR; Multi-task Learning for Facial Expression Recognition and Synthesis

Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks. However, most existing methods take into limited consideration the feature selection, when transferring information between different tasks, which may lead to task interference when training the multi-task networks. To address this problem, we propose a novel selective feature-sharing method, and establish a multi-task network for facial expression recognition and facial expression synthesis. The proposed method can effectively transfer beneficial features between different tasks, while filtering out useless and harmful information. Moreover, we employ the facial expression synthesis task to enlarge and balance the training dataset to further enhance the generalization ability of the proposed method. Experimental results show that the proposed method achieves state-of-the-art performance on those commonly used facial expression recognition benchmarks, which makes it a potential solution to real-world facial expression recognition problems.

#### Responsive Social Smile: A Machine-Learning Based Multimodal Behavior Assessment Framework towards Early Stage Autism Screening

Yueran Pan, Kunjing Cai, Ming Cheng, Xiaobing Zou, Ming Li
Track 2: Biometrics, Human Analysis and Behavior Understanding
Wed 13 Jan 2021 at 12:00 in session PS T2.2

Auto-TLDR; Responsive Social Smile: A Machine Learningbased Assessment Framework for Early ASD Screening

Autism spectrum disorder (ASD) is a neurodevelopmental disorder, which causes social deﬁcits in social lives. Early ASD screening for children is an important method to reduce the impact of ASD on people’s whole lives. Traditional screening methods rely on protocol experiments and subjective evaluations from clinicians and domain experts and thereby cost a lot. To standardize the process of ASD screening, we 1 collaborate with a group of ASD experts, and design a ”Responsive Social Smile” protocol and an experiment environment. Also, we propose a machine learningbased assessment framework for early ASD screening. By integrating technologies of speech recognition and computer vision, the framework can quantitatively analyze the behaviors of children under well-designed protocols. By collecting 196 test samples from 41 children in the clinical treatments, our proposed method obtains 85.20% accuracy for the score prediction of individual protocol, and 80.49% unweighted accuracy for the ﬁnal ASD prediction. This result indicates that our model reaches the average level of domain experts in ASD diagnosis.

#### Learning Disentangled Representations for Identity Preserving Surveillance Face Camouflage

Jingzhi Li, Lutong Han, Hua Zhang, Xiaoguang Han, Jingguo Ge, Xiaochu Cao
Track 2: Biometrics, Human Analysis and Behavior Understanding
Thu 14 Jan 2021 at 12:00 in session PS T2.4

Auto-TLDR; Individual Face Privacy under Surveillance Scenario with Multi-task Loss Function

In this paper, we focus on protecting the person face privacy under the surveillance scenarios, whose goal is to change the visual appearances of faces while keep them to be recognizable by current face recognition systems. This is a challenging problem as that we should retain the most important structures of captured facial images, while alter the salient facial regions to protect personal privacy. To address this problem, we introduce a novel individual face protection model, which can camouflage the face appearance from the perspective of human visual perception and preserve the identity features of faces used for face authentication. To that end, we develop an encoder-decoder network architecture that can separately disentangle the person feature representation into an appearance code and an identity code. Specifically, we first randomly divide the face image into two groups, the source set and the target set, where the source set is used to extract the identity code and the target set provides the appearance code. Then, we recombine the identity and appearance codes to synthesize a new face, which has the same identity with the source subject. Finally, the synthesized faces are used to replace the original face to protect the privacy of individual. Furthermore, our model is trained end-to-end with a multi-task loss function, which can better preserve the identity and stabilize the training loss. Experiments conducted on Cross-Age Celebrity dataset demonstrate the effectiveness of our model and validate our superiority in terms of visual quality and scalability.

#### Facial Expression Recognition by Using a Disentangled Identity-Invariant Expression Representation

Kamran Ali, Charles Hughes
Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; Transfer-based Expression Recognition Generative Adversarial Network (TER-GAN)

Facial Expression Recognition (FER) is a challenging task because many factors of variation such as pose, illumination, and identity-specific attributes are entangled with the expression information in an expressive face image. Recent works show that the performance of a FER algorithm can be improved by disentangling the expression information from identity features. In this paper, we present Transfer-based Expression Recognition Generative Adversarial Network (TER-GAN) that combines the effectiveness of a novel feature disentanglement technique with the concept of identity-invariant expression representation learning for facial expression recognition. More specifically, TER-GAN learns a disentangled expression representation by extracting expression features from one image and transferring the expression information to the identity of another image. To improve the feature disentanglement process, and to learn an identity-invariant expression representation, we introduce a novel expression consistency loss and an identity consistency loss that exploit expression and identity information from both real and synthetic images. We evaluated the performance of our proposed facial expression recognition technique by employing five public facial expression databases, CK+, Oulu-CASIA, MMI, BU-3DFE, and BU-4DFE, the latter being used for pre-training. The experimental results show the effectiveness of the proposed technique.

#### Unconstrained Facial Expression Recogniton Based on Cascade Decision and Gabor Filters

Yanhong Wu, Lijie Zhang, Guannan Chen, Pablo Navarrete Michelini
Track 2: Biometrics, Human Analysis and Behavior Understanding
Thu 14 Jan 2021 at 14:00 in session OS T2.2

Auto-TLDR; Convolutional Neural Network for Facial Expression Recognition under unconstrained natural conditions

Facial Expression Recognition (FER) research with Convolutional Neural Networks (CNN) has been active, especially under unconstrained natural conditions. From our observation, prior arts treat expressions equally in classification and the reconition accuracy of some expression are always higher than others. In this paper, we make the assumption that an expression with a higher accuracy is easier to be recognized, and those expressions easier to recognize will hinder the recognition of uneasy expressions. Then, we propose a novel algorithm for unconstrained FER based on cascade decision and Gabor filters. Easier expressions are recognized before the difficult expressions. This simple method trains up to five models to cascadedly recognize a given facial image expression. The first binary classifier model is for the classification of Happy with the highest accuracy. The second binary classifier model is for the classification of Surprise with the second high accuracy. The third binary classifier model is for the classification of Neutral with the third high accuracy. The forth model is for the classification of Sad with the forth high accuracy. And the final model is 3-class classifier for Angry, Disgust and Fear. Gabor filters are included in every model to enhance robustness on illumination variations and face poses. Extensive experiment results on several datasets validate the effectiveness of the proposed method. We obtain accuracy of 77.6% on FER2013 with the final models, outperforming the latest state-of-the-arts.

#### Identity-Aware Facial Expression Recognition in Compressed Video

Xiaofeng Liu, Linghao Jin, Xu Han, Jun Lu, Jonghye Woo, Jane You
Track 5: Image and Signal Processing
Wed 13 Jan 2021 at 14:00 in session OS T5.3

Auto-TLDR; Exploring Facial Expression Representation in Compressed Video with Mutual Information Minimization

This paper targets to explore the inter-subject variations eliminated facial expression representation in the compressed video domain. Most of the previous methods process the RGB images of a sequence, while the off-the-shelf and valuable expression-related muscle movement already embedded in the compression format. In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possible to extract identity factors from the I frame with a pre-trained face recognition network. By enforcing the marginal independent of them, the expression feature is expected to be purer for the expression and be robust to identity shifts. Specifically, we propose a novel collaborative min-min game for mutual information (MI) minimization in latent space. We do not need the identity label or multiple expression samples from the same person for identity elimination. Moreover, when the apex frame is annotated in the dataset, the complementary constraint can be further added to regularize the feature-level game. In testing, only the compressed residual frames are required to achieve expression prediction. Our solution can achieve comparable or better performance than the recent decoded image based methods on the typical FER benchmarks with about 3$\times$ faster inference with compressed data.

#### Depth Videos for the Classification of Micro-Expressions

Ankith Jain Rakesh Kumar, Bir Bhanu, Christopher Casey, Sierra Cheung, Aaron Seitz
Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; RGB-D Dataset for the Classification of Facial Micro-expressions

Facial micro-expressions are spontaneous, subtle, involuntary muscle movements occurring briefly on the face. The spotting and recognition of these expressions are difficult due to the subtle behavior, and the time duration of these expressions is about half a second, which makes it difficult for humans to identify them. These micro-expressions have many applications in our daily life, such as in the field of online learning, game playing, lie detection, and therapy sessions. Traditionally, researchers use RGB images/videos to spot and classify these micro-expressions, which pose challenging problems, such as illumination, privacy concerns and pose variation. The use of depth videos solves these issues to some extent, as the depth videos are not susceptible to the variation in illumination. This paper describes the collection of a first RGB-D dataset for the classification of facial micro-expressions into 6 universal expressions: Anger, Happy, Sad, Fear, Disgust, and Surprise. This paper shows the comparison between the RGB and Depth videos for the classification of facial micro-expressions. Further, a comparison of results shows that depth videos alone can be used to classify facial micro-expressions correctly in a decision tree structure by using the traditional and deep learning approaches with good classification accuracy. The dataset will be released to the public in the near future.

#### Quality-Based Representation for Unconstrained Face Recognition

Nelson Méndez-Llanes, Katy Castillo-Rosado, Heydi Mendez-Vazquez, Massimo Tistarelli
Track 2: Biometrics, Human Analysis and Behavior Understanding
Thu 14 Jan 2021 at 14:00 in session OS T2.2

Auto-TLDR; activation map for face recognition in unconstrained environments

Significant advances have been achieved in face recognition in the last decade thanks to the development of deep learning methods. However, recognizing faces captured in uncontrolled environments is still a challenging problem for the scientific community. In these scenarios, the performance of most of existing deep learning based methods abruptly falls, due to the bad quality of the face images. In this work, we propose to use an activation map to represent the quality information in a face image. Different face regions are analyzed to determine their quality and then only those regions with good quality are used to perform the recognition using a given deep face model. For experimental evaluation, in order to simulate unconstrained environments, three challenging databases, with different variations in appearance, were selected: the Labeled Faces in the Wild Database, the Celebrities in Frontal-Profile in the Wild Database, and the AR Database. Three deep face models were used to evaluate the proposal on these databases and in all cases, the use of the proposed activation map allows the improvement of the recognition rates obtained by the original models in a range from 0.3 up to 31%. The obtained results experimentally demonstrated that the proposal is able to select those face areas with higher discriminative power and enough identifying information, while ignores the ones with spurious information.

#### Pixel-based Facial Expression Synthesis

Arbish Akram, Nazar Khan
Track 1: Artificial Intelligence, Machine Learning for Pattern Analysis
Thu 14 Jan 2021 at 12:00 in session PS T1.9

Auto-TLDR; pixel-based facial expression synthesis using GANs

Recently, Facial expression synthesis has shown remarkable advances with the advent of Generative Adversarial Networks (GANs). However, these GAN-based approaches mostly generate photo-realistic results as long as the target data distribution is close to the training data distribution. The quality of GANs results significantly degrades when testing images are from a slightly different distribution. In this work, we propose a pixel-based facial expression synthesis method. Recent work has shown that facial expression synthesis changes only local regions of faces. In the proposed method, each output pixel observes only one input pixel. The proposed method achieves generalization capability by leveraging only few hundred images. Experimental results demonstrate that the proposed method performs comparably with the recent GANs on in-dataset images and significantly outperforms on in the wild images. In addition, the proposed method is faster and it also achieves significantly better performance with two orders of magnitudes lesser computational and storage cost as compared to state-of-the-art GAN-based methods.

#### Attribute-Based Quality Assessment for Demographic Estimation in Face Videos

Fabiola Becerra-Riera, Annette Morales-González, Heydi Mendez-Vazquez, Jean-Luc Dugelay
Track 2: Biometrics, Human Analysis and Behavior Understanding
Thu 14 Jan 2021 at 14:00 in session OS T2.2

Auto-TLDR; Facial Demographic Estimation in Video Scenarios Using Quality Assessment

Most existing works regarding facial demographic estimation are focused on still image datasets, although nowadays the need to analyze video content in real applications is increasing. We propose to tackle gender, age and ethnicity estimation in the context of video scenarios. Our main contribution is to use an attribute-specific quality assessment procedure to select best quality frames from a video sequence for each of the three demographic modalities. Best quality frames are classified with fine-tuned MobileNet models and a final video prediction is obtained with a majority voting strategy among the best selected frames. Our validation on three different datasets and our comparison with state-of-the-art models, show the effectiveness of the proposed demographic classifiers and the quality pipeline, which allows to reduce both: the number of frames to be classified and the processing time in practical applications; and improves the soft biometrics prediction accuracy.

#### Interpretable Emotion Classification Using Temporal Convolutional Models

Manasi Bharat Gund, Abhiram Ravi Bharadwaj, Ifeoma Nwogu
Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; Understanding the Dynamics of Facial Emotion Expression with Spatiotemporal Representations

As with many problems solved by deep neural networks, existing solutions rarely explain, precisely, the important factors responsible for the predictions made by the model. This work looks to investigate how different spatial regions and landmark points change in position over time, to better explain the underlying factors responsible for various facial emotion expressions. By pinpointing the specific regions or points responsible for the classification of a particular facial expression, we gain better insight into the dynamics of the face when displaying that emotion. To accomplish this, we examine two spatiotemporal representations of moving faces, while expressing different emotions. The representations are then presented to a convolutional neural network for emotion classification. Class activation maps are used in highlighting the regions of interest and the results are qualitatively compared with the well known facial action units, using the facial action coding system. The model was originally trained and tested on the CK+ dataset for emotion classification, and then generalized to the SAMM dataset. In so doing, we successfully present an interpretable technique for understanding the dynamics that occur during convolutional-based prediction tasks on sequences of face data.

#### Self-Supervised Learning of Dynamic Representations for Static Images

Siyang Song, Enrique Sanchez, Linlin Shen, Michel Valstar
Track 2: Biometrics, Human Analysis and Behavior Understanding
Wed 13 Jan 2021 at 14:00 in session PS T2.3

Auto-TLDR; Facial Action Unit Intensity Estimation and Affect Estimation from Still Images with Multiple Temporal Scale

Facial actions are spatio-temporal signals by nature, and therefore their modeling is crucially dependent on the availability of temporal information. In this paper, we focus on inferring such temporal dynamics of facial actions when no explicit temporal information is available, i.e. from still images. We present a novel approach to capture multiple scales of such temporal dynamics, with an application to facial Action Unit (AU) intensity estimation and dimensional affect estimation. In particular, 1) we propose a framework that infers a dynamic representation (DR) from a still image, which captures the bi-directional flow of time within a short time-window centered at the input image; 2) we show that we can train our method without the need of explicitly generating target representations, allowing the network to represent dynamics more broadly; and 3) we propose to apply a multiple temporal scale approach that infers DRs for different window lengths (MDR) from a still image. We empirically validate the value of our approach on the task of frame ranking, and show how our proposed MDR attains state of the art results on BP4D for AU intensity estimation and on SEMAINE for dimensional affect estimation, using only still images at test time.

#### DAIL: Dataset-Aware and Invariant Learning for Face Recognition

Gaoang Wang, Chen Lin, Tianqiang Liu, Mingwei He, Jiebo Luo
Track 2: Biometrics, Human Analysis and Behavior Understanding
Fri 15 Jan 2021 at 15:00 in session PS T2.5

Auto-TLDR; DAIL: Dataset-Aware and Invariant Learning for Face Recognition

To achieve good performance in face recognition, a large scale training dataset is usually required. A simple yet effective way for improving the recognition performance is to use a dataset as large as possible by combining multiple datasets in the training. However, it is problematic and troublesome to naively combine different datasets due to two major issues. Firstly, the same person can possibly appear in different datasets, leading to the identity overlapping issue between different datasets. Natively treating the same person as different classes in different datasets during training will affect back-propagation and generate non-representative embeddings. On the other hand, manually cleaning labels will take a lot of human efforts, especially when there are millions of images and thousands of identities. Secondly, different datasets are collected in different situations and thus will lead to different domain distributions. Natively combining datasets will lead to domain distribution differences and make it difficult to learn domain invariant embeddings across different datasets. In this paper, we propose DAIL: Dataset-Aware and Invariant Learning to resolve the above-mentioned issues. To solve the first issue of identity overlapping, we propose a dataset-aware loss for multi-dataset training by reducing the penalty when the same person appears in multiple datasets. This can be readily achieved with a modified softmax loss with a dataset-aware term. To solve the second issue, the domain adaptation with gradient reversal layers is employed for dataset invariant learning. The proposed approach not only achieves state-of-the-art results on several commonly used face recognition validation sets, like LFW, CFP-FP, AgeDB-30, but also shows great benefit for practical usage.

#### High Resolution Face Age Editing

Xu Yao, Gilles Puy, Alasdair Newson, Yann Gousseau, Pierre Hellier
Track 5: Image and Signal Processing
Tue 12 Jan 2021 at 17:00 in session PS T5.2

Auto-TLDR; An Encoder-Decoder Architecture for Face Age editing on High Resolution Images

Face age editing has become a crucial task in film post-production, and is also becoming popular for general purpose photography. Recently, adversarial training has produced some of the most visually impressive results for image manipulation, including the face aging/de-aging task. In spite of considerable progress, current methods often present visual artifacts and can only deal with low-resolution images. In order to achieve aging/de-aging with the high quality and robustness necessary for wider use, these problems need to be addressed. This is the goal of the present work. We present an encoder-decoder architecture for face age editing. The core idea of our network is to encode a face image to age-invariant features, and learn a modulation vector corresponding to a target age. We then combine these two elements to produce a realistic image of the person with the desired target age. Our architecture is greatly simplified with respect to other approaches, and allows for fine-grained age editing on high resolution images in a single unified model. Source codes are available at https://github.com/InterDigitalInc/HRFAE.

#### Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion

Track 2: Biometrics, Human Analysis and Behavior Understanding
Thu 14 Jan 2021 at 14:00 in session OS T2.2

Auto-TLDR; Knowledge Distillation for Facial Expression Recognition under Occlusion

In this paper, we study the task of facial expression recognition under strong occlusion. We are particularly interested in cases where 50% of the face is occluded, e.g. when the subject wears a Virtual Reality (VR) headset. While previous studies show that pre-training convolutional neural networks (CNNs) on fully-visible (non-occluded) faces improves the accuracy, we propose to employ knowledge distillation to achieve further improvements. First of all, we employ the classic teacher-student training strategy, in which the teacher is a CNN trained on fully-visible faces and the student is a CNN trained on occluded faces. Second of all, we propose a new approach for knowledge distillation based on triplet loss. During training, the goal is to reduce the distance between an anchor embedding, produced by a student CNN that takes occluded faces as input, and a positive embedding (from the same class as the anchor), produced by a teacher CNN trained on fully-visible faces, so that it becomes smaller than the distance between the anchor and a negative embedding (from a different class than the anchor), produced by the student CNN. Third of all, we propose to combine the distilled embeddings obtained through the classic teacher-student strategy and our novel teacher-student strategy based on triplet loss into a single embedding vector. We conduct experiments on two benchmarks, FER+ and AffectNet, with two CNN architectures, VGG-f and VGG-face, showing that knowledge distillation can bring significant improvements over the state-of-the-art methods designed for occluded faces in the VR setting. Furthermore, we obtain accuracy rates that are quite close to the state-of-the-art models that take as input fully-visible faces. For example, on the FER+ data set, our VGG-face based on concatenated distilled embeddings attains an accuracy rate of 82.75% on lower-half-visible faces, which is only 2.24% below the accuracy rate of a state-of-the-art VGG-13 that is evaluated on fully-visible faces. Given that our model sees only the lower-half of the face, we consider this to be a remarkable achievement. In conclusion, we consider that our distilled CNN models can provide useful feedback for the task of recognizing the facial expressions of a person wearing a VR headset.

#### SSDL: Self-Supervised Domain Learning for Improved Face Recognition

Samadhi Poornima Kumarasinghe Wickrama Arachchilage, Ebroul Izquierdo
Track 2: Biometrics, Human Analysis and Behavior Understanding
Fri 15 Jan 2021 at 15:00 in session PS T2.5

Auto-TLDR; Self-supervised Domain Learning for Face Recognition in unconstrained environments

Face recognition in unconstrained environments is challenging due to variations in illumination, quality of sensing, motion blur and etc. An individual’s face appearance can vary drastically under different conditions creating a gap between train (source) and varying test (target) data. The domain gap could cause decreased performance levels in direct knowledge transfer from source to target. Despite fine-tuning with domain specific data could be an effective solution, collecting and annotating data for all domains is extremely expensive. To this end, we propose a self-supervised domain learning (SSDL) scheme that trains on triplets mined from unlabelled data. A key factor in effective discriminative learning, is selecting informative triplets. Building on most confident predictions, we follow an “easy-to-hard” scheme of alternate triplet mining and self-learning. Comprehensive experiments on four different benchmarks show that SSDL generalizes well on different domains.

#### How Unique Is a Face: An Investigative Study

Michal Balazia, S L Happy, Francois Bremond, Antitza Dantcheva
Track 2: Biometrics, Human Analysis and Behavior Understanding
Fri 15 Jan 2021 at 15:00 in session PS T2.5

Auto-TLDR; Uniqueness of Face Recognition: Exploring the Impact of Factors such as image resolution, feature representation, database size, age and gender

Face recognition has been widely accepted as a means of identification in applications ranging from border control to security in the banking sector. Surprisingly, while widely accepted, we still lack the understanding of the uniqueness or distinctiveness of face as a biometric characteristic. In this work, we study the impact of factors such as image resolution, feature representation, database size, age and gender on uniqueness denoted by the Kullback-Leibler divergence between genuine and impostor distributions. Towards understanding the impact, we present experimental results on the datasets AT&T, LFW, IMDb-Face, as well as ND-TWINS, with the feature extraction algorithms VGGFace, VGG16, ResNet50, InceptionV3, MobileNet and DenseNet121, that reveal the quantitative impact of the named factors. While these are early results, our findings indicate the need for a better understanding of the concept of biometric uniqueness and its implication on face recognition.

#### MRP-Net: A Light Multiple Region Perception Neural Network for Multi-Label AU Detection

Yang Tang, Shuang Chen, Honggang Zhang, Gang Wang, Rui Yang
Track 2: Biometrics, Human Analysis and Behavior Understanding
Wed 13 Jan 2021 at 12:00 in session PS T2.2

Auto-TLDR; MRP-Net: A Fast and Light Neural Network for Facial Action Unit Detection

Facial Action Units (AUs) are of great significance in communication. Automatic AU detection can improve the understanding of psychological condition and emotional status. Recently, a number of deep learning methods have been proposed to take charge with problems in automatic AU detection. Several challenges, like unbalanced labels and ignorance of local information, remain to be addressed. In this paper, we propose a fast and light neural network called MRP-Net, which is an end-to-end trainable method for facial AU detection to solve these problems. First, we design a Multiple Region Perception (MRP) module aimed at capturing different locations and sizes of features in the deeper level of the network without facial landmark points. Then, in order to balance the positive and negative samples in the large dataset, a batch balanced method adjusting the weight of every sample in one batch in our loss function is suggested. Experimental results on two popular AU datasets, BP4D and DISFA prove that MRP-Net outperforms state-of-the-art methods. Compared with the best method, not only does MRP-Net have an average F1 score improvement of 2.95% on BP4D and 5.43% on DISFA, and it also decreases the number of network parameters by 54.62% and the number of network FLOPs by 19.6%.

#### SATGAN: Augmenting Age Biased Dataset for Cross-Age Face Recognition

Wenshuang Liu, Wenting Chen, Yuanlue Zhu, Linlin Shen
Track 2: Biometrics, Human Analysis and Behavior Understanding
Wed 13 Jan 2021 at 12:00 in session PS T2.2

Auto-TLDR; SATGAN: Stable Age Translation GAN for Cross-Age Face Recognition

In this paper, we propose a Stable Age Translation GAN (SATGAN) to generate fake face images at different ages to augment age biased face datasets for Cross-Age Face Recognition (CAFR) . The proposed SATGAN consists of both generator and discriminator. As a part of the generator, a novel Mask Attention Module (MAM) is introduced to make the generator focus on the face area. In addition, the generator employs a Uniform Distribution Discriminator (UDD) to supervise the learning of latent feature map and enforce the uniform distribution. Besides, the discriminator employs a Feature Separation Module (FSM) to disentangle identity information from the age information. The quantitative and qualitative evaluations on Morph dataset prove that SATGAN achieves much better performance than existing methods. The face recognition model trained using dataset (VGGFace2 and MS-Celeb-1M) augmented using our SATGAN achieves better accuracy on cross age dataset like Cross-Age LFW and AgeDB-30.

#### Learning Semantic Representations Via Joint 3D Face Reconstruction and Facial Attribute Estimation

Zichun Weng, Youjun Xiang, Xianfeng Li, Juntao Liang, Wanliang Huo, Yuli Fu
Track 3: Computer Vision Robotics and Intelligent Systems
Thu 14 Jan 2021 at 16:00 in session PS T3.9

Auto-TLDR; Joint Framework for 3D Face Reconstruction with Facial Attribute Estimation

We propose a novel joint framework for 3D face reconstruction (3DFR) that integrates facial attribute estimation (FAE) as an auxiliary task. One of the essential problems of 3DFR is to extract semantic facial features (e.g., Big Nose, High Cheekbones, and Asian) from in-the-wild 2D images, which is inherently involved with FAE. These two tasks, though heterogeneous, are highly relevant to each other. To achieve this, we leverage a Convolutional Neural Network to extract shared facial representations for both shape decoder and attribute classifier. We further develop an in-batch hybrid-task training scheme that enables our model to learn from heterogeneous facial datasets jointly within a mini-batch. Thanks to the joint loss that provides supervision from both 3DFR and FAE domains, our model learns the correlations between 3D shapes and facial attributes, which benefit both feature extraction and shape inference. Quantitative evaluation and qualitative visualization results confirm the effectiveness and robustness of our joint framework.

#### Pose-Robust Face Recognition by Deep Meta Capsule Network-Based Equivariant Embedding

Fangyu Wu, Jeremy Simon Smith, Wenjin Lu, Bailing Zhang
Track 2: Biometrics, Human Analysis and Behavior Understanding
Fri 15 Jan 2021 at 15:00 in session PS T2.5

Auto-TLDR; Deep Meta Capsule Network-based Equivariant Embedding Model for Pose-Robust Face Recognition

Despite the exceptional success in face recognition related technologies, handling large pose variations still remains a key challenge. Current techniques for pose-robust face recognition either, directly extract pose-invariant features, or first synthesize a face that matches the target pose before feature extraction. It is more desirable to learn face representations equivariant to pose variations. To this end, this paper proposes a deep meta Capsule network-based Equivariant Embedding Model (DM-CEEM) with three distinct novelties. First, the proposed RB-CapsNet allows DM-CEEM to learn an equivariant embedding for pose variations and achieve the desired transformation for input face images. Second, we introduce a new version of a Capsule network called RB-CapsNet to extend CapsNet to perform a profile-to-frontal face transformation in deep feature space. Third, we train the DM-CEEM in a meta way by treating a single overall classification target as multiple sub-tasks that satisfy certain unknown probabilities. In each sub-task, we sample the support and query sets randomly. The experimental results on both controlled and in-the-wild databases demonstrate the superiority of DM-CEEM over state-of-the-art.

#### A Flatter Loss for Bias Mitigation in Cross-Dataset Facial Age Estimation

Ali Akbari, Muhammad Awais, Zhenhua Feng, Ammarah Farooq, Josef Kittler
Track 2: Biometrics, Human Analysis and Behavior Understanding
Wed 13 Jan 2021 at 14:00 in session PS T2.3

Auto-TLDR; Cross-dataset Age Estimation for Neural Network Training

Existing studies in facial age estimation have mostly focused on intra-dataset protocols that assume training and test images captured under similar conditions. However, this is rarely valid in practical applications, where training and test sets usually have different characteristics. In this paper, we advocate a cross-dataset protocol for age estimation benchmarking. In order to improve the cross-dataset age estimation performance, we mitigate the inherent bias caused by the learning algorithm. To this end, we propose a novel loss function that is more effective for neural network training. The relative smoothness of the proposed loss function is its advantage with regards to the optimisation process performed by stochastic gradient decent. Its lower gradient, compared with existing loss functions, facilitates the discovery of and convergence to a better optimum, and consequently a better generalisation. The cross-dataset experimental results demonstrate the superiority of the proposed method over the state-of-the-art algorithms in terms of accuracy and generalisation capability.

#### Attentive Hybrid Feature Based a Two-Step Fusion for Facial Expression Recognition

Jun Weng, Yang Yang, Zichang Tan, Zhen Lei
Track 2: Biometrics, Human Analysis and Behavior Understanding
Thu 14 Jan 2021 at 12:00 in session PS T2.4

Auto-TLDR; Attentive Hybrid Architecture for Facial Expression Recognition

Facial expression recognition is inherently a challenging task, especially for the in-the-wild images with various occlusions and large pose variations, which may lead to the loss of some crucial information. To address it, in this paper, we propose an attentive hybrid architecture (AHA) which learns global, local and integrated features based on different face regions. Compared with one type of feature, our extracted features own complementary information and can reduce the loss of crucial information. Specifically, AHA contains three branches, where all sub-networks in those branches employ the attention mechanism to further localize the interested pixels/regions. Moreover, we propose a two-step fusion strategy based on LSTM to deeply explore the hidden correlations among different face regions. Extensive experiments on four popular expression databases (i.e., CK+, FER-2013, SFEW 2.0, RAF-DB) show the effectiveness of the proposed method.

#### Quantified Facial Temporal-Expressiveness Dynamics for Affect Analysis

Md Taufeeq Uddin, Shaun Canavan
Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; quantified facial Temporal-expressiveness Dynamics for quantified affect analysis

The quantification of visual affect data (e.g. face images) is essential to build and monitor automated affect modeling systems efficiently. Considering this, this work proposes quantified facial Temporal-expressiveness Dynamics (TED) to quantify the expressiveness of human faces. The proposed algorithm leverages multimodal facial features by incorporating static and dynamic information to enable accurate measurements of facial expressiveness. We show that TED can be used for high-level tasks such as summarization of unstructured visual data, expectation from and interpretation of automated affect recognition models. To evaluate the positive impact of using TED, a case study was conducted on spontaneous pain using the UNBC-McMaster spontaneous shoulder pain dataset. Experimental results show the efficacy of using TED for quantified affect analysis.

#### Group-Wise Feature Orthogonalization and Suppression for GAN Based Facial Attribute Translation

Zhiwei Wen, Haoqian Wu, Weicheng Xie, Linlin Shen
Track 1: Artificial Intelligence, Machine Learning for Pattern Analysis
Wed 13 Jan 2021 at 12:00 in session PS T1.3

Auto-TLDR; Semantic Disentanglement of Generative Adversarial Network

Generative Adversarial Network (GAN) has been widely used for object attribute editing. However, the semantic correlation, resulted from the feature map interaction in the generative network of GAN, may impair the generalization ability of the generative network. In this work, semantic disentanglement is introduced in GAN to reduce the attribute correlation. The feature maps of the generative network are first grouped with an efficient clustering algorithm based on hash encoding, which are used to excavate hidden semantic attributes and calculate the group-wise orthogonality loss for the reduction of attribute entanglement. Meanwhile, the feature maps falling in the intersection regions of different groups are further suppressed to reduce the attribute-wise interaction. Extensive experiments reveal that the proposed GAN generated more genuine objects than the state of the arts. Quantitative results of classification accuracy, inception and FID scores further justify the effectiveness of the proposed GAN.

#### An Adaptive Video-To-Video Face Identification System Based on Self-Training

Eric Lopez-Lopez, Carlos V. Regueiro, Xosé M. Pardo
Track 2: Biometrics, Human Analysis and Behavior Understanding
Wed 13 Jan 2021 at 14:00 in session PS T2.3

Auto-TLDR; Adaptive Video-to-Video Face Recognition using Dynamic Ensembles of SVM's

Video-to-video face recognition in unconstrained conditions is still a very challenging problem, as the combination of several factors leads to an in general low-quality of facial frames. Besides, in some real contexts, the availability of labelled samples is limited, or data is streaming or it is only available temporarily due to storage constraints or privacy issues. In these cases, dealing with learning as an unsupervised incremental process is a feasible option. This work proposes a system based on dynamic ensembles of SVM's, which uses the ideas of self-training to perform adaptive Video-to-video face identification. The only label requirements of the system are a few frames (5 in our experiments) directly taken from the video-surveillance stream. The system will autonomously use additional video-frames to update and improve the initial model in an unsupervised way. Results show a significant improvement in comparison to other state-of-the-art static models.

#### Two-Level Attention-Based Fusion Learning for RGB-D Face Recognition

Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; Fused RGB-D Facial Recognition using Attention-Aware Feature Fusion

With recent advances in RGB-D sensing technologies as well as improvements in machine learning and fusion techniques, RGB-D facial recognition has become an active area of research. A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition. The proposed method first extracts features from both modalities using a convolutional feature extractor. These features are then fused using a two layer attention mechanism. The first layer focuses on the fused feature maps generated by the feature extractor, exploiting the relationship between feature maps using LSTM recurrent learning. The second layer focuses on the spatial features of those maps using convolution. The training database is preprocessed and augmented through a set of geometric transformations, and the learning process is further aided using transfer learning from a pure 2D RGB image training process. Comparative evaluations demonstrate that the proposed method outperforms other state-of-the-art approaches, including both traditional and deep neural network-based methods, on the challenging CurtinFaces and IIIT-D RGB-D benchmark databases, achieving classification accuracies over 98.2% and 99.3% respectively. The proposed attention mechanism is also compared with other attention mechanisms, demonstrating more accurate results.

#### Pose-Based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation

Zhengyuan Yang, Amanda Kay, Yuncheng Li, Wendi Cross, Jiebo Luo
Track 2: Biometrics, Human Analysis and Behavior Understanding
Tue 12 Jan 2021 at 17:00 in session PS T2.1

Auto-TLDR; Body Language Based Emotion Recognition for Psychiatric Symptoms Prediction

Inspired by the human ability to infer emotions from body language, we propose an automated framework for body language based emotion recognition starting from regular RGB videos. In collaboration with psychologists, we further extend the framework for psychiatric symptom prediction. Because a specific application domain of the proposed framework may only supply a limited amount of data, the framework is designed to work on a small training set and possess a good transferability. The proposed system in the first stage generates sequences of body language predictions based on human poses estimated from input videos. In the second stage, the predicted sequences are fed into a temporal network for emotion interpretation and psychiatric symptom prediction. We first validate the accuracy and transferability of the proposed body language recognition method on several public action recognition datasets. We then evaluate the framework on a proposed URMC dataset, which consists of conversations between a standardized patient and a behavioral health professional, along with expert annotations of body language, emotions, and potential psychiatric symptoms. The proposed framework outperforms other methods on the URMC dataset.

#### Unsupervised Disentangling of Viewpoint and Residues Variations by Substituting Representations for Robust Face Recognition

Minsu Kim, Joanna Hong, Junho Kim, Hong Joo Lee, Yong Man Ro
Track 2: Biometrics, Human Analysis and Behavior Understanding
Fri 15 Jan 2021 at 15:00 in session PS T2.5

Auto-TLDR; Unsupervised Disentangling of Identity, viewpoint, and Residue Representations for Robust Face Recognition

It is well-known that identity-unrelated variations (e.g., viewpoint or illumination) degrade the performances of face recognition methods. In order to handle this challenge, a robust method for disentangling the identity and view representations has drawn an attention in the machine learning area. However, existing methods learn discriminative features which require a manual supervision of such factors of variations. In this paper, we propose a novel disentangling framework through modeling three representations of identity, viewpoint, and residues (i.e., identity and pose unrelated) which do not require supervision of the variations. By jointly modeling the three representations, we enhance the disentanglement of each representation and achieve robust face recognition performance. Further, the learned viewpoint representation can be utilized for pose estimation or editing of a posed facial image. Extensive quantitative and qualitative evaluations verify the effectiveness of our proposed method which disentangles identity, viewpoint, and residues of facial images.

#### Magnifying Spontaneous Facial Micro Expressions for Improved Recognition

Pratikshya Sharma, Sonya Coleman, Pratheepan Yogarajah, Laurence Taggart, Pradeepa Samarasinghe
Track 2: Biometrics, Human Analysis and Behavior Understanding
Fri 15 Jan 2021 at 15:00 in session PS T2.5

Auto-TLDR; Eulerian Video Magnification for Micro Expression Recognition

Building an effective automatic micro expression recognition (MER) system is becoming increasingly desirable in computer vision applications. However, it is also very challenging given the fine-grained nature of the expressions to be recognized. Hence, we investigate if amplifying micro facial muscle movements as a pre-processing phase, by employing Eulerian Video Magnification (EVM), can boost performance of Local Phase Quantization with Three Orthogonal Planes (LPQ-TOP) to achieve improved facial MER across various datasets. In addition, we examine the rate of increase for recognition to determine if it is uniform across datasets using EVM. Ultimately, we classify the extracted features using Support Vector Machines (SVM). We evaluate and compare the performance with various methods on seven different datasets namely CASME, CAS(ME)2, CASME2, SMIC-HS, SMIC-VIS, SMIC-NIR and SAMM. The results obtained demonstrate that EVM can enhance LPQ-TOP to achieve improved recognition accuracy on the majority of the datasets.

#### ClusterFace: Joint Clustering and Classification for Set-Based Face Recognition

Samadhi Poornima Kumarasinghe Wickrama Arachchilage, Ebroul Izquierdo
Track 2: Biometrics, Human Analysis and Behavior Understanding
Wed 13 Jan 2021 at 14:00 in session PS T2.3

Auto-TLDR; Joint Clustering and Classification for Face Recognition in the Wild

Deep learning technology has enabled successful modeling of complex facial features when high quality images are available. Nonetheless, accurate modeling and recognition of human faces in real world scenarios 'on the wild' or under adverse conditions remains an open problem. When unconstrained faces are mapped into deep features, variations such as illumination, pose, occlusion, etc., can create inconsistencies in the resultant feature space. Hence, deriving conclusions based on direct associations could lead to degraded performance. This rises the requirement for a basic feature space analysis prior to face recognition. This paper devises a joint clustering and classification scheme which learns deep face associations in an easy-to-hard way. Our method is based on hierarchical clustering where the early iterations tend to preserve high reliability. The rationale of our method is that a reliable clustering result can provide insights on the distribution of the feature space, that can guide the classification that follows. Experimental evaluations on three tasks, face verification, face identification and rank-order search, demonstrates better or competitive performance compared to the state-of-the-art, on all three experiments.

#### Exemplar Guided Cross-Spectral Face Hallucination Via Mutual Information Disentanglement

Haoxue Wu, Huaibo Huang, Aijing Yu, Jie Cao, Zhen Lei, Ran He
Track 1: Artificial Intelligence, Machine Learning for Pattern Analysis
Wed 13 Jan 2021 at 14:00 in session PS T1.6

Auto-TLDR; Exemplar Guided Cross-Spectral Face Hallucination with Structural Representation Learning

Recently, many Near infrared-visible (NIR-VIS) heterogeneous face recognition (HFR) methods have been proposed in the community. But it remains a challenging problem because of the sensing gap along with large pose variations. In this paper, we propose an Exemplar Guided Cross-Spectral Face Hallucination (EGCH) to reduce the domain discrepancy through disentangled representation learning. For each modality, EGCH contains a spectral encoder as well as a structure encoder to disentangle spectral and structure representation, respectively. It also contains a traditional generator that reconstructs the input from the above two representations, and a structure generator that predicts the facial parsing map from the structure representation. Besides, mutual information minimization and maximization are conducted to boost disentanglement and make representations adequately expressed. Then the translation is built on structure representations between two modalities. Provided with the transformed NIR structure representation and original VIS spectral representation, EGCH is capable to produce high-fidelity VIS images that preserve the topology structure of the input NIR while transfer the spectral information of an arbitrary VIS exemplar. Extensive experiments demonstrate that the proposed method achieves more promising results both qualitatively and quantitatively than the state-of-the-art NIR-VIS methods.

#### Contrastive Data Learning for Facial Pose and Illumination Normalization

Gee-Sern Hsu, Chia-Hao Tang
Track 2: Biometrics, Human Analysis and Behavior Understanding
Fri 15 Jan 2021 at 15:00 in session PS T2.5

Auto-TLDR; Pose and Illumination Normalization with Contrast Data Learning for Face Recognition

Face normalization can be a crucial step when handling generic face recognition. We propose the Pose and Illumination Normalization (PIN) framework with contrast data learning for face normalization. The PIN framework is designed to learn the transformation from a source set to a target set. The source set and the target set compose a contrastive data set for learning. The source set contains faces collected in the wild and thus covers a wide range of variation across illumination, pose, expression and other variables. The target set contains face images taken under controlled conditions and all faces are in frontal pose and balanced in illumination. The PIN framework is composed of an encoder, a decoder and two discriminators. The encoder is made of a state-of-the-art face recognition network and acts as a facial feature extractor, which is not updated during training. The decoder is trained on both the source and target sets, and aims to learn the transformation from the source set to the target set; and therefore, it can transform an arbitrary face into a illumination and pose normalized face. The discriminators are trained to ensure the photo-realistic quality of the normalized face images generated by the decoder. The loss functions employed in the decoder and discriminators are appropriately designed and weighted for yielding better normalization outcomes and recognition performance. We verify the performance of the propose framework on several benchmark databases, and compare with state-of-the-art approaches.

#### Multi-Attribute Learning with Highly Imbalanced Data

Lady Viviana Beltran Beltran, Mickaël Coustaty, Nicholas Journet, Juan C. Caicedo, Antoine Doucet
Track 1: Artificial Intelligence, Machine Learning for Pattern Analysis
Wed 13 Jan 2021 at 16:30 in session PS T1.8

Auto-TLDR; Data Imbalance in Multi-Attribute Deep Learning Models: Adaptation to face each one of the problems derived from imbalance

Data is one of the most important keys for success when studying a simple or a complex phenomenon. With the use of deep-learning exploding and its democratization, non-computer science experts may struggle to use highly complex deep learning architectures, even when straightforward models offer them suitable performances. In this article, we study the specific and common problem of data imbalance in real databases as most of the bad performance problems are due to the data itself. We review two points: first, when the data contains different levels of imbalance. Classical imbalanced learning strategies cannot be directly applied when using multi-attribute deep learning models, i.e., multi-task and multi-label architectures. Therefore, one of our contributions is our proposed adaptations to face each one of the problems derived from imbalance. Second, we demonstrate that with little to no imbalance, straightforward deep learning models work well. However, for non-experts, these models can be seen as black boxes, where all the effort is put in pre-processing the data. To simplify the problem, we performed the classification task ignoring information that is costly to extract, such as part localization which is widely used in the state of the art of attribute classification. We make use of a widely known attribute database, CUB-200-2011 - CUB as our main use case due to its deeply imbalanced nature, along with two better structured databases: celebA and Awa2. All of them contain multi-attribute annotations. The results of highly fine-grained attribute learning over CUB demonstrate that in the presence of imbalance, by using our proposed strategies is possible to have competitive results against the state of the art, while taking advantage of multi-attribute deep learning models. We also report results for two better-structured databases over which our models over-perform the state of the art.

#### Person Recognition with HGR Maximal Correlation on Multimodal Data

Yihua Liang, Fei Ma, Yang Li, Shao-Lun Huang
Track 5: Image and Signal Processing
Thu 14 Jan 2021 at 12:00 in session PS T5.5

Auto-TLDR; A correlation-based multimodal person recognition framework that learns discriminative embeddings of persons by joint learning visual features and audio features

Multimodal person recognition is a common task in video analysis and public surveillance, where information from multiple modalities, such as images and audio extracted from videos, are used to jointly determine the identity of a person. Previous person recognition techniques either use only uni-modal data or only consider shared representations between different input modalities, while leaving the extraction of their relationship with identity information to downstream tasks. Furthermore, real-world data often contain noise, which makes recognition more challenging practical situations. In our work, we propose a novel correlation-based multimodal person recognition framework that is relatively simple but can efficaciously learn supervised information in multimodal data fusion and resist noise. Specifically, our framework learns a discriminative embeddings of persons by joint learning visual features and audio features while maximizing HGR maximal correlation among multimodal input and persons' identities. Experiments are done on a subset of Voxceleb2. Compared with state-of-the-art methods, the proposed method demonstrates an improvement of accuracy and robustness to noise.

#### Two-Stream Temporal Convolutional Network for Dynamic Facial Attractiveness Prediction

Nina Weng, Jiahao Wang, Annan Li, Yunhong Wang
Track 5: Image and Signal Processing
Fri 15 Jan 2021 at 15:00 in session PS T5.7

Auto-TLDR; 2S-TCN: A Two-Stream Temporal Convolutional Network for Dynamic Facial Attractiveness Prediction

In the field of facial attractiveness prediction, while deep models using static pictures have shown promising results, little attention is paid to dynamic facial information, which is proven to be influential by psychological studies. Meanwhile, the increasing popularity of short video apps creates an enormous demand of facial attractiveness prediction from short video clips. In this paper, we target on the dynamic facial attractiveness prediction problem. To begin with, a large-scale video-based facial attractiveness prediction dataset (VFAP) with more than one thousand clips from TikTok is collected. A two-stream temporal convolutional network (2S-TCN) is then proposed to capture dynamic attractiveness feature from both facial appearance and landmarks. We employ attentive feature enhancement along with specially designed modality and temporal fusion strategies to better explore the temporal dynamics. Extensive experiments on the proposed VFAP dataset demonstrate that 2S-TCN has a distinct advantage over the state-of-the-art static prediction methods.

#### Generating Private Data Surrogates for Vision Related Tasks

Ryan Webster, Julien Rabin, Loic Simon, Frederic Jurie
Track 1: Artificial Intelligence, Machine Learning for Pattern Analysis
Wed 13 Jan 2021 at 14:00 in session PS T1.5

Auto-TLDR; Generative Adversarial Networks for Membership Inference Attacks

With the widespread application of deep networks in industry, membership inference attacks, i.e. the ability to discern training data from a model, become more and more problematic for data privacy. Recent work suggests that generative networks may be robust against membership attacks. In this work, we build on this observation, offering a general-purpose solution to the membership privacy problem. As the primary contribution, we demonstrate how to construct surrogate datasets, using images from GAN generators, labelled with a classifier trained on the private dataset. Next, we show this surrogate data can further be used for a variety of downstream tasks (here classification and regression), while being resistant to membership attacks. We study a variety of different GANs proposed in the literature, concluding that higher quality GANs result in better surrogate data with respect to the task at hand.

#### Local Facial Attribute Transfer through Inpainting

Ricard Durall, Franz-Josef Pfreundt, Janis Keuper
Track 1: Artificial Intelligence, Machine Learning for Pattern Analysis
Wed 13 Jan 2021 at 14:00 in session PS T1.5

Auto-TLDR; Attribute Transfer Inpainting Generative Adversarial Network

The term attribute transfer refers to the tasks of altering images in such a way, that the semantic interpretation of a given input image is shifted towards an intended direction, which is quantified by semantic attributes. Prominent example applications are photo realistic changes of facial features and expressions, like changing the hair color, adding a smile, enlarging the nose or altering the entire context of a scene, like transforming a summer landscape into a winter panorama. Recent advances in attribute transfer are mostly based on generative deep neural networks, using various techniques to manipulate images in the latent space of the generator. In this paper, we present a novel method for the common sub-task of local attribute transfers, where only parts of a face have to be altered in order to achieve semantic changes (e.g. removing a mustache). In contrast to previous methods, where such local changes have been implemented by generating new (global) images, we propose to formulate local attribute transfers as an inpainting problem. Removing and regenerating only parts of images, our Attribute Transfer Inpainting Generative Adversarial Network (ATI-GAN) is able to utilize local context information to focus on the attributes while keeping the background unmodified resulting in visually sound results.

#### Real-Time Driver Drowsiness Detection Using Facial Action Units

Malaika Vijay, Nandagopal Netrakanti Vinayak, Maanvi Nunna, Subramanyam Natarajan
Track 3: Computer Vision Robotics and Intelligent Systems
Fri 15 Jan 2021 at 16:00 in session PS T3.11

Auto-TLDR; Real-Time Detection of Driver Drowsiness using Facial Action Units using Extreme Gradient Boosting

This paper presents a two-stage, vision-based pipeline for the real-time detection of driver drowsiness using Facial Action Units (FAUs). FAUs capture movements in groups of muscles in the face like widening of the eyes or dropping of the jaw. The first stage of the pipeline employs a Convolutional Neural Network (CNN) trained to detect FAUs. The output of the penultimate layer of this network serves as an image embedding that captures features relevant to FAU detection. These embeddings are then used to predict drowsiness using an Extreme Gradient Boosting (XGBoost) classifier. A separate XGBoost model is trained for each user of the system so that behavior specific to each user can be modeled into the drowsiness classifier. We show that user-specific classifiers require very little data and low training time to yield high prediction accuracies in real-time.

#### Continuous Learning of Face Attribute Synthesis

Ning Xin, Shaohui Xu, Fangzhe Nan, Xiaoli Dong, Weijun Li, Yuanzhou Yao
Track 5: Image and Signal Processing
Thu 14 Jan 2021 at 16:00 in session PS T5.6

Auto-TLDR; Continuous Learning for Face Attribute Synthesis

The generative adversarial network (GAN) exhibits great superiority in the face attribute synthesis task. However, existing methods have very limited effects on the expansion of new attributes. To overcome the limitations of a single network in new attribute synthesis, a continuous learning method for face attribute synthesis is proposed in this work. First, the feature vector of the input image is extracted and attribute direction regression is performed in the feature space to obtain the axes of different attributes. The feature vector is then linearly guided along the axis so that images with target attributes can be synthesized by the decoder. Finally, to make the network capable of continuous learning, the orthogonal direction modification module is used to extend the newly-added attributes. Experimental results show that the proposed method can endow a single network with the ability to learn attributes continuously, and, as compared to those produced by the current state-of-the-art methods, the synthetic attributes have higher accuracy.

#### Hybrid Approach for 3D Head Reconstruction: Using Neural Networks and Visual Geometry

Oussema Bouafif, Bogdan Khomutenko, Mohammed Daoudi
Track 3: Computer Vision Robotics and Intelligent Systems
Fri 15 Jan 2021 at 16:00 in session PS T3.11

Auto-TLDR; Recovering 3D Head Geometry from a Single Image using Deep Learning and Geometric Techniques

Recovering the 3D geometric structure of a face from a single input image is a challenging active research area in computer vision. In this paper, we present a novel method for reconstructing 3D heads from a single or multiple image(s) using a hybrid approach based on deep learning and geometric techniques. We propose an encoder-decoder network based on the U-net architecture and trained on synthetic data only. It predicts both pixel-wise normal vectors and landmarks maps from a single input photo. Landmarks are used for the pose computation and the initialization of the optimization problem, which, in turn, reconstructs the 3D head geometry by using a parametric morphable model and normal vector fields. State-of-the-art results are achieved through qualitative and quantitative evaluation tests on both single and multi-view settings. Despite the fact that the model was trained only on synthetic data, it successfully recovers 3D geometry and precise poses for real-world images.

#### Video Face Manipulation Detection through Ensemble of CNNs

Nicolo Bonettini, Edoardo Daniele Cannas, Sara Mandelli, Luca Bondi, Paolo Bestagini, Stefano Tubaro
Track 5: Image and Signal Processing
Tue 12 Jan 2021 at 14:00 in session OS T5.1

Auto-TLDR; Face Manipulation Detection in Video Sequences Using Convolutional Neural Networks

In the last few years, several techniques for facial manipulation in videos have been successfully developed and made available to the masses (i.e., FaceSwap, deepfake, etc.). These methods enable anyone to easily edit faces in video sequences with incredibly realistic results and a very little effort. Despite the usefulness of these tools in many fields, if used maliciously, they can have a significantly bad impact on society (e.g., fake news spreading, cyber bullying through fake revenge porn). The ability of objectively detecting whether a face has been manipulated in a video sequence is then a task of utmost importance. In this paper, we tackle the problem of face manipulation detection in video sequences targeting modern facial manipulation techniques. In particular, we study the ensembling of different trained Convolutional Neural Network (CNN) models. In the proposed solution, different models are obtained starting from a base network (i.e., EfficientNetB4) making use of two different concepts: (i) attention layers; (ii) siamese training. We show that combining these networks leads to promising face manipulation detection results on two publicly available datasets with more than 119000 videos.

#### Inner Eye Canthus Localization for Human Body Temperature Screening

Claudio Ferrari, Lorenzo Berlincioni, Marco Bertini, Alberto Del Bimbo
Track 3: Computer Vision Robotics and Intelligent Systems
Wed 13 Jan 2021 at 16:30 in session PS T3.6

Auto-TLDR; Automatic Localization of the Inner Eye Canthus in Thermal Face Images using 3D Morphable Face Model

In this paper, we propose an automatic approach for localizing the inner eye canthus in thermal face images. We first coarsely detect 5 facial keypoints corresponding to the center of the eyes, the nosetip and the ears. Then we compute a sparse 2D-3D points correspondence using a 3D Morphable Face Model (3DMM). This correspondence is used to project the entire 3D face onto the image, and subsequently locate the inner eye canthus. Detecting this location allows to obtain the most precise body temperature measurement for a person using a thermal camera. We evaluated the approach on a thermal face dataset provided with manually annotated landmarks. However, such manual annotations are normally conceived to identify facial parts such as eyes, nose and mouth, and are not specifically tailored for localizing the eye canthus region. As additional contribution, we enrich the original dataset by using the annotated landmarks to deform and project the 3DMM onto the images. Then, by manually selecting a small region corresponding to the eye canthus, we enrich the dataset with additional annotations. By using the manual landmarks, we ensure the correctness of the 3DMM projection, which can be used as ground-truth for future evaluations. Moreover, we supply the dataset with the 3D head poses and per-point visibility masks for detecting self-occlusions. The data will be publicly released.