Social Perception of Faces in a Vision-Language Model
California Institute of Technology（加州理工学院）；ETH Zurich（苏黎世联邦理工学院）；Computational Social Science（计算社会科学）；Swiss Data Science Center（瑞士数据科学中心）；Empa（瑞士联邦材料科学与技术研究院）
Carina I. Hausladen, Manuel Knott, Colin F. Camerer, Pietro Perona
发表信息：
Published in the Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency (FAccT 2025)
We explore social perception of human faces in CLIP, a widely used open-source vision-language model. To this end, we compare the similarity in CLIP embeddings between different textual prompts and a set of face images. Our textual prompts are constructed from well-validated social psychology terms denoting social perception. The face images are synthetic and are systematically and independently varied along six dimensions: the legally protected attributes of age, gender, and race, as well as facial expression, lighting, and pose. Independently and systematically manipulating face attributes allows us to study the effect of each on social perception and avoids confounds that can occur in wild-collected data due to uncontrolled systematic correlations between attributes. Thus, our findings are experimental rather than observational. Our main findings are three. First, while CLIP is trained on the widest variety of images and texts, it is able to make fine-grained human-like social judgments on face images. Second, age, gender, and race do systematically impact CLIP's social perception of faces, suggesting an undesirable bias in CLIP vis-a-vis legally protected attributes. Most strikingly, we find a strong pattern of bias concerning the faces of Black women, where CLIP produces extreme values of social perception across different ages and facial expressions. Third, facial expression impacts social perception more than age and lighting as much as age. The last finding predicts that studies that do not control for unprotected visual attributes may reach the wrong conclusions on bias. Our novel method of investigation, which is founded on the social psychology literature and on the experiments involving the manipulation of individual attributes, yields sharper and more reliable observations than previous observational methods and may be applied to study biases in any vision-language model.
FaceInsight: A Multimodal Large Language Model for Face Perception
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区计算机科学与技术学院）；Key Laboratory of Education Informatization for Nationalities (Yunnan Normal University), Ministry of Education（民族教育信息化重点实验室（云南师范大学））
FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs
Shenzhen University（深圳大学）；Tsinghua University（清华大学）；The Hong Kong Polytechnic University（香港理工大学）；City University of Hong Kong（香港城市大学）；Sun Yat-sen University（中山大学）
Subjective-Graph LLM Agents for Simulating Uncertainty in Classroom Social Perception
Complex Lab, School of Computer Science and Engineering（复杂实验室，计算机科学与工程学院）；University of Electronic Science and Technology of China（电子科学与技术大学）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；School of Health and Medical Technology, Chengdu Neusoft University（成都新软大学健康与医疗技术学院）
An important goal in human-robot-interaction (HRI) is for machines to achieve a close to human level of face perception. One of the important differences between machine learning and human intelligence is the lack of compositionality. This paper introduces a new scheme to enable generative adversarial networks to learn the distribution of face images composed of smaller parts. This results in a more flexible machine face perception and easier generalization to outside training examples. We demonstrate that this model is able to produce realistic high-quality face images by generating and pieci…
The ability to perceive and reason about social interactions in the context of physical environments is core to human social intelligence and human-machine cooperation. However, no prior dataset or benchmark has systematically evaluated physically grounded perception of complex social interactions that go beyond short actions, such as high-fiving, or simple group activities, such as gathering. In this work, we create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions by including social concepts such as helping another ag…
Creating artificial social intelligence - algorithms that can understand the nuances of multi-person interactions - is an exciting and emerging challenge in processing facial expressions and gestures from multimodal videos. Recent multimodal methods have set the state of the art on many tasks, but have difficulty modeling the complex face-to-face conversational dynamics across speaking turns in social interaction, particularly in a self-supervised setup. In this paper, we propose Face-to-Face Contrastive Learning (F2F-CL), a graph neural network designed to model social interactions using fact…
University of Trento（特伦托大学）；University of Innsbruck（因斯布鲁克大学）；Université Catholique de Louvain（鲁汶天主教大学）
Deep fakes became extremely popular in the last years, also thanks to their increasing realism. Therefore, there is the need to measures human's ability to distinguish between real and synthetic face images when confronted with cutting-edge creation technologies. We describe the design and results of a perceptual experiment we have conducted, where a wide and diverse group of volunteers has been exposed to synthetic face images produced by state-of-the-art Generative Adversarial Networks (namely, PG-GAN, StyleGAN, StyleGAN2). The experiment outcomes reveal how strongly we should call into ques…
This work digs into a root question in human perception: can face geometry be gleaned from one's voices? Previous works that study this question only adopt developments in image synthesis and convert voices into face images to show correlations, but working on the image domain unavoidably involves predicting attributes that voices cannot hint, including facial textures, hairstyles, and backgrounds. We instead investigate the ability to reconstruct 3D faces to concentrate on only geometry, which is much more physiologically grounded. We propose our analysis framework, Cross-Modal Perceptionist,…
South China University of Technology（华南理工大学）；Hong Kong Polytechnic University（香港理工大学）；Sun Yat-Sen University（中山大学）
Face sketch generation has attracted much attention in the field of visual computing. However, existing methods either are limited to constrained conditions or heavily rely on various preprocessing steps to deal with in-the-wild cases. In this paper, we argue that accurately perceiving facial region and facial components is crucial for unconstrained sketch synthesis. To this end, we propose a novel Perception-Adaptive Network (PANet), which can generate high-quality face sketches under unconstrained conditions in an end-to-end scheme. Specifically, our PANet is composed of i) a Fully Convoluti…
University of Bamberg（班贝格大学）；University of Ulm（乌尔姆大学）
Warmth and competence represent the fundamental traits in social judgment that determine emotional reactions and behavioral intentions towards social targets. This research investigates whether an algorithm can learn visual representations of social categorization and accurately predict human perceivers' impressions of warmth and competence in face images. In addition, this research unravels which areas of a face are important for the classification of warmth and competence. We use Deep Convolutional Neural Networks to extract features from face images and the Gradient-weighted Class Activatio…
University of Notre Dame（圣母大学）；Kitware, Inc.（Kitware公司）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
Advances in face synthesis have raised alarms about the deceptive use of synthetic faces. Can synthetic identities be effectively used to fool human observers? In this paper, we introduce a study of the human perception of synthetic faces generated using different strategies including a state-of-the-art deep learning-based GAN model. This is the first rigorous study of the effectiveness of synthetic face generation techniques grounded in experimental techniques from psychology. We answer important questions such as how often do GAN-based and more traditional image processing-based techniques c…
The Open University of Israel（以色列开放大学）；USC（南加州大学）；Information Sciences Institute, USC（南加州大学信息科学研究所）
We show that even when face images are unconstrained and arbitrarily paired, face swapping between them is actually quite simple. To this end, we make the following contributions. (a) Instead of tailoring systems for face segmentation, as others previously proposed, we show that a standard fully convolutional network (FCN) can achieve remarkably fast and accurate segmentations, provided that it is trained on a rich enough example set. For this purpose, we describe novel data collection and generation routines which provide challenging segmented face examples. (b) We use our segmentations to en…
Fudan University（复旦大学）；Pennsylvania State University（宾夕法尼亚州立大学）
Recent advancements in computational power and algorithms have enabled unabridged data (e.g., raw images or audio) to be used as input in some models (e.g., deep learning). However, the black box nature of such models reduces their likelihood of adoption by marketing scholars. Our paradigm of analysis, the Transparent Model of Unabridged Data (TMUD), enables researchers to investigate the inner workings of such black box models by incorporating an ex ante filtration module and an ex post experimentation module. We empirically demonstrate the TMUD by investigating the role of facial components …
Social relation defines the association, e.g, warm, friendliness, and dominance, between two or more people. Motivated by psychological studies, we investigate if such fine-grained and high-level relation traits can be characterised and quantified from face images in the wild. To address this challenging problem we propose a deep model that learns a rich face representation to capture gender, expression, head pose, and age-related attributes, and then performs pairwise-face reasoning for relation prediction. To learn from heterogeneous attribute sources, we formulate a new network architecture…
University of Oulu（奥卢大学）；Chinese Academy of Sciences（中国科学院）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Xi’an Jiaotong University（西安交通大学）
Face anti-spoofing (FAS) plays a vital role in securing the face recognition systems from presentation attacks. Most existing FAS methods capture various cues (e.g., texture, depth and reflection) to distinguish the live faces from the spoofing faces. All these cues are based on the discrepancy among physical materials (e.g., skin, glass, paper and silicone). In this paper we rephrase face anti-spoofing as a material recognition problem and combine it with classical human material perception [1], intending to extract discriminative and robust features for FAS. To this end, we propose the Bilat…
It is common practice nowadays to use multiple social networks for different social roles. Although this, these networks assume differences in content type, communications and style of speech. If we intend to understand human behaviour as a key-feature for recommender systems, banking risk assessments or sociological researches, this is better to achieve using a combination of the data from different social media. In this paper, we propose a new approach for user profiles matching across social media based on embeddings of publicly available users' face photos and conduct an experimental study…
Recently, productization of face recognition and identification algorithms have become the most controversial topic about ethical AI. As new policies around digital identities are formed, we introduce three face access models in a hypothetical social network, where the user has the power to only appear in photos they approve. Our approach eclipses current tagging systems and replaces unapproved faces with quantitatively dissimilar deepfakes. In addition, we propose new metrics specific for this task, where the deepfake is generated at random with a guaranteed dissimilarity. We explain access m…
Beauty is in the ELBO of the Beholder: A Variational Account of Processing Fluency in Face Perception
Frankfurt Institute for Advanced Studies（法兰克福高等研究院）；School of Computer Science and Engineering, UNSW Sydney（新南威尔士大学悉尼分校计算机科学与工程学院）；Goethe University Frankfurt（法兰克福大学）
University of British Columbia（英属哥伦比亚大学）；Department of Statistics, University of British Columbia（英属哥伦比亚大学统计系）；Department of Electrical and Computer Engineering, University of British Columbia（英属哥伦比亚大学电气与计算机工程系）；School of Information and Communications Engineering, Xi’an Jiaotong University（西安交通大学信息与通信工程学院）
Recently, generative adversarial networks (GANs) can generate photo-realistic fake facial images which are perceptually indistinguishable from real face photos, promoting research on fake face detection. Though fake face forensics can achieve high detection accuracy, their anti-forensic counterparts are less investigated. Here we explore more \textit{imperceptible} and \textit{transferable} anti-forensics for fake face imagery detection based on adversarial attacks. Since facial and background regions are often smooth, even small perturbation could cause noticeable perceptual impairment in fak…
National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；University of Chinese Academy of Sciences（中国科学院大学）
Photorealistic frontal view synthesis from a single face image has a wide range of applications in the field of face recognition. Although data-driven deep learning methods have been proposed to address this problem by seeking solutions from ample face data, this problem is still challenging because it is intrinsically ill-posed. This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details. Four landmark located patch networks are proposed to attend to local textures in addit…
This article is a sequel to our earlier work [25]. The main objective of our research is to explore the potential of supervised machine learning in face-induced social computing and cognition, riding on the momentum of much heralded successes of face processing, analysis and recognition on the tasks of biometric-based identification. We present a case study of automated statistical inference on sociopsychological perceptions of female faces controlled for race, attractiveness, age and nationality. Our empirical evidences point to the possibility of training machine learning algorithms, using e…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Istanbul Technical University（伊斯坦布尔技术大学）
Health organizations advise social distancing, wearing face mask, and avoiding touching face to prevent the spread of coronavirus. Based on these protective measures, we developed a computer vision system to help prevent the transmission of COVID-19. Specifically, the developed system performs face mask detection, face-hand interaction detection, and measures social distance. To train and evaluate the developed system, we collected and annotated images that represent face mask usage and face-hand interaction in the real world. Besides assessing the performance of the developed system on our ow…
The current COVID-19 pandemic has shown us that we are still facing unpredictable challenges in our society. The necessary constrain on social interactions affected heavily how we envision and prepare the future of social robots and artificial agents in general. Adapting current affective perception models towards constrained perception based on the hard separation between facial perception and affective understanding would help us to provide robust systems. In this paper, we perform an in-depth analysis of how recognizing affect from persons with masks differs from general facial expression p…
