Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data
School of Computer Science and Information Engineering, Hefei University of Technology（计算机科学与信息工程学院，合肥工业大学）；Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences（智能信息处理重点实验室，计算技术研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）
动态面部表情识别（DFER）从表情的时间演化过程推断情绪，这与仅依赖单张快照的静态面部表情识别（SFER）不同。这种时间分析能提供更丰富的信息，有望实现更强的识别能力。但当前DFER方法性能往往不尽人意，主要原因是其训练样本远少于SFER。鉴于静态与动态表情之间存在内在关联，我们假设利用海量SFER数据可以提升DFER效果。为此，我们提出Static-for-Dynamic（S4D），这是一个统一的双模态学习框架，将SFER数据作为DFER的补充资源加以整合。具体而言，S4D采用共享的Vision Transformer（ViT）编解码架构，在面部图像和视频上开展双模态自监督预训练，从而得到更优的时空表征。随后，预训练后的编码器在静态和动态表情数据集上以多任务学习方式进行微调，以促进情绪信息的交互。但研究发现，普通的多任务学习会导致负迁移问题。为解决该问题，我们提出了创新的混合适配器专家（Mixture of Adapter Experts, MoAE）模块，既能促进任务专属知识的获取，又能有效提取静态与动态表情数据中的共享知识。大量实验表明，S4D实现了对DFER的更深层理解，在FERV39K、MAFW和DFEW基准上均刷新了当前最优性能，加权平均召回率（WAR）分别达到53.65%、58.44%和76.68%。此外，本文还对SFER与DFER任务进行了系统性的相关性分析，进一步阐明了利用SFER数据的潜在价值。
英文摘要：
Dynamic facial expression recognition (DFER) infers emotions from the temporal evolution of expressions, unlike static facial expression recognition (SFER), which relies solely on a single snapshot. This temporal analysis provides richer information and promises greater recognition capability. However, current DFER methods often exhibit unsatisfied performance largely due to fewer training samples compared to SFER. Given the inherent correlation between static and dynamic expressions, we hypothesize that leveraging the abundant SFER data can enhance DFER. To this end, we propose Static-for-Dynamic (S4D), a unified dual-modal learning framework that integrates SFER data as a complementary resource for DFER. Specifically, S4D employs dual-modal self-supervised pre-training on facial images and videos using a shared Vision Transformer (ViT) encoder-decoder architecture, yielding improved spatiotemporal representations. The pre-trained encoder is then fine-tuned on static and dynamic expression datasets in a multi-task learning setup to facilitate emotional information interaction. Unfortunately, vanilla multi-task learning in our study results in negative transfer. To address this, we propose an innovative Mixture of Adapter Experts (MoAE) module that facilitates task-specific knowledge acquisition while effectively extracting shared knowledge from both static and dynamic expression data. Extensive experiments demonstrate that S4D achieves a deeper understanding of DFER, setting new state-of-the-art performance on FERV39K, MAFW, and DFEW benchmarks, with weighted average recall (WAR) of 53.65\%, 58.44\%, and 76.68\%, respectively. Additionally, a systematic correlation analysis between SFER and DFER tasks is presented, which further elucidates the potential benefits of leveraging SFER.
From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos
School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）；Institute of Computing Technology, Chinese Academy of Sciences（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）
A Survey on Facial Expression Recognition of Static and Dynamic Emotions
Academy for Engineering & Technology, Fudan University（复旦大学工程与技术学院）；College of Information Technology, Shanghai Ocean University（上海海洋大学信息技术学院）；School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）；School of Computer Science, Fudan University（复旦大学计算机科学学院）
Automatic Analysis of Facial Expressions Based on Deep Covariance Trajectories
Mohammed V University in Rabat（拉巴特穆罕默德五世大学）；University of Luxembourg（卢森堡大学）；IMT Lille-Douai（法国里尔-杜埃国立高等矿业电信学校）；University of Lille（里尔大学）；CNRS（法国国家科学研究中心）；University of Florence（佛罗伦萨大学）
LaCoVL-FER: Landmark-Guided Contrastive Learning Network with Vision-Language Enhancement for Facial Expression Recognition
School of Airspace and Engineering, Shandong University（山东大学航空航天与工程学院）；School of Computer Science and Technology, Shandong University of Finance and Economics（山东财经大学计算机科学与技术学院）；School of Psychology and Neuroscience, University of Glasgow（格拉斯哥大学心理学与神经科学学院）；Faculty of Information Science and Engineering, Ocean University of China（中国海洋大学信息科学与工程学院）
Snap Inc.（Snap 公司）；University of Hong Kong（香港大学）；Adobe Research（Adobe 研究院）；University of Notre Dame（圣母大学）
人脸检测是许多人脸识别和人脸分析系统中至关重要的第一步。早期的人脸检测方法主要基于从局部图像区域提取的手工特征，如Haar Cascades和Histogram of Oriented Concentrants。然而，这些方法不够强大，无法在不受控制的环境中实现高精度的图像。随着2012年在使用深度神经网络进行图像分类方面的突破性工作，人脸检测出现了巨大的范式转变。受深度学习在计算机视觉中的快速发展的启发，在过去的几年中，已经提出了许多基于深度学习的框架用于人脸检测，在准确性方面取得了显著的提高。在这项工作中，我们提供了一些最具代表性的基于深度学习的人脸检测方法的详细概述，将它们分为几个主要类别，并在流行的基准测试中展示其核心架构设计和准确性。我们还描述了一些最流行的人脸检测数据集。最后，我们讨论了该领域目前面临的一些挑战，并提出了潜在的未来研究方向。
Test-Time Adaptation via Cache Personalization for Facial Expression Recognition in Videos
LIVIA, Dept. of Systems Engineering, ETS Montreal, Canada（LIVIA系统工程系，蒙特利尔工程学院，加拿大）；LIVIA, Dept. of Software and IT Engineering, ETS Montreal, Canada（LIVIA软件与信息工程系，蒙特利尔工程学院，加拿大）
DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy
University of Electronic Science and Technology of China（电子科技大学）；CISPA Helmholtz Center for Information Security（信息安全赫尔姆霍茨中心）；The Chinese University of Hong Kong（香港中文大学）
Attributes Shape the Embedding Space of Face Recognition Models
Department of Mathematical Sciences, Politecnico di Torino, Turin, Italy（波兰理工学院数学科学系）；Department of Computer Science, University of Pisa, Pisa, Italy（比萨大学计算机科学系）；CENTAI Institute, Turin, Italy（CENTAI研究院）
Going Deeper than Tracking: a Survey of Computer-Vision Based Recognition of Animal Pain and Affective States
KTH Royal Institute of Technology（瑞典皇家理工学院）；University of Haifa（海法大学）；University of São Paulo（圣保罗大学）；Swedish University of Agricultural Sciences（瑞典农业科学大学）；Universiteit Utrecht（乌得勒支大学）；University of Glasgow（格拉斯哥大学）；Silo AI；Boğaziçi University（博阿齐奇大学）
Investigating Identity Signals in Conversational Facial Dynamics via Disentangled Expression Features
1 Department of Computational Linguistics, University of Zurich , Zurich, Switzerland 2 UZH Digital Society Initiative 3 Idiap Research Institute, Martigny, Switzerland 4 \'E cole Polytechnique F \'e d \'e rale de Lausanne (EPFL), Lausanne, Switzerland
Hierarchical Space-Time Attention for Micro-Expression Recognition
University of Science and Technology of China（中国科学技术大学）；Hefei University of Technology（合肥工业大学）；Chery HuiYin Motor Finance Service Co.,Ltd（奇瑞徽银汽车金融股份有限公司）
Capturing Dynamics: The 4D Facial Expression Intensity Dataset
École Centrale Nantes（南特中央理工学院）；CNRS（法国国家科学研究中心）；LS2N（LS2N实验室）；Nantes Université（南特大学）；CAPACITÉS SAS（CAPACITÉS公司）；Institut universitaire de France (IUF)（法国大学研究院）；University of Oulu（奥卢大学）
Hugging Rain Man: A Novel Facial Action Units Dataset for Analyzing Atypical Facial Expressions in Children with Autism Spectrum Disorder
Faculty of Artificial Intelligence in Education, Central China Normal University（华中师范大学教育人工智能学院）；Computer Science and Artificial Intelligence School, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院）
ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition
Sikkim Manipal Institute of Technology (SMIT)（锡金曼尼普尔理工学院（SMIT））；National Institute of Technology Sikkim（锡金国家理工学院）；Bay Area Advanced Analytics India (P) Ltd（湾区高级分析印度私人有限公司）
Facial Affect Analysis for Service-Oriented Systems: Advances, Challenges, and Future Visions
International Hellenic University（国际希腊大学）；Democritus University of Thrace（德谟克利特大学）；Kingston University London（伦敦金斯顿大学）；University of Western Macedonia（西马其顿大学）
MVRD-Bench: Multi-View Learning and Benchmarking for Dynamic Remote Photoplethysmography under Occlusion
Nanjing University of Information Science and Technology（南京信息工程大学）；University of Oulu（奥卢大学）；Xi’an Jiaotong University（西安交通大学）；Zhejiang University（浙江大学）
