FG21
* *FG
* 5th Recognizing Families in the Wild Data Challenge: Predicting Kinship from Faces, The
* Adversarial Attacks on Kinship Verification using Transformer
* Adversarial Mask Generation for Preserving Visual Privacy
* Adversarially Perturbed Wavelet-based Morphed Face Generation
* Affect-Aware Deep Belief Network Representations for Multimodal Unsupervised Deception Detection
* Affect-DML: Context-Aware One-Shot Recognition of Human Affect using Deep Metric Learning
* Anonysign: Novel Human Appearance Synthesis for Sign Language Video Anonymisation
* Apparent Personality Recognition from Uncertainty-Aware Facial Emotion Predictions using Conditional Latent Variable Models
* Asymmetric 3D face model for Speech Language Pathologist applications
* Augmented Face Representation Learning via Transitive Distillation
* AULA-Caps: Lifecycle-Aware Capsule Networks for Spatio-Temporal Analysis of Facial Actions
* Beyond the Words: Analysis and Detection of Self-Disclosure Behavior during Robot Positive Psychology Interaction
* Body Gesture and Head Movement Analyses in Dyadic Parent-Child Interaction as Indicators of Relationship
* BVPNet: Video-to-BVP Signal Prediction for Remote Heart Rate Estimation
* Channel Split Convolutional Neural Network for Single Image Super-Resolution (CSISR)
* Coarse-to-Fine Dual Attention Network for Blind Face Completion, A
* Comparing Facial Expressions for Face Swapping Evaluation with Supervised Contrastive Representation Learning
* Compositional Graph Convolutional Networks for 3D Human Pose Estimation
* Content4All Open Research Sign Language Translation Datasets
* Contextual Emotion Learning Challenge
* Coupled Systems for Modeling Rapport Between Interlocutors
* Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition
* Cross-Quality LFW: A Database for Analyzing Cross- Resolution Image Face Recognition in Unconstrained Environments
* Deep Kinship Verification and Retrieval Based on Fusion Siamese Neural Network
* Deep Parametric Surfaces for 3D Outfit Reconstruction from Single View Image
* Demystifying Attention Mechanisms for Deepfake Detection
* Dense 3D Coordinate Code Prior Guidance for High-Fidelity Face Swapping and Face Reenactment
* Dense Face Detection via High-level Context Mining
* Detecting Human-to-Human-or-Object (H2O) Interactions with DIABOLO
* Does Keypoint Estimation Benefit Object Detection? An Empirical Study of One-stage and Two-stage Detectors
* Dominant subject recognition by Bayesian learning
* Driver Glance Classification In-the-wild: Towards Generalization Across Domains and Subjects
* Dynamic Cross-Feature Fusion for American Sign Language Translation
* Efficient Facial Landmark Detector by Knowledge Distillation
* Efficient Human Pose Estimation by Maximizing Fusion and High-Level Spatial Attention
* Emotion Editing in Head Reenactment Videos using Latent Space Manipulation
* Emotion-aware Contrastive Learning for Facial Action Unit Detection
* Explainable Thermal to Visible Face Recognition Using Latent-Guided Generative Adversarial Network
* Explaining Face Presentation Attack Detection Using Natural Language
* Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition
* Expression Recognition Across Age
* Expression-Latent-Space-guided GAN for Facial Expression Animation based on Discrete Labels
* Face Recognition Based on Panoramic Video
* Face Trees for Expression Recognition
* FaceQgen: Semi-Supervised Deep Learning for Face Image Quality Assessment
* Facial Action Unit Detection Based on Teacher-Student Learning Framework for Partially Occluded Facial Images
* Facial Action Unit Recognition Using Pseudo-Intensities and their Transformation
* Facial Action Units and Head Dynamics in Longitudinal Interviews Reveal OCD and Depression severity and DBS Energy
* Federated Test-Time Adaptive Face Presentation Attack Detection with Dual-Phase Privacy Preservation
* Foreign Shadow Robust Makeup Transfer via Hierarchical Deep Aggregation and Disentangled Representation
* Frame-level Feature Tokenization Learning for Human Body Pose and Shape Estimation
* From Face to Gait: Weakly-Supervised Learning of Gender Information from Walking Patterns
* Fusion-based Spatiotemporal Convolutions with Constant Temporal Snapshots for Sign Language Recognition
* Gaussian Mixture Distribution Makes Data Uncertainty Learning Better
* GazeGrid: A Novel Interaction Method Based on Gaze Estimation
* Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution
* Generative Adversarial Network for Text-to-Face Synthesis and Manipulation with Pretrained BERT Model
* Geodesic squared exponential kernel for non-rigid shape registration
* Goals, Tasks, and Bonds: Toward the Computational Assessment of Therapist Versus Client Perception of Working Alliance
* GROWL: Group Detection With Link Prediction
* Hairstyle Transfer between Face Images
* Hand Gesture Recognition in Range-Doppler Images Using Binary Activated Spiking Neural Networks
* harAGE: A Novel Multimodal Smartwatch-based Dataset for Human Activity Recognition
* HeadPosr: End-to-end Trainable Head Pose Estimation using Transformer Encoders
* Heterogeneous Face Frontalization via Domain Agnostic Learning
* High-Accuracy RGB-D Face Recognition via Segmentation-Aware Face Depth Estimation and Mask-Guided Attention Network
* Human Motion Prediction Using Manifold-Aware Wasserstein GAN
* Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering
* Identity-Expression Ambiguity in 3D Morphable Face Models
* Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition, The
* Importance of Qualitative Elements in Subjective Evaluation of Semantic Gestures, The
* Improving Evaluation of Facial Attribute Prediction Models
* Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition
* Invariant Representation Learning for Infant Pose Estimation with Small Data
* KSL-Guide: A Large-scale Korean Sign Language Dataset Including Interrogative Sentences for Guiding the Deaf and Hard-of-Hearing
* Landmark-aware Self-supervised Eye Semantic Segmentation
* Learning Shape-Appearance Based Attributes Representation for Facial Attribute Recognition with Limited Labeled Data
* Leveraging Affect Transfer Learning for Behavior Prediction in an Intelligent Tutoring System
* Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild
* Lightweight Deep Symmetric Positive Definite Manifold Network for Real-Time 3D Hand Gesture Recognition
* Local Feature Enhancement Network for Set-based Face Recognition
* Local Global Relational Network for Facial Action Units Recognition
* Looking for the Signs: Identifying Isolated Sign Instances in Continuous Video Footage
* Many Faces of Anger: A Multicultural Video Dataset of Negative Emotions in the Wild (MFA-Wild), The
* Masked Batch Normalization to Improve Tracking-Based Sign Language Recognition Using Graph Convolutional Networks
* MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detection
* Micro-expression Action Unit Detection with Dual-view Attentive Similarity-Preserving Knowledge Distillation
* Modeling Dynamics of Facial Behavior for Mental Health Assessment
* Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features
* Multi-Modal Learning for AU Detection Based on Multi-Head Fused Transformers
* Multi-Person Gaze-Following with Numerical Coordinate Regression
* New RGB-D Gesture Video Dataset for Real-life Scenarios, A
* NoPeek-Infer: Preventing face reconstruction attacks in distributed inference after on-premise training
* Pose-Invariant Facial Expression Recognition
* PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding
* Predicting Trust Using Automated Assessment of Multivariate Interactional Synchrony
* Progressive Text-to-Face Synthesis with Generative Adversarial Network
* Relative Pose Consistency for Semi-Supervised Head Pose Estimation
* Replay Attention and Data Augmentation Network for 3D Dense Alignment and Face Reconstruction
* ReSORT: an ID-recovery multi-face tracking method for surveillance cameras
* Rethinking Deconvolution for 2D Human Pose Estimation Light yet Accurate Model for Real-time Edge Computing
* RGB-D Face Recognition using Reconstruction based Shared Representation
* Robust LWIR-based Eye Center Detection through Thermal to Visible Image Synthesis
* RSFAD: A Large-Scale Real Scenario Face Age Dataset in the wild
* Safe Fakes: Evaluating Face Anonymizers for Face Detectors
* Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry
* Self-Supervised Learning via Multi-view Facial Rendezvous for 3D/4D Affect Recognition
* Self-Supervised Patch Localization for Cross-Domain Facial Action Unit Detection
* Self-Supervised Video Pose Representation Learning for Occlusion- Robust Action Recognition
* Sign, Attend and Tell: Spatial Attention for Sign Language Recognition
* Similarity-based Gray-box Adversarial Attack Against Deep Face Recognition
* Skeleton-based Action Recognition for Human-Robot Interaction using Self-Attention Mechanism
* Skeleton-Based Explainable Bodily Expressed Emotion Recognition Through Graph Convolutional Networks
* Smile Action Unit detection from distal wearable Electromyography and Computer Vision
* SMPL-Based 3D Pedestrian Pose Prediction
* Solving the Families In the Wild Kinship Verification Challenge by Program Synthesis
* Spatially Constrained GAN for Face and Fashion Synthesis
* SRL: Separation-and-Recombination Learning for Video Facial Landmark Detection with Limited Data
* Study of the Human Perception of Synthetic Faces, A
* StyleDNA: A High-Fidelity Age and Gender Aware Kinship Face Synthesizer
* Stylized Text-to-Fashion Image Generation
* Supervised Contrastive Learning for Facial Kinship Recognition
* Synthesis-Based Approach for Thermal-to-Visible Face Verification, A
* Synthesis-Guided Feature Learning for Cross-Spectral Periocular Recognition
* TADPool: Target Adaptive Pooling for Set Based Face Recognition
* Tensor-based Subspace Factorization for StyleGAN
* Toward Personalized Emotion Recognition: A Face Recognition Based Attention Method for Facial Emotion Recognition
* Towards Occlusion Robust Facial Landmark Detector
* Towards the Synthesis of Parent-Infant Facial Interactions
* TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction
* Two-Stream Gabor-AGraph Convolutional Networks for Facial Expression Recognition
* Two-Stream Global-Guided Attention Network for Facial Expression Recognition
* Understanding Cross Domain Presentation Attack Detection for Visible Face Recognition
* Unimodal Face Classification with Multimodal Training
* Unknown Aware Feature Learning for Face Forgery Detection
* Unsupervised Compound Domain Adaptation for Face Anti-Spoofing
* UV-based reconstruction of 3D garments from a single RGB image
* Weakly-supervised Joint Anomaly Detection and Classification
* When Sketch Face Recognition Meets Mask Obfuscation: Database and Benchmark
* Which CNNs and Training Settings to Choose for Action Unit Detection? A Study Based on a Large-Scale Dataset
* Your Attention Deserves Attention: A Self-Diversified Multi-Channel Attention for Facial Action Analysis
* ZF-SSE: A Unified Sequential Semantic Encoder for Zero-Few-Shot Learning
143 for FG21