FG26
* *FG
* 3D Temporal Analysis for Autism Spectrum Disorder Screening During Attention Tasks
* 3DRealHead: Few-Shot Detailed Head Avatar
* Adversarial-Robust Child Face Verification Using Spiking Neural Networks
* AGCM: Attention-Guided Concept-based Model for Interpretable Affective Computing Applications
* Algorithm for On-Sensor Agnostic Detection of Changes in Human Activity for Ultra-Low-Power Applications, An
* AmbiGest: A Dataset of Social Gestures with Inter-Class Similarity and Intra-Class Variability
* Anthropometrically Accurate Human Mesh Reconstruction via Body-Structured NeRF for Vision-Based Analysis
* Arc2Morph: Identity-Preserving Facial Morphing with Arc2Face
* ARiSE: Efficient Mesh-Based Action Recognition from Wi-Fi Sensing on Edge Devices
* ATFFormer: Asymmetric Temporal Fusion for Identity-Consistent Blind Video Face Restoration
* ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers
* Automated detection of positive and non-positive shyness in infants from videos
* Bayesian Contrastive Augmented Open-set Action Recognition
* Beyond the Surface: Incorporating 3D Facial Information into Action Unit Detection
* Bi-Level Keypoint Relation Helps Versatile and Occluded Human Pose Estimation
* BlendEmo: Structured Set Prediction and Pair-Conditioned Ratio Modeling for Blended Emotion Recognition
* C2F-OR: Coarse-to-Fine Occlusion Removal for Facial Age Estimation on Partially Occluded Faces
* CAKE: Context-Aware Kid Emotion In-the-Wild Dataset
* CANDOR: Centroid-Adjusted Normalized Decision-Level Optimization and Recognition for Blended Emotions
* CAPE: A Hierarchical Global-to-Local Framework for Crowd-Aware Pose Estimation
* CapStARE-LM: Capsule-based Spatiotemporal Architecture for Calibration-Free Gaze Estimation Using Facial Landmarks
* Capturing Individual Differences of Facial Expression for Authentic Expression Generation
* Controlled Face Manipulation and Synthesis for Data Augmentation
* CP-VLM: Causal Prompting for Human Intention Inference with Vision-Language Models
* Database-Agnostic Gait Enrollment using SetTransformers
* Depth-Copy-Paste: Multimodal and Depth-Aware Compositing for Robust Face Detection
* DF-OOD: Real-Only Deepfake Detection via Confidence Dynamics under Perturbations
* DGCMam: Fusing Distance Graph Convolution and Mamba for Skeleton-based Action Recognition
* DiffEyeSyn: User-specific Subtle Eye Movement Synthesis Using Diffusion Models
* Dyna-Westdrive - VR-Based Multimodal Dataset for Emotion Recognition
* Dynamic-Static Dataset of Facial Feature Variations Induced by Six Basic Tastes, A
* EA-VTON: Equivariance and AttentionFlow for Pose-Adaptive Virtual Try-On in Latent Diffusion Models
* Efficient Human Pose Estimation with Cross-Stage Fusion and Self-Distillation
* Efficient Isolated Sign Language Recognition via MediaPipe Landmarks and Affinity Mixed Attention: A Case Study On American Sign Language
* Egocentric Gesture Dataset for Robust Human-Robot Communication via Head Mounted Devices in Industrial and Military Settings
* EgoSSA: Egocentric Stereo Structure-Aware 3D Hand Reconstruction for American Sign Language Gesture Modeling
* Elastic Spiking Transformers for Efficient Gesture Understanding
* EMA: Effort Metric Attention for Anatomical Effort-Guided Human Motion Diffusion
* Employing Vision-Language Models for Face Image Quality Assessment
* EPAT: Enhanced Parameter-Efficient Transfer Learning with Adaptive Strategy Fusion for Text-to-Image Person Re-identification
* Event-based Liveness Detection using Temporal Ocular Dynamics: An Exploratory Approach
* EX-FIQA: Leveraging Intermediate Early eXit Representations from Vision Transformers for Face Image Quality Assessment
* Exploring Bayesian Prior-Driven Pseudo-Profile Reasoning for MLLM-based Micro-Expression Analysis
* Exploring PPG-Guided Knowledge Distillation for Contactless Respiration Estimation
* Exploring User Identification During Radar-Based Gesture Interaction
* FaceLayer: Multimodal 3D Face Asset Synthesis and Editing via Topology-Aware Disentangled Layer Composition
* Facial Expression Features of Deception in Dynamic Naturalistic Social Interactions
* FD-MAD: Frequency-Domain Residual Analysis for Face Morphing Attack Detection
* Few-Reference Identity-Aware Face Completion via Edge-Guided Structure and Self-Supervised Semantic Priors
* FILD: Flash Interaction Latent Diffusion for Real-Time Text-Conditioned Human-Human Interaction Generation
* Flow Augmentation and Knowledge Distillation for Lightweight Face Presentation Attack Detection
* Friend or Foe? Benchmarking Human Perception and ST-GCN Decoding of Embodied Social Intention
* FRLD-DF: Frequency Ring-Guided LoRA Adaptation of DINOv2 Vision Transformer for Generalizable Deepfake Detection
* From Real Faces to XR Avatars: Evaluating Face Recognition Vulnerability Through Avatar-Based Presentation Attacks
* Functional Differentiation of Postural Cues across Body Regions in Deception Detection: Implications for Human-Machine Trust and Interaction Systems
* FunFace: Feature Utility and Norm Estimation for Face Recognition
* GaitProtector: Impersonation-Driven Gait De-Identification via Training-Free Diffusion Latent Optimization
* Gaze4HRI: Zero-shot Benchmarking Gaze Estimation Neural-Networks for Human-Robot Interaction
* Generative Data Augmentation for Skeleton Action Recognition
* Generic Deepfake Feature Space Discovery via Coarse-to-Fine Disentanglement Learning
* Geometry-Conditioned Diffusion for Occlusion-Robust In-Bed Pose Estimation
* Global Attention-Based CNN for Interpretable Gender Classification in Palm Vein Biometrics
* GlossRefine: Gloss-Conditioned Transformer for Low-Resource Sign Language Motion Generation
* Hierarchical Cross-Attention Transformer for Non-contact Multimodal Pain Classification using Remote Physiological Signals and Visual Features
* High Fidelity and Real-time Video Face Swapping
* HUI360: A 360° Egocentric Dataset and Baselines for Human-Robot Interaction Anticipation
* IDSync: Improving diffusion models through identity classification
* Inclusive AI for Group Interactions: Predicting Gaze-Direction Behaviors in People with Intellectual and Developmental Disabilities
* InstaFace: Identity-Preserving Facial Editing with Single Image Inference
* Inter-Stance: A Dyadic Multimodal Corpus for Conversational Stance Analysis
* Interactive Visual Exploration of Cross-Cultural Embodied Affect and Social Intent
* Investigating Bias and Fairness in Appearance-based Gaze Estimation
* Investigating the Relationship Between Micro-Expressions and Cognitive Load via a Novel Maze Paradigm
* Large-Scale 3D Representation Dataset and Benchmark for Continuous Sign Language Understanding, A
* LBOR: Laplace-Beltrami Operator Regularization for Robust Skeleton-based Isolated Sign Language Recognition
* Learning When to Adapt: Forecast-Driven Meta Learning for Few-Shot Professional Action Recognition under Data Scarcity
* LibreFace 2.0: A Generalizable Facial Expression Analysis Toolkit Leveraging Synthetic Data
* MEGC2026: Micro-Expression Grand Challenge on Visual Question Answering
* Mesh-Gait: A Unified Framework for Gait Recognition Through Multi-Modal Representation Learning from 2D Silhouettes
* MiAFormer: Micro Analysis Transformer for Fine-Grained Micro-Expression Understanding via Scene Flow
* Micro-DualNet: Dual-Path Spatio-Temporal Network for Micro-Action Recognition
* Micro-Expression-Aware Avatar Fingerprinting via Inter-Frame Feature Differencing
* Modality-decoupled Transformer with Memory Learning for Video-based Visible-infrared Person Re-identification
* MoME: Estimating Psychological Traits from Gait with Multi-Stage Mixture of Movement Experts
* Multi-Camera Self-Calibration in Sports Motion Capture: Leveraging Human and Stick Poses
* Multimodal Voice Activity Projection for Multi-Party Conversations
* Non-Invasive 3D Gait Analysis Framework for Quantifying Psychomotor Retardation in Major Depressive Disorder, A
* Not all Blends are Equal: The BlEmoRe Dataset of Blended Emotion Expressions with Relative Salience Annotations
* NullFace: Training-Free Localized Face Anonymization
* On Applicability of Synthetic Datasets for Facial Expression Recognition
* On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detection
* Open Set Face Forgery Detection via Dual-Level Evidence Collection
* Open Your Eyes to See More: Dual Perspective Contrastive Learning for Skeleton-Based Action Understanding
* Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition
* PaW-ViT: A Patch-based Warping Vision Transformer for Robust Ear Verification
* Physics-informed Dynamic 3D Face Reconstruction from Videos
* PKTA: Part-oriented Knowledge Transfer and Acquisition for Non-Exemplar Lifelong Person Re-Identification
* PMP: Plug-and-Play Physics Momentum Prior for Contact-Stable 3D Human Pose Estimation
* Polyglot: Multilingual Style Preserving Speech-Driven Facial Animation
* PopSign v2.0: Extending an Isolated American Sign Language Dataset to Over 360,000 Examples of 562 Concepts
* PosePilot-V3D: A Web-Based Framework for 3D Hierarchical Skeleton Reconstruction from Monocular Video
* PosePilot-V3D: Interactive Exploration and Analysis of 3D Human Motion from Monocular Video
* Privacy-Compliant Human Data Synthesis in Images for GDPR
* Progressive Curriculum Learning and Ghost-Aware Supervision for Real-World Face Detection
* Prompt-to-Gesture: Measuring the Capabilities of Image-to-Video Deictic Gesture Generation
* Quality-driven Adaptive Morphing Attack Detection in Operational Scenarios via Online Learning
* REACH: Hand Pose Estimation from Room Corners
* ReactionMamba: Generating Short & Long Human Reaction Sequences
* Region-Aware Latent Axis Discovery for Predictive Botulinum Toxin Facial Simulation
* ReMiX-MAE: Learning Missing-Channel Cross-Modal Representations from RGB-Only Clinical Facial Videos for Sympathetic-Mediated Pain Assessment
* Repurposing Gait Recognition Priors for Generalizable Fine-Grained Parkinson's Disease Assessment
* RGB-TViT: Multimodal RGB-Thermal Transformers for Early Prediction of Vasovagal Reactions in Blood Donation
* RIFD-DETR: Rotation-Invariant Face Detection with DETR and Polar-Aware Landmarks
* Role of Context in Prosocial Affect Recognition, The
* SEEKr: Efficient Knowledge Distillation for Face Recognition
* Semi Synthetic Iris Image Generation with Identity Preservation Using Latent Diffusion Models
* Shades of Generalization: Diversity Aware Open Set Deepfake Detection
* Shape vs. Texture: Influence of Geometric Structure and Surface Patterns on Face Recognition
* Shape-Based Object Detection via Gesture Prompts: Leveraging Pre-trained Open-Vocabulary Models
* Simplifying Spatio-Temporal Graphs in Skeleton-Based Gait Analysis
* Skarimva: Skeleton-based Action Recognition is a Multi-view Application
* SODA: Semantic-Cohesive Knowledge Distillation for Deep Cross-modal Hashing
* Standardized Benchmark for Skeleton-Based Rehabilitation Assessment Using Deep Learning, A
* STEN-FAWA: Spatial-Temporal Expert Network with Forgery-Aware Weighted-Adaptive Aggregator for Deepfake Detection
* StyleDiT: A Unified Framework for Diverse Child and Partner Faces Synthesis with Style Latent Diffusion Transformer
* Test-time Adaptation for 3D Human Pose and Shape Estimation
* Toward a Cross-Domain Taxonomy of Motion Quality Metrics
* Towards Pareto Efficiency in Fair Facial Expression and Action Unit Recognition
* Towards Trustworthy Face Avatars: Dynamic 3D Reconstruction with Faithful Eye Motion Modeling
* Towards Unconstrained Human-Object Interaction
* Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting
* Training-Free Semantic Multi-Object Tracking with Vision-Language Models
* TransFIRA: Transfer Learning for Face Image Recognizability Assessment
* Two-Stage MAE with Dual-Asymmetry Learning for 3D Facial Paralysis Grading
* Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral Sampling
* Uplifting 2D to 3D Human Poses with Joint Rotations and Bone Constraints: A Strong Baseline for Sports and Fitness Applications
* Vision Transformers for Face Recognition Need More Registers
* ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation
* Zero-Shot Temporal Action Localization Through Textual Guidance
140 for FG26