The 13th IEEE Conference on Automatic Face and Gesture Recognition (FG 2019) will take place during the week of May 14-18, 2019. Workshops and tutorials will be held on Tuesday (May 14) and Saturday (May 18), while the main conference will take place on Wednesday through Friday (May 15-17). Please see the Registration page to register for the full conference (including workshops and tutorials) or for individual days.
FG Booklet available for download here
The papers selected for oral presentation will have the following format:
- 12 minutes oral presentation and 3 minutes question/answer.
- Authors are also required to present their paper in a designated poster session. The poster presentation is scheduled on the same day as the oral presentation.
The papers selected for poster presentation will have the following format:
- Spotlight presentation, 2 minutes oral. The pptx template for spotlight presentations is available for download here.
Please do not change the format and timers of the spotlight template.
The spotlights should be uploaded on CMT by May 10th, 2019. - Poster format: Display board size is 2.5m (8.20′) x 1.0m (3.28′) – portrait orientation. Suggested poster size in portrait orientation is 1.5m ~ 1.8m (in height) x 0.9m (in width). We will provide clear adhesive tape for poster mounting.
May 14th | May 15th | May 16th * | May 17th | May 18th |
---|---|---|---|---|
Workshops, Tutorials and Challenges | Main Conference | Main Conference | Main Conference | Workshops, Tutorials and Challenges |
Lunch Break *on May 16th the Lunch Break starts at 12h45 |
||||
Workshops, Tutorials and Challenges, Doctoral Consortium | Main Conference | Main Conference | Main Conference | Workshops, Tutorials and Challenges |
Reception | Banquet |
Time | May 14th | May 15th | May 16th * | May 17th | May 18th |
---|---|---|---|---|---|
8:00 | Registration | Registration | |||
8:45 | Welcome address | ||||
9:00 | Workshops, Tutorials and Challenges | Keynote 1 | Keynote 2 | Keynote 3 | Workshops, Tutorials and Challenges |
9:30 | |||||
10:00 | Coffee | Coffee | Coffee | ||
10:30 | Oral 1 – Face Analysis and Synthesis | Oral 3 – Face Analysis and Synthesis | Oral 5 – Face Recognition | ||
11:00 | |||||
11:30 | |||||
12:00 | Poster Spotlights | Poster Spotlights | Poster Spotlights | ||
12:30 | *on May 16th the Lunch Break starts at 12h45 |
||||
14:00 | Workshops, Tutorials and Challenges, Doctoral Consortium | Special Session 1 – Fundamental Challenges in Modeling, Representation and Synthesis of Gestures | Special Session 2 – Human Health Monitoring Based on Computer Vision | Special Session 3 – Efficient and Reliable 3D Face Analysis | Workshops, Tutorials and Challenges |
14:30 | |||||
15:00 | Oral 2 – Emotion | Oral 4 – Action Units | Oral 6 – Gaze, Pose and Gestures starts at 14:45 |
||
15:30 | |||||
16:00 | Poster+Demo with Coffee | Poster+Demo with Coffee | Poster+Demo with Coffee | ||
16:30 | |||||
17:00 | |||||
17:30 | |||||
18:00 | |||||
19:00 | Reception | Banquet |
May 14th | ||||
---|---|---|---|---|
9:00-12:30 | Workshop 2 – LERA | Workshop 4 – FA4ADAS | Tutorial 1 – Face Recognition From Acamedia to Industry: Past, Present and Future | Challenge – Recognizing Families in the Wild (RFIW – 3rd edition) |
14:00-18:00 | Workshop 1 – MEGC | Workshop 3 – CBAR | Tutorial 2 – Introduction to Deep Learning for Facial and Gesture Understanding | Tutorial 3 – Adversial Learning in Face Recognition – Two sides of the Security Coin |
May 18th | ||||
9:00-12:30 | Workhop 5 and Challenge – OMG | Tutorial 4 – Visual Recognition of Families in the Wild | Tutorial 5 – 3D Human Pose Understanding |
Day 1 10:30-12:00 |
Oral 1: Face Analysis and Synthesis |
12 | Facial Expression Analysis through Point Cloud Neural Networks |
81 | Tree-gated Deep Regressor Ensemble For Face Alignment In The Wild |
36 | FCSR-GAN: End-to-end Learning for Joint Face Completion and Super-resolution |
86 | Boundary-sensitive Network for Portrait Segmentation |
80 | Improving Face Sketch Recognition via Adversarial Sketch-Photo Transformation |
169 | MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild |
Day 1 15:00-16:00 |
Oral 2: Emotion |
122 | Valence and Arousal Estimation In-The-Wild with Tensor Methods |
128 | Audio-Visual Emotion Forecasting: Characterizing and Predicting Future Emotion Using Deep Learning |
140 | Facial Expression Editing with Continuous Emotion Labels |
96 | The Many Variations of Emotion |
Day 2 10:30-12:00 |
Oral 3: Face Analysis and Synthesis |
40 | Attribute-Guided Sketch Generation |
21 | Photo-Realisitc Exemplar-Based Face Aging |
239 | DroneSURF: Benchmark Dataset for Drone-based Face Recognition |
204 | Modeling and Synthesizing Idiopathic Facial Paralysis |
125 | LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild |
164 | Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis |
Day 2 15:00-16:00 |
Oral 4: Action Units |
54 | IdenNet: Identity-Aware Facial Action Unit Detection |
154 | Cross-domain AU Detection: Domains, Learning Approaches, and Measures |
103 | Learning Temporal Information From A Single Image For AU Detection |
213 | Expression Empowered ResiDen Network for Facial Action Unit Detection |
Day 3 10:30-12:00 |
Oral 5: Face Recognition |
24 | The Deeper, the Better: Analysis of Person Attributes Recognition |
4 | Self-Supervised Learning of Face Representations for Video Face Clustering |
201 | Robust Video Face Recognition From a Single Still Using a Synthetic Plus Variational Model |
71 | Learning Discriminative and Complementary Patches for Face Recognition |
153 | Deformable Face Net: Learning Pose Invariant Feature with Pose Aware Feature Alignment for Face Recognition |
177 | Active Authentication using an Autoencoder regularized CNN-based One-Class Classifier |
Day 3 14:45-16:00 |
Oral 6 – Gaze, Pose and Gestures |
113 | A CNN Model for Head Pose Recognition using Wholes and Regions |
76 | Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks |
48 | Deep Conditional Variational Estimation for Depth-Based Hand Poses |
20 | Extended Gaze Following: Detecting Objects in Videos Beyond the Camera Field of View |
197 | AutoRate: How attentive is the driver? |
Day 1 | |
88 | Stacked Hourglass Network Joint with Salient Region Attention Refinement for Face Alignment |
31 | Video Prediction with Bidirectional Constraint Network |
171 | Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation |
72 | Bounded Residual Gradient Networks (BReG-Net) for Facial Affect Computing |
180 | Representation Learning Through Cross-Modality Supervision |
23 | Fully End to End Composite Recurrent Convolution Network for Deformable Facial Tracking In The Wild |
44 | Simultaneous Adversarial Training – Learn from Others’ Mistakes |
58 | Generalizing to Unseen Head Poses in Facial Expression Recognition and Action Unit Intensity Estimation |
240 | FaceSurv: A Benchmark Video Dataset for Face Detection and Recognition Across Spectra and Resolutions |
42 | shallowCNN-LE: A shallow CNN with Laplacian Embedding for face anti-spoofing |
73 | Context-aware Hybrid Neural Network Architecture for Video-based Facial Expression Recognition in the Wild |
27 | GF-CapsNet: Using Gabor Jet and Capsule Networks for Facial Age, Gender, and Expression Recognition |
56 | Automated Measurement of Head Movement Synchrony during Dyadic Depression Severity Interviews |
222 | Improving Viseme Recognition with GAN-based Muti-view Mapping |
234 | Facial Expression Recognition Using Deep Siamese Neural Networks with a Supervised Loss function |
Day 2 | |
62 | Analysis of temporal alignment for Video Classification |
35 | A Graph-Structured Representation with BRNN for Static-based Facial Expression Recognition |
82 | Hierarchical Group-level Emotion Recognition in the Wild |
78 | Toward Automated Classroom Observation: Predicting Positive and Negative Climate |
109 | On the effect of age perception biases for real age regression |
37 | Exploring Features and Attributes in Deep Face Recognition Using Visualization Techniques |
74 | A Boost in Revealing Subtle Facial Expressions: A Consolidated Eulerian Framework |
77 | DemogPairs: Quantifying the Impact of Demographic Imbalance in Deep Face Recognition |
93 | Improving Head Pose Estimation with a Combined Loss and Bounding Box Margin Adjustment |
150 | Revisiting a single-stage method for face detection |
152 | Discovering Identity Specific Activation Patterns in Deep Descriptors for Template Based Face Recognition |
146 | Skeleton-Based Hand Gesture Recognition by Learning SPD Matrices with Neural Networks |
116 | Analyze Spontaneous Gestures for Emotional Stress State Recognition: A Micro-gesture Dataset and Analysis with Deep Learning |
65 | Affect-driven Learning Outcomes Prediction in Intelligent Tutoring Systems |
220 | Hand range of motion evaluation for Rheumathoid Artritis patients |
236 | Robust Remote Heart Rate Estimation from Face Utilizing Spatial-temporal Attention |
238 | Characterizing the State of Apathy with Facial Expression and Motion Analysis |
Day 3 | |
136 | Time-series Clustering with Jointly Learning Deep Representations, Clusters and Temporal Boundaries |
143 | ESTIMATION OF MISSING HUMAN BODY PARTS VIA BIDIRECTIONAL LSTM |
117 | Pain Expression Recognition Using Occluded Faces |
22 | Deformable Synthesis Model for Emotion Recognition |
200 | Multimodal Deep feature aggregation for Facial Action Unit Recognition Using Visible images and physiological signals |
155 | 2D Landmark-Based Facial Asymmetry Assessment in the Clinical Case of Facial Paralysis |
47 | Fast Facial Image Analogy with Spatial Guidance |
130 | Are You Speaking: Real-Time Speech Activity Detection via Landmark Pooling Network |
156 | Reparameterising 3D Statistical Shape Models |
89 | LPM: Learnable Pooling Module for Efficient Full-Face Gaze Estimation |
205 | Matching Thermal to Visible Face Images Using a Semantic-Guided Generative Adversarial Network |
183 | Large Scale Sign Language Interpretation |
138 | Your Fellows Matter: Affect Analysis across Subjects in Group Videos |
Day 1 14:00-15:00 |
Fundamental Challenges in Modeling, Representation and Synthesis of Gestures |
13 | Segmentation Guided Image-to-Image Translation with Adversarial Networks |
67 | MAGIC: A Fundamental Framework for Gesture Representation, Comparison and Assessment |
66 | Database of Gesture Attributes: Zero Shot Learning for Gesture Recognition |
191 | Equipping social robots with culturally-sensitive facial expressions of emotion using data-driven methods |
Day 2 14:00-15:00 |
Human Health Monitoring Based on Computer Vision |
221 | Learning to Detect Genuine versus Posed Pain from Facial Expressions using Residual Generative Adversarial Networks |
232 | Characterization of the Handwriting Skills as a Biomarker for Parkinson’s Disease |
223 | Combining Global and Local Convolutional 3D Networks for Detecting Depression from Facial Expressions |
217 | Encoding Visual Behaviors with Attentive Temporal Convolution for Depression Prediction |
Day 3 14:00-15:00 |
Efficient and Reliable 3D Face Analysis |
225 | Local Feature Tensor Based Deep Learning for 3D Face Recognition |
219 | Learning Interpretable Expression-sensitive Features for 3D Dynamic Facial Expression Recognition |
218 | Discriminative Attention-based Convolutional Neural Network for 3D Facial Expression Recognition |
Demonstration title |
---|
When computers decode your social intention |
Event-based Visual Gesture Recognition with Background Suppression running on a Smart-phone |
Hand Gesture Recognition using Deep Root Nodal Architecture (DRONA) |
Coarse to Fine 3D Face Reconstruction from Single Image |
AFAR: A Deep Learning Based Tool for Automated Facial Affect Recognition |