HelloFace

An Awesome Face Technology Repository. (Updating)

SOTA

Highlight

face detection

face alignment

face recognition

## :computer: Website
https://becauseofAI.github.io/HelloFace (Welcome to maintain the website as a contributor through pulling request.)

## :bookmark_tabs: Content
- Recent Update
- 2022-04-05
- 2020-10-02
- 2020-01-26
- 2019-07-11
- 2019-04-06
- 2019-01-12
- 2018-12-01
- 2018-07-21
- 2018-04-20
- 2018-03-28
- Face Benchmark and Dataset
- Face Recognition Data
- Face Detection Data
- Face Landmark Data
- Face Attribute Data
- Face Recognition
- Face Detection
- Face Landmark
- Face Clustering
- Face Expression
- Face Action
- Face 3D
- Face GAN
- Face Character
- Face Editing
- Face De-Occlusion
- Face Aging
- Face Drawing
- Face Generation
- Face Makeup
- Face Swap
- Face Other
- Face Deblurring
- Face Super-Resolution
- Face Manipulation
- Face Anti-Spoofing
- Face Adversarial Attack
- Face Cross-Modal
- Face Capture
- Face Lib and Tool

## 👋 Recent Update
###### 2022-04-05
CVPR2021
- VirFace: Enhancing Face Recognition via Unlabeled Shallow Data [paper]
- MagFace: A Universal Representation for Face Recognition and Quality Assessment [paper]
- Variational Prototype Learning for Deep Face Recognition [paper]
- Cross-Domain Similarity Learning for Face Recognition in Unseen Domains [paper]
- Virtual Fully-Connected Layer: Training a Large-Scale Face Recognition Dataset With Limited Computational Resources [paper]
- Mitigating Face Recognition Bias via Group Adaptive Classifier [paper]
- Pseudo Facial Generation With Extreme Poses for Face Recognition [paper]
- Dynamic Class Queue for Large Scale Face Recognition in the Wild [paper]
- Improving Transferability of Adversarial Patches on Face Recognition With Generative Models [paper]
- WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition [paper]
- FaceSec: A Fine-Grained Robustness Evaluation Framework for Face Recognition Systems [paper]
- Spherical Confidence Learning for Face Recognition [paper]
- Consistent Instance False Positive Improves Fairness in Face Recognition [paper]
- CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement [paper]
- HLA-Face: Joint High-Low Adaptation for Low Light Face Detection [paper]
- Structure-Aware Face Clustering on a Large-Scale Graph With 107 Nodes [paper]
- img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation [paper]
- Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition [paper]
- Continuous Face Aging via Self-Estimated Residual Age Embedding [paper]
- When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework [paper]
- SDD-FIQA: Unsupervised Face Image Quality Assessment With Similarity Distribution Distance [paper]
- TediGAN: Text-Guided Diverse Face Image Generation and Manipulation [paper]
- GAN Prior Embedded Network for Blind Face Restoration in the Wild [paper]
- Inverting Generative Adversarial Renderer for Face Reconstruction [paper]
- Progressive Semantic-Aware Style Transformation for Blind Face Restoration [paper]
- Towards Real-World Blind Face Restoration With Generative Facial Prior [paper]
- FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains [paper]
- One Shot Face Swapping on Megapixels [paper]
- High-Fidelity and Arbitrary Face Editing [paper]
- Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association [paper]
- Flow-Guided One-Shot Talking Face Generation With a High-Resolution Audio-Visual Dataset [paper]
- Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation [paper]
- Monocular Reconstruction of Neural Face Reflectance Fields [paper]
- Learning Complete 3D Morphable Face Models From Images and Videos [paper]
- Riggable 3D Face Reconstruction via In-Network Optimization [paper]
- Learning To Aggregate and Personalize 3D Face From In-the-Wild Photo Collection [paper]
- Lifting 2D StyleGAN for 3D-Aware Face Generation [paper]
- 3DCaricShop: A Dataset and a Baseline Method for Single-View 3D Caricature Face Reconstruction [paper]
- Pareidolia Face Reenactment [paper]
- Lips Don’t Lie: A Generalisable and Robust Approach To Face Forgery Detection [paper]
- Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain [paper]
- Frequency-Aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection [paper]
- Generalizing Face Forgery Detection With High-Frequency Features [paper]
- Face Forgery Detection by 3D Decomposition [paper]
- Exploring Adversarial Fake Images on Face Manifold [paper]
- Representative Forgery Mining for Fake Face Detection [paper]
- Cross Modal Focal Loss for RGBD Face Anti-Spoofing [paper]
- High-Fidelity Face Tracking for AR/VR via Deep Lighting Adaptation [paper]
- Towards High Fidelity Face Relighting With Realistic Shadows [paper]
- IronMask: Modular Architecture for Protecting Deep Face Template [paper]
- Face Forensics in the Wild [paper]

ICCV2021
- Body-Face Joint Detection via Embedding and Head Hook [paper]
- Adaptive Label Noise Cleaning With Meta-Supervision for Deep Face Recognition [paper]
- Teacher-Student Adversarial Depth Hallucination To Improve Face Recognition [paper]
- DAM: Discrepancy Alignment Metric for Face Recognition [paper]
- SynFace: Face Recognition With Synthetic Data [paper]
- PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition [paper]
- Disentangled Representation for Age-Invariant Face Recognition: A Mutual Information Minimization Perspective [paper]
- Learning Facial Representations From the Cycle-Consistency of Face [paper]
- Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation [paper]
- ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment [paper]
- Towards Face Encryption by Generating Adversarial Identity Masks [paper]
- A Latent Transformer for Disentangled Face Editing in Images and Videos [paper]
- Re-Aging GAN: Toward Personalized Face Age Transformation [paper]
- Disentangled Lifespan Face Synthesis [paper]
- Face Image Retrieval With Attribute Manipulation [paper]
- Self-Supervised 3D Face Reconstruction via Conditional Estimation [paper]
- Towards High Fidelity Monocular Face Reconstruction With Rich Reflectance Using Self-Supervised Learning and Ray Tracing [paper]
- Self-Supervised 3D Face Reconstruction via Conditional Estimation [paper]
- Topologically Consistent Multi-View Face Inference Using Volumetric Sampling [paper]
- Fake It Till You Make It: Face Analysis in the Wild Using Synthetic Data Alone [paper]
- Exploring Temporal Coherence for More General Video Face Forgery Detection [paper]
- OpenForensics: Large-Scale Challenging Dataset for Multi-Face Forgery Detection and Segmentation In-the-Wild [paper]
- Detection and Continual Learning of Novel Face Presentation Attacks [paper]
- MeshTalk: 3D Face Animation From Speech Using Cross-Modality Disentanglement [paper]
- Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar [paper]
- Multi-Modality Associative Bridging Through Memory: Speech Sound Recollected From Face Video [paper]
- FACIAL: Synthesizing Dynamic Talking Face With Implicit Attribute Learning [paper]
- VariTex: Variational Neural Face Textures [paper]
- Learning High-Fidelity Face Texture Completion Without Complete Face Texture [paper]

###### 2020-10-02
ICIP2020
- 3D SPARSE DEFORMATION SIGNATURE FOR DYNAMIC FACE RECOGNITION
- A Stacking Ensemble for Anomaly Based Client-Specific Face Spoofing Detection
- ADAPTIVE AGGREGATED TRACKLET LINKING FOR MULTI-FACE TRACKING
- ATTENTION SELECTIVE NETWORK FOR FACE SYNTHESIS AND POSE-INVARIANT FACE RECOGNITION
- EDGE-GAN: EDGE CONDITIONED MULTI-VIEW FACE IMAGE GENERATION
- EXTRACTING DEEP LOCAL FEATURES TO DETECT MANIPULATED IMAGES OF HUMAN FACES
- FACE AUTHENTICATION FROM GRAYSCALE CODED LIGHT FIELD
- FACE RECOGNITION UNDER LOW ILLUMINATION VIA DEEP FEATURE RECONSTRUCTION NETWORK
- IMPROVING DETECTION AND RECOGNITION OF DEGRADED FACES BY DISCRIMINATIVE FEATURE RESTORATION USING GAN
- QAMFACE: QUADRATIC ADDITIVE ANGULAR MARGIN LOSS FOR FACE RECOGNITION
- REALISTIC TALKING FACE SYNTHESIS WITH GEOMETRY-AWARE FEATURE TRANSFORMATION
- TRIPLET DISTILLATION FOR DEEP FACE RECOGNITION

ECCV2020
- “Look Ma, no landmarks!” – Unsupervised, Model-based Dense Face Alignment
- Hierarchical Face Aging through Disentangled Latent Characteristics
- Semi-Siamese Training for Shallow Face Learning
- Face Super-Resolution Guided by 3D Facial Priors
- Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting
- ProgressFace: Scale-Aware Progressive Learning for Face Detection
- Face Anti-Spoofing with Human Material Perception
- Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction
- Blind Face Restoration via Deep Multi-scale Component Dictionaries
- Inequality-Constrained and Robust 3D Face Model Fitting
- BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition
- Explainable Face Recognition
- CONFIG: Controllable Neural Face Image Generation
- Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces
- CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations
- Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues
- Edge-aware Graph Representation Learning and Reasoning for Face Parsing
- Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision
- CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention Feature
- Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency
- Generate to Adapt: Resolution Adaption Network for Surveillance Face Recognition
- Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation
- Design and Interpretation of Universal Adversarial Patches in Face Detection
- JNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling
- On Disentangling Spoof Trace for Generic Face Anti-Spoofing
- Towards causal benchmarking of bias in face analysis algorithms
- Towards Fast, Accurate and Stable 3D Dense Face Alignment
- Face Anti-Spoofing via Disentangled Representation Learning
- Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model
- MEAD: A Large-scale Audio-visual Dataset for Emotional Talking-face Generation
- Margin-Mix: Semi–Supervised Learning for Face Expression Recognition
- Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
- Improving Face Recognition by Clustering Unlabeled Faces in the Wild
- Exclusivity-Consistency Regularized Knowledge Distillation for Face Recognition
- BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions
- Eyeglasses 3D shape reconstruction from a single face image
- Deep Cross-species Feature Learning for Animal Face Recognition via Residual Interspecies Equivariant Network
- High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images
- ByeGlassesGAN: Identity Preserving Eyeglasses Removal for Face Images
- Jointly De-biasing Face Recognition and Demographic Attribute Estimation
- Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks
- Improving Face Recognition from Hard Samples via Distribution Distillation Loss
- Manifold Projection for Adversarial Defense on Face Recognition

SIGGRAPH2020
- A System for Efficient 3D Printed Stop-Motion Face Animation
- Accurate Face Rig Approximation With Deep Differential Subspace Reconstruction
- DeepFaceDrawing: Deep Generation of Face Images from Sketches
- The Eyes Have It: An Integrated Eye and Face Model for Photorealistic Facial Animation

IJCAI2020
- Biased Feature Learning for Occlusion Invariant Face Recognition
- Reference Guided Face Component Editing
- Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning
- FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces

CVPR2020
- Cross-Modal Deep Face Normals With Deactivable Skip Connections
- One-Shot Domain Adaptation for Face Generation
- Towards Learning Structure via Consensus for Face Segmentation and Parsing
- BFBox: Searching Face-Appropriate Backbone and Feature Pyramid Network for Face Detector
- Domain Balancing: Face Recognition on Long-Tailed Domains
- FReeNet: Multi-Identity Face Reenactment
- Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment
- Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition
- 3FabRec: Fast Few-Shot Face Alignment by Reconstruction
- Global Texture Enhancement for Fake Face Detection in the Wild
- CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
- On the Detection of Digital Face Manipulation
- Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing
- ReDA:Reinforced Differentiable Attribute for 3D Face Reconstruction
- Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning
- FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction
- Interpreting the Latent Space of GANs for Semantic Face Editing
- Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View Images
- Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
- Density-Aware Feature Embedding for Face Clustering
- Learning to Have an Ear for Face Super-Resolution
- Learning Formation of Physically-Based Face Attributes
- LUVLi Face Alignment: Estimating Landmarks’ Location, Uncertainty, and Visibility Likelihood
- Learning Meta Face Recognition in Unseen Domains
- Cross-Spectral Face Hallucination via Disentangling Independent Factors
- Deep Face Super-Resolution With Iterative Collaboration Between Attentive Recovery and Landmark Estimation
- Data Uncertainty Learning in Face Recognition
- Face X-Ray for More General Face Forgery Detection
- Vec2Face: Unveil Human Faces From Their Blackbox Features in Face Recognition
- FM2u-Net: Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification
- Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction
- Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature Fusion
- SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness
- Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional Networks
- RDCFace: Radial Distortion Correction for Face Recognition
- Searching Central Difference Convolutional Networks for Face Anti-Spoofing
- RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild
- Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning
- DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
- GroupFace: Learning Latent Groups and Constructing Group-Based Representations for Face Recognition
- A Morphable Face Albedo Model
- Learning Oracle Attention for High-Fidelity Face Completion
- Learning Physics-Guided Face Relighting Under Directional Light
- Towards Universal Representation Learning for Deep Face Recognition
- Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition
- HAMBox: Delving Into Mining High-Quality Anchors on Face Detection
- Hierarchical Pyramid Diverse Attention Networks for Face Recognition
- Dynamic Face Video Segmentation via Reinforcement Learning
- Copy and Paste GAN: Face Hallucination From Shaded Thumbnails
- Single-Side Domain Generalization for Face Anti-Spoofing

AAAI2020
- Fast and Robust Face-to-Parameter Translation for Game Character Auto-Creation
- Mis-classified Vector Guided Softmax Loss for Face Recognition
- Learning Meta Model for Zero- and Few-shot Face Anti-spoofing
- Learning to Deblur Face Images via Sketch Synthesis
- FAN-Face: a simple orthogonal improvement to deep face recognition
- KPNet: Towards Minimal Face Detector
- Towards Omni-Supervised Face Alignment for Large Scale Unlabeled Videos
- Regularized Fine-grained Meta Face Anti-spoofing
- GDFace: Gated Deformation for Multi-view Face Image Synthesis
- Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose
- MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets
- A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing
- Video Face Super-Resolution with Motion-Adaptive Feedback Cell
- Facial Attribute Capsules for Noise Face Super Resolution
- Joint Super-Resolution and Alignment of Tiny Faces
###### 2020-01-26
- UGG: Uncertainty Modeling of Contextual-Connections Between Tracklets for Unconstrained Video-Based Face Recognition
- PDSN: Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network
- Attentional Feature-Pair Relation Networks for Accurate Face Recognition
- PFE: Probabilistic Face Embeddings
- Towards Interpretable Face Recognition
- Co-Mining: Deep Face Recognition With Noisy Labels
- Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition
- Discriminatively Learned Convex Models for Set Based Face Recognition
- DVG: Dual Variational Generation for Low Shot Heterogeneous Face Recognition
- CDP: Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition

- BCL: Video Face Clustering With Unknown Number of Clusters

- DeCaFA: Deep Convolutional Cascade for Face Alignment in the Wild
- AWing: Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
- KDN: Face Alignment With Kernel Density Deep Neural Network

- DF2Net: A Dense-Fine-Finer Network for Detailed 3D Face Reconstruction
- Face Video Deblurring Using 3D Facial Priors
- Semi-Supervised Monocular 3D Face Reconstruction With End-to-End Shape-Preserved Domain Transfer
- 3DFC: 3D Face Modeling From Diverse Raw Scan Data

- Live Face De-Identification in Video
- Face-to-Parameter Translation for Game Character Auto-Creation
- SC-FEGAN: Face Editing Generative Adversarial Network With User’s Sketch and Color
- FSGAN: Subject Agnostic Face Swapping and Reenactment
- Make a Face: Towards Arbitrary High Fidelity Face Manipulation
- Face De-Occlusion Using 3D Morphable Model and Generative Adversarial Network
- FRV: Face Reconstruction from Voice using Generative Adversarial Networks
- From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech
- PFSR: Progressive Face Super-Resolution via Attention to Facial Landmark

###### 2019-07-11
- Deep face recognition using imperfect facial data
- Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data
- RegularFace: Deep Face Recognition via Exclusive Regularization
- UniformFace: Learning Deep Equidistributed Representation for Face Recognition
- P2SGrad: Refined Gradients for Optimizing Deep Face Models
- AdaptiveFace: Adaptive Margin and Sampling for Face Recognition
- AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
- Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition
- NoiseFace: Noise-Tolerant Paradigm for Training Face Recognition CNNs
- Feature Transfer Learning for Face Recognition With Under-Represented Data
- Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces
- R3 Adversarial Network for Cross Model Face Recognition

- RetinaFace: Single-stage Dense Face Localisation in the Wild
- Group Sampling for Scale Invariant Face Detection
- FA-RPN: Floating Region Proposals for Face Detection

- Semantic Alignment: Finding Semantically Consistent Ground-Truth for Facial Landmark Detection
- Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks

- LTC: Learning to Cluster Faces on an Affinity Graph

- FECNet: A Compact Embedding for Facial Expression Similarity
- LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences

- Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation
- Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection
- TCAE: Self-Supervised Representation Learning From Videos for Facial Action Unit Detection
- JAANet: Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment

- 2DASL: Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning
- MVF-Net: Multi-View 3D Face Morphable Model Regression
- Dense 3D Face Decoding Over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders
- Towards High-Fidelity Nonlinear 3D Face Morphable Model
- Combining 3D Morphable Models: A Large Scale Face-And-Head Model
- Disentangled Representation Learning for 3D Face Shap
- Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking
- MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction
- Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision
- Boosting Local Shape Matching for Dense 3D Face Correspondence
- FML: Face Model Learning From Videos
- 2DASL: Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning

- ATVGnet: Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss
- Speech2Face: Learning the Face Behind a Voice

- Unsupervised Face Normalization With Extreme Pose and Expression in the Wild
- GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction

- BeautyGAN: Instance-level Facial Makeup Transfer with Deep Generative Adversarial Network
- FUNIT: Few-Shot Unsupervised Image-to-Image Translation
- Automatic Face Aging in Videos via Deep Reinforcement Learning
- Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks
- SAGAN:Generative Adversarial Network with Spatial Attention for Face Attribute Editing
- APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs
- StyleGAN: A Style-Based Generator Architecture for Generative Adversarial Networks

- 3D Guided Fine-Grained Face Manipulation
- SemanticComponent: Semantic Component Decomposition for Face Attribute Manipulation

- Dataset and Benchmark: A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing
- Deep Tree Learning for Zero-Shot Face Anti-Spoofing

- Decorrelated Adversarial Learning for Age-Invariant Face Recognition
- Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection
- Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition

- Speech2Face: Learning the Face Behind a Voice
- JFDFMR: Joint Face Detection and Facial Motion Retargeting for Multiple Faces
- ATVGnet: Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss

- High-Quality Face Capture Using Anatomical Muscles
- Monocular Total Capture: Posing Face, Body, and Hands in the Wild
- Expressive Body Capture: 3D Hands, Face, and Body From a Single Image

###### 2019-04-06
- ISRN: Improved Selective Refinement Network for Face Detection
- DSFD: Dual Shot Face Detector
- PyramidBox++: High Performance Detector for Finding Tiny Face
- VIM-FD: Robust and High Performance Face Detector
- SHF: Robust Face Detection via Learning Small Faces on Hard Images
- SRN: Selective Refinement Network for High Performance Face Detection
- SFDet: Single-Shot Scale-Aware Network for Real-Time Face Detection
- JFDFMR: Joint Face Detection and Facial Motion Retargeting for Multiple Faces
- PFLD: A Practical Facial Landmark Detector
- LinkageFace: Linkage Based Face Clustering via Graph Convolution Network
- MLT: Face Recognition: A Novel Multi-Level Taxonomy based Survey
- GhostVLAD: GhostVLAD for set-based face recognition
- DocFace+: ID Document to Selfie Matching
- DiF: Diversity in Faces
- 2018Survey: Face Recognition: From Traditional to Deep Learning Methods

###### 2019-01-12
- 2018Survey: Deep Facial Expression Recognition: A Survey
- 2018Survey: Deep Face Recognition: A Survey
- SphereFace+(MHE): Learning towards Minimum Hyperspherical Energy
- HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition

###### 2018-12-01
- FRVT: Face Recognition Vendor Test
- GANimation: Anatomically-aware Facial Animation from a Single Image
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
- Faceswap: A tool that utilizes deep learning to recognize and swap faces in pictures and videos
- HF-PIM: Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization
- PRNet: Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network
- LAB: Look at Boundary: A Boundary-Aware Face Alignment Algorithm
- Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
- Face-Alignment: How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)
- Face3D: Python tools for processing 3D face
- IMDb-Face: The Devil of Face Recognition is in the Noise
- AAM-Softmax(CCL): Face Recognition via Centralized Coordinate Learning
- AM-Softmax: Additive Margin Softmax for Face Verification
- FeatureIncay: Feature Incay for Representation Regularization
- NormFace: L2 hypersphere embedding for face Verification
- CocoLoss: Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
- L-Softmax: Large-Margin Softmax Loss for Convolutional Neural Networks

###### 2018-07-21
- MobileFace: A face recognition solution on mobile device
- Trillion Pairs: Challenge 3: Face Feature Test/Trillion Pairs
- MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices

###### 2018-04-20
- PyramidBox: A Context-assisted Single Shot Face Detector
- PCN: Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks
- S³FD: Single Shot Scale-invariant Face Detector
- SSH: Single Stage Headless Face Detector
- NPD: A Fast and Accurate Unconstrained Face Detector
- PICO: Object Detection with Pixel Intensity Comparisons Organized in Decision Trees
- libfacedetection: A fast binary library for face detection and face landmark detection in images.
- SeetaFaceEngine: SeetaFace Detection, SeetaFace Alignment and SeetaFace Identification.
- FaceID: An implementation of iPhone X’s FaceID using face embeddings and siamese networks on RGBD images.

###### 2018-03-28
- InsightFace(ArcFace): 2D and 3D Face Analysis Project
- CosFace: Large Margin Cosine Loss for Deep Face Recognition

## 🔖 Face Benchmark and Dataset
#### Face Recognition Data
- DiF: Diversity in Faces [project] [blog]
- FRVT: Face Recognition Vendor Test [project] [leaderboard]
- IMDb-Face: The Devil of Face Recognition is in the Noise(59k people in 1.7M images) [paper] [dataset]
- Trillion Pairs: Challenge 3: Face Feature Test/Trillion Pairs(MS-Celeb-1M-v1c with 86,876 ids/3,923,399 aligned images + Asian-Celeb 93,979 ids/2,830,146 aligned images) [benckmark] [dataset] [result]
- MF2: Level Playing Field for Million Scale Face Recognition(672K people in 4.7M images) [paper] [dataset] [result] [benckmark]
- MegaFace: The MegaFace Benchmark: 1 Million Faces for Recognition at Scale(690k people in 1M images) [paper] [dataset] [result] [benckmark]
- UMDFaces: An Annotated Face Dataset for Training Deep Networks(8k people in 367k images with pose, 21 key-points and gender) [paper] [dataset]
- MS-Celeb-1M: A Dataset and Benchmark for Large Scale Face Recognition(100K people in 10M images) [paper] [dataset] [result] [benchmark] [project]
- VGGFace2: A dataset for recognising faces across pose and age(9k people in 3.3M images) [paper] [dataset]
- VGGFace: Deep Face Recognition(2.6k people in 2.6M images) [paper] [dataset]
- CASIA-WebFace: Learning Face Representation from Scratch(10k people in 500k images) [paper] [dataset]
- LFW: Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments(5.7k people in 13k images) [report] [dataset] [result] [benchmark]

#### Face Detection Data
- WiderFace: WIDER FACE: A Face Detection Benchmark(400k people in 32k images with a high degree of variability in scale, pose and occlusion) [paper] [dataset] [result] [benchmark]
- FDDB: A Benchmark for Face Detection in Unconstrained Settings(5k faces in 2.8k images) [report] [dataset] [result] [benchmark]

#### Face Landmark Data
- LS3D-W: A large-scale 3D face alignment dataset constructed by annotating the images from AFLW, 300VW, 300W and FDDB in a consistent manner with 68 points using the automatic method [paper] [dataset]
- AFLW: Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization(25k faces with 21 landmarks) [paper] [benchmark]

#### Face Attribute Data
- CelebA: Deep Learning Face Attributes in the Wild(10k people in 202k images with 5 landmarks and 40 binary attributes per image) [paper] [dataset]

## 🔖 Face Recognition
- Live Face De-Identification in Video [paper]
- UGG: Uncertainty Modeling of Contextual-Connections Between Tracklets for Unconstrained Video-Based Face Recognition [paper]
- PDSN: Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network [paper] [code]
- Attentional Feature-Pair Relation Networks for Accurate Face Recognition [paper]
- Probabilistic Face Embeddings [paper] [code]
- Towards Interpretable Face Recognition [paper] [code] [project]
- Co-Mining: Deep Face Recognition With Noisy Labels [paper]
- Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition [paper]
- Discriminatively Learned Convex Models for Set Based Face Recognition [paper]
- DVG: Dual Variational Generation for Low Shot Heterogeneous Face Recognition [paper] [code]
- Deep face recognition using imperfect facial data [paper]
- Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Data [paper] [code]
- RegularFace: Deep Face Recognition via Exclusive Regularization [paper]
- UniformFace: Learning Deep Equidistributed Representation for Face Recognition [paper]
- P2SGrad: Refined Gradients for Optimizing Deep Face Models [paper]
- AdaptiveFace: Adaptive Margin and Sampling for Face Recognition [paper]
- AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations [paper] [code1] [code2]
- Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition [paper]
- NoiseFace: Noise-Tolerant Paradigm for Training Face Recognition CNNs [paper] [code]
- Feature Transfer Learning for Face Recognition With Under-Represented Data [paper]
- Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces [paper] [code] [dataset]
- R3 Adversarial Network for Cross Model Face Recognition [paper]
- MLT: Face Recognition: A Novel Multi-Level Taxonomy based Survey [paper]
- CDP: Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition [paper] [code] [project]
- GhostVLAD: GhostVLAD for set-based face recognition [paper]
- DocFace+: ID Document to Selfie Matching [paper] [code]
- 2018Survey: Face Recognition: From Traditional to Deep Learning Methods [paper]
- 2018Survey: Deep Facial Expression Recognition: A Survey [paper]
- 2018Survey: Deep Face Recognition: A Survey [paper]
- SphereFace+(MHE): Learning towards Minimum Hyperspherical Energy [paper] [code]
- MobileFace: A face recognition solution on mobile device [code]
- MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices [paper] [code1] [code2] [code3] [code4]
- FaceID: An implementation of iPhone X’s FaceID using face embeddings and siamese networks on RGBD images. [code] [blog]
- InsightFace(ArcFace): 2D and 3D Face Analysis Project [paper] [code1] [code2]
- AAM-Softmax(CCL): Face Recognition via Centralized Coordinate Learning [paper]
- AM-Softmax: Additive Margin Softmax for Face Verification [paper] [code1] [code2]
- CosFace: Large Margin Cosine Loss for Deep Face Recognition [paper] [code1] [code2]
- FeatureIncay: Feature Incay for Representation Regularization [paper]
- CocoLoss: Rethinking Feature Discrimination and Polymerization for Large-scale Recognition [paper] [code]
- NormFace: L2 hypersphere embedding for face Verification [paper] [code]
- SphereFace(A-Softmax): Deep Hypersphere Embedding for Face Recognition [paper] [code]
- L-Softmax: Large-Margin Softmax Loss for Convolutional Neural Networks [paper] [code1] [code2] [code3] [code4] [code5] [code6] [code7]
- CenterLoss: A Discriminative Feature Learning Approach for Deep Face Recognition [paper] [code1] [code2] [code3] [code4]
- OpenFace: A general-purpose face recognition library with mobile applications [report] [project] [code1] [code2]
- FaceNet: A Unified Embedding for Face Recognition and Clustering [paper] [code]
- DeepID3: DeepID3: Face Recognition with Very Deep Neural Networks [paper]
- DeepID2+: Deeply learned face representations are sparse, selective, and robust [paper]
- DeepID2: Deep Learning Face Representation by Joint Identification-Verification [paper]
- DeepID: Deep Learning Face Representation from Predicting 10,000 Classes [paper]
- DeepFace: Closing the gap to human-level performance in face verification [paper]
- LBP+Joint Bayes: Bayesian Face Revisited: A Joint Formulation [paper] [code1] [code2] [code3]
- LBPFace: Face recognition with local binary patterns [paper] [code]
- FisherFace(LDA): Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection [paper] [code]
- EigenFace(PCA): Face recognition using eigenfaces [paper] [code]

## 🔖 Face Detection
- RetinaFace: Single-stage Dense Face Localisation in the Wild [paper] [code]
- Group Sampling for Scale Invariant Face Detection [paper]
- FA-RPN: Floating Region Proposals for Face Detection [paper]
- SFA: Small Faces Attention Face Detector [paper] [code]
- ISRN: Improved Selective Refinement Network for Face Detection [paper]
- DSFD: Dual Shot Face Detector [paper] [code]
- PyramidBox++: High Performance Detector for Finding Tiny Face [paper]
- VIM-FD: Robust and High Performance Face Detector [paper]
- SHF: Robust Face Detection via Learning Small Faces on Hard Images [paper] [code]
- SRN: Selective Refinement Network for High Performance Face Detection [paper]
- SFDet: Single-Shot Scale-Aware Network for Real-Time Face Detection [paper]
- HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition [paper] [code]
- PyramidBox: A Context-assisted Single Shot Face Detector [paper] [code]
- PCN: Real-Time Rotation-Invariant Face Detection with Progressive Calibration Networks [paper] [code]
- S³FD: Single Shot Scale-invariant Face Detector [paper] [code]
- SSH: Single Stage Headless Face Detector [paper] [code]
- FaceBoxes: A CPU Real-time Face Detector with High Accuracy [paper][code1] [code2]
- TinyFace: Finding Tiny Faces [paper] [project] [code1] [code2] [code3]
- MTCNN: Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks [paper] [project] [code1] [code2] [code3] [code4] [code5] [code6] [code7]
- NPD: A Fast and Accurate Unconstrained Face Detector [paper] [code] [project]
- PICO: Object Detection with Pixel Intensity Comparisons Organized in Decision Trees [paper] [code]
- libfacedetection: A fast binary library for face detection and face landmark detection in images. [code]
- SeetaFaceEngine: SeetaFace Detection, SeetaFace Alignment and SeetaFace Identification [code]

## 🔖 Face Landmark
- DeCaFA: Deep Convolutional Cascade for Face Alignment in the Wild [paper]
- AWing: Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression [paper] [code]
- KDN: Face Alignment With Kernel Density Deep Neural Network [paper]
- Semantic Alignment: Finding Semantically Consistent Ground-Truth for Facial Landmark Detection [paper]
- Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks [paper]
- PFLD: A Practical Facial Landmark Detector [paper] [project] [code]
- PRNet: Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network [paper] [code]
- LAB: Look at Boundary: A Boundary-Aware Face Alignment Algorithm [paper] [project] [code]
- Face-Alignment: How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks) [paper] [project] [code1] [code2]
- ERT: One Millisecond Face Alignment with an Ensemble of Regression Trees [paper] [code]

## 🔖 Face Clustering
- BCL: Video Face Clustering With Unknown Number of Clusters [paper] [code]
- LinkageFace: Linkage Based Face Clustering via Graph Convolution Network [paper]
- LTC: Learning to Cluster Faces on an Affinity Graph [paper] [code]

## 🔖 Face Expression
- FECNet: A Compact Embedding for Facial Expression Similarity [paper] [code]
- LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences [paper]

## 🔖 Face Action
- Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation [paper]
- Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection [paper]
- TCAE: Self-Supervised Representation Learning From Videos for Facial Action Unit Detection [paper] [code]
- JAANet: Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment [paper] [code]

## 🔖 Face 3D
- DF2Net: A Dense-Fine-Finer Network for Detailed 3D Face Reconstruction [paper] [code]
- Semi-Supervised Monocular 3D Face Reconstruction With End-to-End Shape-Preserved Domain Transfer [paper]
- 3DFC: 3D Face Modeling From Diverse Raw Scan Data [paper] [code]
- 2DASL: Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning [paper] [code]
- MVF-Net: Multi-View 3D Face Morphable Model Regression [paper] [code]
- Dense 3D Face Decoding Over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders [paper]
- Towards High-Fidelity Nonlinear 3D Face Morphable Model [paper] [project]
- Combining 3D Morphable Models: A Large Scale Face-And-Head Model [paper]
- Disentangled Representation Learning for 3D Face Shape [paper] [code]
- Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking [paper]
- MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction [paper]
- RingNet: Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision [paper] [code] [project]
- Boosting Local Shape Matching for Dense 3D Face Correspondence [paper]
- FML: Face Model Learning From Videos [paper]

## 🔖 Face GAN
#### Face Character
- Face-to-Parameter Translation for Game Character Auto-Creation [paper]
—-
#### Face Editing
- SC-FEGAN: Face Editing Generative Adversarial Network With User’s Sketch and Color [paper] [code]
—-
#### Face De-Occlusion
- Face De-Occlusion Using 3D Morphable Model and Generative Adversarial Network [paper] [code]
—-
#### Face Aging
- Automatic Face Aging in Videos via Deep Reinforcement Learning [paper] [blog]
- Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks [paper]
- SAGAN:Generative Adversarial Network with Spatial Attention for Face Attribute Editing [paper] [code]
—-
#### Face Drawing
- APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs [paper] [code]
—-
#### Face Generation
- StyleGAN: A Style-Based Generator Architecture for Generative Adversarial Networks [paper] [code] [dataset]
—-
#### Face Makeup
- BeautyGAN: Instance-level Facial Makeup Transfer with Deep Generative Adversarial Network [paper] [code] [project] [poster]
—-
#### Face Swap
- FSGAN: Subject Agnostic Face Swapping and Reenactment [paper] [code] [project]
- Faceswap: A tool that utilizes deep learning to recognize and swap faces in pictures and videos [code1] [code2]
- FUNIT: Few-Shot Unsupervised Image-to-Image Translation [paper] [code] [project]
—-
#### Face Other
- Unsupervised Face Normalization With Extreme Pose and Expression in the Wild [paper] [code]
- GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction [paper] [project]
- HF-PIM: Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization [paper]
- Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs [paper]
- GANimation: Anatomically-aware Facial Animation from a Single Image [paper] [project] [code]
- StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation [paper]
[code]
- PGAN: Progressive Growing of GANs for Improved Quality, Stability, and Variation [paper]
[code1] [code2]

## 🔖 Face Deblurring
- Face Video Deblurring Using 3D Facial Priors [paper] [code]

## 🔖 Face Super-Resolution
- PFSR: Progressive Face Super-Resolution via Attention to Facial Landmark [paper] [code]

## 🔖 Face Manipulation
- Make a Face: Towards Arbitrary High Fidelity Face Manipulation [paper]
- 3D Guided Fine-Grained Face Manipulation [paper]
- SemanticComponent: Semantic Component Decomposition for Face Attribute Manipulation [paper] [code] [demo]

## 🔖 Face Anti-Spoofing
- Dataset and Benchmark: A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing [paper] [poster] [dataset]
- Deep Tree Learning for Zero-Shot Face Anti-Spoofing [paper]

## 🔖Face Adversarial Attack
- Decorrelated Adversarial Learning for Age-Invariant Face Recognition [paper]
- Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection [paper]
- Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition [paper]

## 🔖 Face Cross-Modal
- From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech [paper]
- FRV: Face Reconstruction from Voice using Generative Adversarial Networks [paper] [code] [poster]
- Speech2Face: Learning the Face Behind a Voice [paper] [project]
- JFDFMR: Joint Face Detection and Facial Motion Retargeting for Multiple Faces [paper]
- ATVGnet: Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Loss [paper] [code]

## 🔖 Face Capture
- High-Quality Face Capture Using Anatomical Muscles [paper]
- Monocular Total Capture: Posing Face, Body, and Hands in the Wild [paper] [code] [project]
- Expressive Body Capture: 3D Hands, Face, and Body From a Single Image [paper] [code] [project]

## :hammer: Face Lib and Tool
- Dlib [url] [github]
- OpenCV [docs] [github]
- Face3D [github]

—-
#

:boom:Big Bang:boom:

####

Receptive Field Is Natural Anchor

####

Receptive Field Is All You Need

2K real-time detection is so easy!

[Paper] [MXNet] [PyTorch]

" class="reference-link">

[Paper] [MXNet] [PyTorch]