jnulzl/facepapercollection

A collection of face related papers

Face related papers collection

A collection for the face-related papers and codes.

Updated on 11/04/2017

Face Detection

1. Multiview Face Detection: [Paper] [Code] (Caffe + Python)
2. Finding Tiny Faces: [Project][Paper] [Code] (MatConvNet + MATLAB)
3. Focal Loss: [Paper]
4. SSH: [Paper]
5. Face R-CNN: [Paper]
6. FaceBoxes: [Paper] [Code] (Caffe)
7. S³FD: [Paper]

Face Alignment

In this part, you can retrieve the paper before 2016 on this site.

1. PIFA: Pose-invariant 3D face alignment [Paper] [Code]
2. MDM: Mnemonic Descent Method [Paper] [Code]
3. JFA: Joint head pose estimation and face alignment [Paper]
4. GoDP: Globally optimized dual path way [Paper]
5. Recurrent 3D-2D Dual Learning: [Paper]

Face Reconstruction

1. UH-E2FAR [Paper]
2. Multi-View RNN [Paper]
3. 3D Face Morphable Models "In-the-Wild" [Paper]
4. 3DMM-CNN [Paper] [Code]
5. VRN [Paper] [Code]
6. 3DFaceNet [Paper]
7. MoFA: Unsupervised learning for 3D model and pose parameters [Paper]
8. 3DMM-STN: Using 3DMM to transfer 2D image to 2D image texture [Paper]

Face GAN

1. TP-GAN: [Paper]
2. FF-GAN: [Paper]
3. DR-GAN: [Paper] [Website]
4. BEGAN: Boundary Equilibrium Generative Adversarial Networks [Paper]

Feature Representation

Network

1. DeepFace: [Paper]
2. DeepID series: [DeepID] [DeepID2] [DeepID3]
3. VGG-Face: VGG-Face CNN descriptor.
4. VGG-Face2: VGG-Face ResNet descriptor.

Loss

1. Triplet Loss [Paper][Code](Torch) [Code](TensorFlow)
2. Center Loss [Paper] [Code](Caffe + MATLAB) [Code] (MxNet)
3. Range Loss [Paper] [Code] (Caffe)
4. L-Softmax [Paper] [Code] (Caffe) [Code] (MxNet)
5. A-Softmax Loss (SphereFace) [Paper] [Code] (Caffe)
6. Marginal Loss [Paper]

Pipelines

1. OpenFace: Face recognition with Google's FaceNet deep neural network using Torch.
2. SeetaFaceEngine: An open source C++ face recognition engine.
3. UR2D: 3D-aided 2D Face Recognition system

Tutorial

1. Deep Learning for Face Recognition

Datasets

1. Detection
   1. FDDB: Face Detection and Data Set Benchmark. 5k images [Download]
   2. AFLW: Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization. 25K images. [Download]
2. Recognition:
   1. MS-Celeb-1M: Microsoft dataset contains around 1M subjects [Paper] [Download]
   2. CASIA WebFace: 10,575 subjects and 494,414 images [Paper] [Download]
   3. LFW: 13,000 images and 5749 subjects [Download]
   4. CelebA: 202,599 images and 10,177 subjects, 5 landmark locations, 40 binary attributes [Download]
   5. MegaFace: 1 Million Faces for Recognition at Scale, 690,572 subjects [Download]
   6. VGG-Face2: A large-scale face dataset contains 3.31 million imaes of 9131 identities. [Download]

Libraries

1. Deep Learning:
   1. MXNet and Gluon: A flexible and efficient library for deep learning.
   2. Torch and PyTorch: Tensors and Dynamic neural networks in Python with strong GPU acceleration.
   3. TensorFlow: An open-source software library for Machine Intelligence.
   4. Caffe and Caffe2: A lightweight, modular, and scalable deep learning framework.
2. Machine Learning:
   1. Dlib: A machine learning toolkit.
3. Computer Vision:
   1. OpenCV: Open Source Computer Vision Library.
4. Probabilistic Programming
   1. Pyro: Deep universal probabilistic programming with Python and PyTorch