Coarse-to-Fine Auto-Encoder Networks (CFAN) for Real-Time Face Alignment

By Jie Zhang, Shiguang Shan, Meina Kan, Xilin Chen. European Conference on Computer Vision, 2014

545 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/581f5c2e00aaa19942355ef99ecd46bcff55be08

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting (2016, methodology): “Figure 2 shows the overall process of the proposed method.”
Face Alignment in Full Pose Range: A 3D Total Solution (2015, background): “Cascaded Linear Regression [11] and traditional nonlinear models [10], [16] are not flexible enough to cover these complex variations in a unified way.”
Facial Landmark Detection: A Literature Survey (2018, methodology): “In [118], the deep auto-encoder model is used to perform the same cascaded landmark search.”
Deep learning for visual understanding (2017, unknown): “[104], and is still extensively studied in recent papers [105, 106].”
OpenFace 2.0: Facial Behavior Analysis Toolkit (2018, methodology): “CFAN [77] — Coarse-to-Fine Auto-encoder Network, uses cascaded regression on auto-encoder visual features.”
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks (2017, methodology): “C V ] 2 3 O ct 2 ing deep neural networks, different network types have been explored, such as the Convolutional Neural Network (CNN) [55], Auto-Encoder Network [73] and Recurrent Neural Network (RNN) [58, 64].”
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression (2019, unknown): “CFANECCV 14 [72] 5.”
A convolutional neural network cascade for face detection (2015, methodology): “Considering the success of CNNs in a number of visual tasks including the face alignment [31], our framework is more general in that we can adopt a CNN-based face alignment method to achieve joint face alignment and detection, and we use CNN to learn more robust features for faces.”
Look at Boundary: A Boundary-Aware Face Alignment Algorithm (2018, unknown): “35 CFAN [69] 5.”
Unsupervised Discovery of Object Landmarks as Structural Representations (2018, methodology): “[77] Jie Zhang, Shiguang Shan, Meina Kan, and Xilin Chen.”
FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors (2017, methodology): “We adopt a popular alignment model CFAN [43] to estimate the landmarks of different recovered images.”
Mnemonic Descent Method: A Recurrent Process Applied for End-to-End Face Alignment (2016, methodology): “Our proposed method is also reminiscent of previously proposed deep learning methods for face alignment [43, 55, 47, 61, 63, 62].”
Style Aggregated Network for Facial Landmark Detection (2018, methodology): “A very typical framework is to construct features to depict the facial appearance and shape information by the convolutional neural networks (ConvNets) or hand-crafted features, and then learn a model, i.e., a regressor, to map the features to the landmark locations [64, 10, 7, 42, 72, 67, 40].”
High-Resolution Representations for Labeling Pixels and Regions (2019, methodology): “CFAN [119] 5.”
Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings (2017, methodology): “Deep learning methods use cascaded CNNs [56], coarse-to-fine autoencoders [70], auxiliary attribute prediction [73, 74], learned deformations [69] and LSTMs [64].”