Face Alignment by Explicit Shape Regression

By Xudong Cao, Yichen Wei, Fang Wen. 2012

1,253 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Cascade R-CNN: High Quality Object Detection and Instance Segmentation (2019, background): “However, as is commonly done for pose regression [9] or face alignment [4], [57], [58], the regression task can be decomposed into a sequence of simpler steps.”
Cascade R-CNN: Delving Into High Quality Object Detection (2017, methodology): “The difficult regression task can be decomposed into a sequence of simpler steps, inspired by the works of cascade pose regression [6] and face alignment [2, 35].”
Mirror, mirror on the wall, tell me, is the error small? (2015, background): “To address this problem, [5] proposed to use several random initializations and give the final estimate as the median of the solutions to which they convergence.”
Automatic Analysis of Facial Actions: A Survey (2019, background): “Initially proposed by [24], [25], much of the popularity of regression-based approaches is due to the Supervised Descent Method (SDM) [203].”
Supervised Descent Method and Its Applications to Face Alignment (2013, methodology): “Recent work on boosted regression [27, 29, 15, 10] learns a set of weak regressors to model the relation between φ and ∆x.”
Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection (2019, methodology): “Supervised facial landmark detection algorithms can be categorized into linear regression based methods [44, 7] and heatmap regression based methods [41, 11, 9, 30].”
The face of art (2019, methodology): “A common approach for facial landmark detection is to learn a regression model for feature positions [Cao et al. 2014; Lv et al. 2017; Xiong and la Torre 2013].”
Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting (2016, methodology): “Recently, face alignment works are very popular in top vision venues, as demonstrated by the progress in Constrained Local Model based approaches [5, 22], AAM-based approaches [15, 13, 14] and regressionbased approaches [27, 4, 33].”
Incremental Face Alignment in the Wild (2014, methodology): “Recently, a number of discriminative methodologies have shown excellent results for facial landmark localization [4, 2, 32].”
Learn to Combine Multiple Hypotheses for Accurate Face Alignment (2013, background): “[2] extended the work for face alignment task and achieve very promising result on face alignment task.”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, background): “Benefit from the current breakthrough of face alignment algorithm [47, 16], robustly detecting face landmarks in unconstrained environment has become possible.”
An All-In-One Convolutional Neural Network for Face Analysis (2016, background): “Existing methods for landmark localization have focused mainly on near-frontal faces [2], [38], [22] where all the essential keypoints are visible.”
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors (2018, methodology): “Though image-based facial landmark detectors [8, 19, 37, 38, 3, 20] can achieve very good performance on images, sequentially running these detectors on each frame of a video in a tracking-by-detection fashion usually leads to jittering and unstable detections.”
UMDFaces: An annotated face dataset for training deep networks (2016, background): “The NME(%) of face alignment results on AFLW test set for various poses (frontal ([0-30]) to profile ([60-90])).”