Locally Linear Regression for Pose-Invariant Face Recognition

By Xiujuan Chai, Shiguang Shan, Xilin Chen, Wen Gao. IEEE Transactions on Image Processing, 2007

305 citations recorded by the source corpus.

How researchers see this paper

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

Disentangled Representation Learning GAN for Pose-Invariant Face Recognition (2017, background): “However, Pose-Invariant Face Recognition (PIFR) is far from solved [2, 8, 21, 22].”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, methodology): “Another type of 2D methods tries to learn the appearance transformations between different poses, such as Local Linear Regression [18] and Tied Factor [39].”
Linear Regression for Face Recognition (2010, background): “In [10], the concept of Locally Linear Regression (LLR) is introduced specifically to tackle the problem of pose.”
Recognizing Rotated Faces From Frontal and Side Views: An Approach Toward Effective Use of Mugshot Databases (2008, methodology): “Two-dimensional techniques [5], [10], [14], [34], [48], [60] and 3-D approaches [7], [11], [22], [30] were used to predict the appearance of a human face”
Face recognition across pose: A review (2009, methodology): “parameter manipulation [32], TFA [63], LLR [19], composite deformable model [48], view-based AAM [25,68], linear”
A Comprehensive Survey on Pose-Invariant Face Recognition (2015, methodology): “Inspite of its simplicity, LLR suffers from the overﬁtting problem in Eq.”