Video-based face recognition using probabilistic appearance manifolds

By Kuang-chih Lee, Jeffrey Ho, Ming-Hsuan Yang, David J. Kriegman. 2003

540 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

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

In Signal Processing

Citations in the corpus

SphereFace: Deep Hypersphere Embedding for Face Recognition (2017, background): “A-Softmax loss can be interpreted as constraining learned features to be discriminative on a hypersphere manifold, which intrinsically matches the prior that face images lie on a manifold [14, 5, 31].”
Neural Aggregation Network for Video Face Recognition (2016, methodology): “For set based face recognition, many previous methods have attempted to represent the set of face images with appearance subspaces or manifolds and perform recognition via computing manifold similarity or distance [19, 2, 17, 40, 37].”
Unsupervised Learning of Image Manifolds by Semidefinite Programming (2004, background): “The problem arises often in computer vision and pattern recognition ( Lee et al., 2003; Pless, 2004; Elgammal & Lee, 2004; Souvenir & Pless, 2005).”
Multi-manifold deep metric learning for image set classification (2015, methodology): “There have been a variety of studies on image set clas-siﬁcation over the past decade [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 15, 16, 18, 22, 24, 26, 27, 28, 29, 34, 35, 36, 37, 38, 39, 40], and signiﬁcant progresses have been made in recent years [3, 4, 5, 11, 26, 27, 35, 37, 39, 40].”
A 3D Face Model for Pose and Illumination Invariant Face Recognition (2009, background): “Numerous face recognition articles acknowledge the fact that 3DMM based face image analysis constitutes the state of the art, but note that the main obstacle resides in the complications of their construction (e.g. [22] [13] [12] [5]).”
KinectFaceDB: A Kinect Database for Face Recognition (2014, background): “be used for multiple purposes ranging from the video-based face recognition using either 2-D [65]–[68] or 3-D [30], [69], to the dense face model reconstruction [70] from 3-D frames.”
Face recognition using Laplacianfaces (2005, background): “Recently, a number of research efforts have shown that the face images possibly reside on a nonlinear submanifold [7], [10], [18], [19], [21], [23], [27].”
Locality Preserving Projections (2003, background): “Recently, a number of research efforts have shown that the face images possibly reside on a nonlinear sub-manifold [16] [47] [61] [62][65] [2] [71].”
From sample similarity to ensemble similarity: probabilistic distance measures in reproducing kernel Hilbert space (2006, methodology): “The face images of size 16 16 are obtained by automatically cropping from video sequences (courtesy of [38]) using an in-house flow tracking algorithm.”
Face recognition in unconstrained videos with matched background similarity (2011, unknown): “The Honda/UCSD Video Database [23, 22].”
Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based Recognition (2011, background): “Video-based face recognition by modeling the “cropped video” either as dynamical models ([6]) or as a collection of PCA subspaces [46] have recently gained popularity because of their ability to recognize faces from lowresolution videos.”
Face recognition with image sets using manifold density divergence (2005, background): “In [19], Lee et al. approximate face manifolds by a finite number of infinite extent subspaces and use temporal information to robustly estimate the operating part of the manifold .”
A Survey of Face Recognition Techniques (2009, background): “Since it has been shown that face images possibly reside on a nonlinear submanifold [124-130] (especially if there is a perceivable variation in viewpoint, illumination or facial expression), some nonlinear techniques have consequently been proposed to discover the nonlinear structure of the manifol”
Efficient Representation of Low-Dimensional Manifolds using Deep Networks (2016, background): “In many problems, for example face recognition, data lie on or near manifolds that are of much lower dimension than the input space (Turk & Pentland, 1991; Basri & Jacobs, 2003; Lee et al., 2003), and that represent the intrinsic degrees of variation in the data.”
Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction (2014, methodology): “Various methods of dimensionality reduction have been proposed to discover the underlying manifold structure, which plays an important role in many tasks, such as pattern classification [9] and information visualization [16].”
Neighborhood preserving embedding (2005, background): “In recent years, computer vision research has witnessed a growing interest in discovering the manifold of perceptual observation, [6], [7], [13], [11].”
Manifold Discriminant Analysis (2009, methodology): “Honda/UCSD: This database is the benchmark for face recognition based on image sets or video [14], [16], [26], [31].”