Overview of the face recognition grand challenge

By P. Jonathon Phillips, Patrick J. Flynn, W. T. Scruggs, Kevin W. Bowyer, Jin Chang, Kevin Hoffman, Joe Marques, Jaesik Min, W. Worek. Computer Vision and Pattern Recognition, 2005

2,782 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4f140022ae2a37b8186b34e690012a58fee0c820

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

A Database and Evaluation Methodology for Optical Flow (2007, background): “Many areas of computer vision, such as stereo [63], face recognition [28, 55, 68], and object recognition [23, 24], have challenging datasets to track the progress made by leading algorithms and to stimulate new ideas.”
Describable Visual Attributes for Face Verification and Image Search (2011, neutral): “0 data set [46] has a limited number of subjects, image acquisition locations, and all images were taken with the same camera type.”
A Semi-automatic Methodology for Facial Landmark Annotation (2013, methodology): “(3) The annotation model of each database consists of different number of landmarks (MultiPIE [5], XM2VTS [9], AR [7] FRGC Ver.2 [10]).”
Hierarchical Ensemble of Global and Local Classifiers for Face Recognition (2009, methodology): “In this sub-section, we formulate weight learning as a discriminant analysis problem, in which the weighted sum can be considered as linear projection from -”
Diagnosing Error in Object Detectors (2012, background): “Studies in specialized domains, such as pedestrian detection [20] and face recognition [21, 22], have provided useful insights.”
Global-Local Face Upsampling Network (2016, methodology): “The controlled setting was conducted using Face Recognition Grand Challenge (FRGC) dataset [40], where frontal face images were taken in a studio setting under two lighting conditions with only two facial expressions (smiling and neutral).”
Recognition of blurred faces using Local Phase Quantization (2008, methodology): “The efficiency of the proposed face descriptor in the face recognition scenario was tested using two datasets, the CMU PIE (Pose, Illumination, and Expression) dataset [6] and the Face Recognition Grand Challenge (FRGC) experiment 1.0.4 [5].”
Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis (2020, background): “The covariance matrix is difﬁcult to evaluate in an accurate manner ( Phillips et al., 2005).”
Maximum Correntropy Criterion for Robust Face Recognition (2011, methodology): “FRGC Database [50]: The FRGC version two face database is a challenging benchmark face recognition database.”
Face recognition in unconstrained videos with matched background similarity (2011, background): “• FRVT’s successor, the Face Recognition Grand Challenge (FRGC) images and benchmarks [28, 29], which already consisted of 4000 subjects, and 50,000 recordings.”
Adversarial Attacks on Face Detectors Using Neural Net Based Constrained Optimization (2018, methodology): “W test set [11] [12] [13] [14] [15].”
Eigenfeature Regularization and Extraction in Face Recognition (2008, neutral): “[2].”
Coupled Kernel Embedding for Low-Resolution Face Image Recognition (2012, methodology): “In this section, we randomly select 501 images from the FERET data [35] and train the projection directions using our Gaussian-kernel-based CKE algorithm.”
Image Super-Resolution Via Sparse Representation (2010, methodology): “The experiments are conducted on the face database FRGC Ver 1.0 [ 35 ].”
Understanding OSN-based facial disclosure against face authentication systems (2014, methodology): “Since the accuracy of automatic labeling tools is limited [1, 30], we manually label the OSN images with the help of automatic tools and follow the similar validating methodology used in prior study [21, 17, 41].”
Unconstrained Face Recognition: Identifying a Person of Interest From a Media Collection (2014, neutral): “[9]”