The CMU Pose, Illumination, and Expression (PIE) database

By Terence Sim, Simon Baker, Maan Bsat. 2002

1,798 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks

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 Evaluation & Benchmarks

Citations in the corpus

FaceNet: A unified embedding for face recognition and clustering (2015, background): “Shown are image pairs from PIE [13] that previously were considered to be very difficult for face verification systems.”
Joint Unsupervised Learning of Deep Representations and Image Clusters (2016, positive): “Interestingly, we achieved perfect results (NMI = 1) on COIL20 and CMU-PIE datasets, which means that all samples in the same category are clustered into the same group.”
Matrix Coherence and the Nystrom Method (2010, background): “Equations (12) and (14) further reduce Dataset Type of data # Points ( n ) # Features ( d ) Kernel PIE (Sim et al. , 2002) face images 2731 2304 linear MNIST (LeCun and Cortes, 1998) digit images 4000 784 linear Essential (Gustafson et al. , 2006) proteins 4728 16 RBF Abalone (Asuncion and Newman,…”
Face recognition using Histograms of Oriented Gradients (2011, methodology): “The experimental results were evaluated using four face databases: FERET (Phillips et al., 2000), AR (Martinez and Benavente, 1998), CMU Multi-PIE (Sim et al., 2001) and Yale ( Yale face database , 2009).”
FaceTracer: A Search Engine for Large Collections of Images with Faces (2008, background): “In contrast, existing face datasets such as Yale Face A&B [16], CMU PIE [17], and FERET [6] are either much smaller in size and/or taken in highly controlled settings.”
Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization (2017, neutral): “CMU-PIE: A dataset including 32 by 32 face images of 68 people with 4 different expressions [40].”
Acquiring linear subspaces for face recognition under variable lighting (2005, background): “A more recent database designed for similar purposes is the PIE database from CMU (see [18]).”
A Comprehensive Survey to Face Hallucination (2013, methodology): “2000), PIE (Sim et al. 2002) BI(GP) VP N/A”
Sampling Methods for the Nyström Method (2012, neutral): “Table 1: Description of the datasets and kernels used in fixed and adaptive sampling experiments (Sim et al., 2002; LeCun and Cortes, 1998; Gustafson et al., 2006; Asuncion and Newman, 2007 ).”
Maximum Margin Correlation Filter: A New Approach for Localization and Classification (2013, neutral): “of the CMU PIE database [39] with images that have been captured over multiple sessions (maximum of 5 sessions).”
Utility data annotation with Amazon Mechanical Turk (2008, background): “It is obvious from this figure that hips are much more difficult to localize compared to shoulders, knees, elbows, wrists, ankles, the head and the neck.”
Studying Very Low Resolution Recognition Using Deep Networks (2016, background): “Dataset Although many face image datasets, such as LFW [13], SCface [11], and CMU-PIE [27], have been developed, most of them were collected in controlled indoor environments with limited variability.”