Principal Manifolds and Probabilistic Subspaces for Visual Recognition

By Baback Moghaddam. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002

347 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/a8caea2199061186c793e473860835bd9b818157

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

1. Dacheng Tao
2. Luc Van Gool
3. Xiaogang Wang
4. Shuicheng Yan
5. Ming-Hsuan Yang
6. Yi Yang
7. Trevor Darrell
8. Xiaoou Tang

In Media Technology

1. Kristen Grauman
2. Trevor Darrell
3. Ramalingam Chellappa
4. Gregory Shakhnarovich
5. Jian Yang
6. Xiaogang Wang
7. Xiaoou Tang
8. Shaohua Kevin Zhou

In Signal Processing

1. Ramalingam Chellappa
2. Xiaoou Tang
3. Xiaogang Wang
4. Shuicheng Yan
5. Ming Li
6. Trevor Darrell
7. Jian Yang
8. Kristen Grauman

Citations in the corpus

• Visual tracking and recognition using appearance-adaptive models in particle filters (2004, methodology): “Modeling appearance changes between probe video frames and g llery images: We adopt the MAP rule developed in [15] for the recognition score pn(Yt|nt, θt).”
• Independent comparative study of PCA, ICA, and LDA on the FERET data set (2005, background): “Moghaddam (2002) states that there is no significant difference.”
• A General Exponential Framework for Dimensionality Reduction (2014, methodology): “Another important subspace method is the Bayesian algorithm using probabilistic subspace [4].”
• Gabor-based kernel PCA with fractional power polynomial models for face recognition (2004, background): “Gabor wavelets model quite well the receptive field profiles of cortical simple cells [12], [13].”
• A unified framework for subspace face recognition (2004, methodology): “Another important subspace method is the Bayesian algorithm using probabilistic subspace [ 8 ], [9].”
• Joint Factor Analysis of Speaker and Session Variability: Theory and Algorithms (2006, result): “(This would be in keeping with the terminology used in the dual eigenspace approach to face recognition [5].)”
• 2D-LDA: A statistical linear discriminant analysis for image matrix (2005, methodology): “Moghaddan (2002) compared the Bayesian subspace method with several PCA-related methods (PCA, ICA, and Kernel PCA).”
• Neighborhood preserving embedding (2005, methodology): “Different pattern classifiers have been applied for face recognition, including nearest-neighbor [14], Bayesian [9], and Support Vector Machines [10], etc.”
• Inferring 3D structure with a statistical image-based shape model (2003, methodology): “A probabilistic interpretation of PCA-based manifolds has been introduced by [9, 17] as well as in [13], where it was applied directly to face images.”
• Probabilistic recognition of human faces from video (2002, methodology): “We then fit a probabilistic subspace density [30] on top of the IPS.”
• Hallucinating face by eigentransformation (2005, background): “Moghaddam [ 21 ] downsampled face images to 12 by 21 pixels and still achieved 95% recognition accuracy on face images from the FERET database.”
• Eigenfeature Regularization and Extraction in Face Recognition (2008, methodology): “Linear subspace analysis has been extensively studied and becomes a popular feature extraction method since the principal component analysis (PCA) [3], Bayesian maximum likelihood (BML) [4],[5],[ 6 ],andlinear discriminant analysis (LDA) [7], [8] were introduced into face recognition.”