Multilinear image analysis for facial recognition

By M. Alex O. Vasilescu, Demetri Terzopoulos. Object recognition supported by user interaction for service robots, 2002

295 citations recorded by the source corpus.

Subfields: Computational Mathematics, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/069b6fd90506709fd4e7c15963f256d5946c943f

How researchers see this paper

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

In Computational Mathematics

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

RNNs Implicitly Implement Tensor Product Representations (2018, unknown): “For example, in face recognition, eigenfaces (Sirovich & Kirby, 1987; Turk & Pentland, 1991) and TensorFaces (Vasilescu & Terzopoulos, 2002; 2005) use such techniques to disentangle facial features, camera angle, and lighting.”
Tensor-Based Formulation and Nuclear Norm Regularization for Multienergy Computed Tomography (2013, methodology): “As mentioned before, low-rank modeling is an important tool not only for compressing [50] and analyzing [30], [51] large data sets but also for regularization and the incorporation of prior information [9], [52].”
Multilinear Multitask Learning (2013, methodology): “For example (Vasilescu & Terzopoulos, 2002) decompose natural facial images according to four modes: identity, expression, head pose and lighting condition.”
A survey of multilinear subspace learning for tensor data (2011, methodology): “Multilinear analysis of image data is pioneered by the TensorFace method [76, 77], which employs the multilinear algorithms proposed in [30,31] to analyze the factors involved in the formation of facial images.”
Tensor Rank and the Ill-Posedness of the Best Low-Rank Approximation Problem (2006, unknown): “problem for higher order tensors is a problem of central importance in the statistical analysis of multiway data [11, 16, 20, 21, 45, 50, 38, 56, 65, 66, 74, 75, 76].”
Factorization strategies for third-order tensors (2011, methodology): “Applications involving operations with tensors include chemometrics [41], psychometrics [24], signal processing [9] [27] [39], computer vision [44] [46] [45], data mining [1] [38], graph analysis [21], neuroscience [3] [30] [31], and many more.”
Human gesture recognition on product manifolds (2012, methodology): “Tensor computing has been successfully applied to many computer vision applications such as face recognition (Vasilescu and Terzopoulos, 2002), visual tracking (Li et al., 2007), and action classification (Vasilescu, 2002; Kim and Cipolla, 2009).”
Most Tensor Problems Are NP-Hard (2009, methodology): “…2005], computational biology [Cartwright et al. 2009], computer graphics [Vasilescu and Terzopoulos 2004], computer vision [Shashua and Hazan 2005; Vasilescu and Terzopoulos 2002], data analysis [Coppi and Bolasco 1989], graph theory [Friedman 1991; Friedman and Wigderson 1995], neuroimaging…”
Hallucinating face by position-patch (2010, methodology): “Multilinear analysis [22,23] can be employed to model the correlation between two spaces with different modalities.”
Tucker Dimensionality Reduction of Three-Dimensional Arrays in Linear Time (2008, background): “One can mention signal processing, statistics [3, 1, 4], chemometrics [5], face recognition [7], solving multidimensional integral and differential equations [6](a very comprehensive list of references on the subject can be found on a Three-mode company web site, [2]).”
A New Truncation Strategy for the Higher-Order Singular Value Decomposition (2012, methodology): “Applications of such a compressed representation are described in [59, 60, 61], where similar data sets are used.”
Tensor Decompositions and Applications (2009, background): “Alternatively, the k th frontal slice of a third-order tensor, X :: k , may be denoted more compactly as X k .”
Appearance-based face recognition and light-fields (2004, background): “sentation that separates the different modes underlying the formation of face images such as pose, illumination and expression [ 29 ].”