Grassmann discriminant analysis: a unifying view on subspace-based learning

By Jihun Ham, Daniel D. Lee. 2008

686 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Representation & Self-Supervised Learning, Statistical Learning Theory

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 Media Technology

In Representation & Self-Supervised Learning

In Statistical Learning Theory

Citations in the corpus

Covariance discriminative learning: A natural and efficient approach to image set classification (2012, methodology): “1.1, one class of conventional set classification methods is based on linear subspace modeling and learning [8], [12], [13], [26], [27], [30].”
Grassmannian Sparse Representations and Motion Depth Surfaces for 3D Action Recognition (2013, methodology): “[21] J. M. Lee, "Introduction to smooth manifolds," in Springer, 2002.”
A Comprehensive Look at Coding Techniques on Riemannian Manifolds (2018, methodology): “More specifically, we employ the Stein [32] and Jeffrey [39] divergences on the SPD manifold and the projection distance [16] on Grassmannian to obtain new variants of our solution.”
Generalized Rank Pooling for Activity Recognition (2017, methodology): “Unless otherwise specified, we use the projection metric kernel [19] for classifying the subspaces on the Grassmannian.”
Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification (2015, methodology): “For GDA, the dimensionality of Grassmann manifold is set to 10.”
Domain adaptation for object recognition: An unsupervised approach (2011, neutral): “[37, 21, 28, 22].”
A Blur-Robust Descriptor with Applications to Face Recognition (2012, methodology): “pursued the method of Hamm and Lee [15] that performs kernel”
Visual Domain Adaptation with Manifold Embedded Distribution Alignment (2018, methodology): “ . 3.3 Manifold Feature Learning Manifold feature learning serves as the preprocessing step to eliminate the threat of degenerated feature transformation. MEDA learns g„”in the Grassmann manifold G„d”[18] since features in the manifold have some geometrical structures [5, 18] that can avoid distorti”
Deep Reconstruction Models for Image Set Classification (2015, neutral): “Recommended for acceptance by A. Vedaldi.”
Geodesic flow kernel for unsupervised domain adaptation (2012, background): “sinαd or sinβd is called the minimum correlation distance [16].”
Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching (2011, methodology): “A convenient way of dealing with subspaces is to represent them as points on Grassmannian manifolds [11, 13, 19, 25].”
Building Deep Networks on Grassmann Manifolds (2016, background): “(4) In the context of ConvNets, (Cybenko 1989; Jarrett et al. 2009; Nair and Hinton 2010; Goodfellow et al. 2013; He et al. 2015) have presented various nonlinear activation 3A PSD manifold PSD(dk, dk−1) is the set of dk-rank positive semidefinite matrices of size dk−1 (Bonnabel and Sepulchre 2009;…”
Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification (2018, background): “projection distance [31, 32] of the Grassmann manifold deduces a bilinear feature mapping without explicitly computing the bilinear feature matrix, which leads to a very compact feature representation.”