Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification

By Zhiwu Huang, Ruiping Wang, Shiguang Shan, Xianqiu Li, Xilin Chen. 2015

264 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Deep Learning on Lie Groups for Skeleton-Based Action Recognition (2016, methodology): “As well-known from classical manifold learning theory [37, 35, 4, 12, 20, 19], one can learn or preserve the original data structure to faithfully maintain geodesic distances for better classiﬁcation.”
Multi-view Harmonized Bilinear Network for 3D Object Recognition (2018, methodology): “Different from matrix-logarithm [12, 11] and improved bilinear pooling [19], we adaptively learn the {λk}k=1 from the data, possessing higher flexibility and modelling ability.”
Building Deep Networks on Grassmann Manifolds (2016, methodology): “More recently, a new learning scheme was proposed by (Huang et al. 2015b) to perform a geometry-aware dimensionality reduction from the original Grassmann manifold to another lower-dimensional, more discriminative Grassmann manifold.”
Probabilistic Face Embeddings (2019, background): “In the field of face template/video matching, there exists abundant literature on modeling the faces as probabilistic distributions [33, 2], subspace [4] or manifolds [2, 12] in the feature space.”
Hierarchical Gaussian Descriptor for Person Re-identification (2016, methodology): “Following the setting of [13], we set the regularization parameter for region Gaussian as G = 0Tr(ΣG).”
A Riemannian Network for SPD Matrix Learning (2016, methodology): “As done in (Huang et al. 2015b), we compute an SPD matrix of size 401 × 401 for each video to fuse its data covariance matrix and mean.”
Distribution Consistency Based Covariance Metric Networks for Few-Shot Learning (2019, background): “…and Meer 2006; 2007; Tabia et al. 2014) or a general representation (Wang et al. 2012; Harandi, Salzmann, and Porikli 2014; Wang et al. 2015b; 2015a; Huang et al. 2015; Wang et al. 2017), due to its favorable properties, e.g. , second-order statistic, symmetric positive-deﬁniteness and so on.”