Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching

By Mehrtash Harandi, Conrad Sanderson, Sareh Abolahrari Shirazi, Brian C. Lovell. Computer Vision and Pattern Recognition, 2011

308 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/dc1f981ec62d6df08dc836d07cf679d9fbf501ff

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. Luc Van Gool
2. Jiwen Lu
3. G. Wang
4. Dacheng Tao
5. Xilin Chen
6. Jie Zhou
7. Weihong Deng
8. Shiguang Shan

In Media Technology

1. Jiwen Lu
2. Shiguang Shan
3. Zhiwu Huang
4. Xilin Chen
5. G. Wang
6. Ruiping Wang
7. Munawar Hayat
8. Xianqiu Li

Citations in the corpus

• Grassmannian Sparse Representations and Motion Depth Surfaces for 3D Action Recognition (2013, background): “A manifold is a topological space consisting of surfaces embedded in a high dimensional Euclidean space [19].”
• Multi-manifold deep metric learning for image set classification (2015, background): “Image set classification has been an important problem in computer vision in recent years [1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 13, 15, 16, 18, 22, 24, 26, 27, 28, 29, 34, 35, 36, 37, 38, 39, 40], especially when more and more data are easily accessible and multiple images of the same object are easily…”
• Deep Reconstruction Models for Image Set Classification (2015, methodology): “Image set classification methods commonly model the appearance variability information within images of a set on a geometric surface such as an image set modeled by a subspace [4], [15], a combination of subspaces [5], [16], a point on the Grassmannian [8] or Lie Group [10] of Riemannian manifold.”
• Domain adaptation for object recognition: An unsupervised approach (2011, unknown): “[37, 21, 28, 22].”
• Discriminability Distillation in Group Representation Learning (2020, methodology): “To tackle set-to-set face recognition, traditional methods directly estimate the feature similarity among sets of feature vectors [1,23,5].”
• Log-Euclidean Metric Learning on Symmetric Positive Definite Manifold with Application to Image Set Classification (2015, background): “2011; Harandi et al., 2011; Wang et al., 2012; Yang et al., 2013; Zhu et al., 2013; Lu et al., 2013; 2014; Hayat et al., 2014; Mahmood et al., 2014; Huang et al., 2015b; Wang et al., 2015) have been suggested for the problem of image set classification, where each sample either for training or for…”
• Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition (2011, background): “However, many of the recent face recognition algorithms are capable of handling relatively minor variations in both illumination and expression [15, 17, 24, 28], thus these characteristics of the quality assessment method might be more of a feature than a limitation.”
• Building Deep Networks on Grassmann Manifolds (2016, methodology): “As wellstudied in (Edelman, Arias, and Smith 1998; Hamm and Lee. 2008; Hamm and Lee 2009; Harandi et al. 2011; Huang et al. 2015b), the projection metric is one of the most popular Grassmannian metrics, and is able to endow the specific Riemannian manifold with an inner product structure so that the”