Learning a Spatially Smooth Subspace for Face Recognition

By Deng Cai, Xiaofei He, Yuxiao Hu, Jiawei Han, Thomas S. Huang. 2007 IEEE Conference on Computer Vision and Pattern Recognition, 2007

380 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f259d84dda78bcf49ac02299fed36ed2aa76b296

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. Dacheng Tao
3. Ming-Hsuan Yang
4. Yi Yang
5. Xiaogang Wang
6. Andrew Zisserman
7. Andrea Vedaldi
8. Trevor Darrell

In Media Technology

1. Jia Deng
2. G. Wang
3. Mathieu Salzmann
4. Thomas S. Huang
5. Jianchao Yang
6. Kai Yu
7. Cuntai Guan
8. Ian David Reid

Citations in the corpus

• SIFT Flow: Dense Correspondence across Scenes and Its Applications (2011, neutral): “All the motions fields are different, but plausible.”
• Unsupervised K-Means Clustering Algorithm (2020, background): “It has 165 grayscale images in GIF format of 15 individuals [36].”
• Beyond pixels: exploring new representations and applications for motion analysis (2009, background): “performance of SIFT flow and the state-of-the-art [24] for few training samples in Table 4.”
• Supervised translation-invariant sparse coding (2010, methodology): “We use a subset of the database same as in [6, 5] for fair comparison.”
• Discriminative multi-manifold analysis for face recognition from a single training sample per person (2011, background): “Most existing manifold learning algorithms [2, 3, 4, 10, 33] empirically select the optimal feature dimension because there is only one projection matrix to be sought for feature extraction.”
• Deep Subspace Clustering Networks (2017, methodology): “Following [4], we down-sampled the original face images from 112× 92 to 32× 32.”
• Decorrelated Batch Normalization (2018, methodology): “Conditioning Analysis We perform conditioning analysis on the Yale-B dataset [14], specifically, the subset [6] with 2,414 images and 38 classes.”
• Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms (2011, background): “As wT (DG − G)w = ∑ i,j G(i, j)(wi − wj )2 [21], the penalty term P (w) will be large for nonsmooth filters, i.”