Multi-View Discriminant Analysis

By Meina Kan, Shiguang Shan, Haihong Zhang, Shihong Lao, Xilin Chen. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012

702 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ae5b1b14fec3633d249bb4d49611ffd1f7d04a4d

How researchers see this paper

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

In Computational Mechanics

1. Jiwen Lu
2. Tien-Ping Tan
3. Dacheng Tao
4. Ran He
5. Chunhong Pan
6. Shiming Xiang
7. Venice Erin Liong
8. Zhenan Sun

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Jiwen Lu
3. Jie Zhou
4. Ran He
5. Yi Yang
6. Xiaogang Wang
7. Luc Van Gool
8. Zhenan Sun

Citations in the corpus

• A Comprehensive Survey on Pose-Invariant Face Recognition (2015, methodology): “For example, the MATLAB implementation of the MvDA approach [Kan et al. 2012] takes about 120 s for model training on an Intel Core i5 CPU @ 2.6 GHz, with training data whose dimension is 600 from 4,347 images of seven poses.”
• Cross-Modal Similarity Learning: A Low Rank Bilinear Formulation (2014, methodology): “The proposed formulation is introduced and derived to find the solution detailed in the next part.”
• Methodologies for Cross-Domain Data Fusion: An Overview (2015, background): “[33] is developed to find informative projections with label information.”
• Scalable Deep Multimodal Learning for Cross-Modal Retrieval (2019, methodology): “With the well-known Fisher’s criterion, some approaches attempt to learn common discriminative features from multiple modalities by maximizing the between-class variations and simultaneously minimizing the within-class variations [11, 12, 35].”
• Learning Compact Binary Face Descriptor for Face Recognition (2015, background): “While binary features have been proven to very successful in face recognition [26], most existing binary face descriptors are all hand-crafted (e.g., LBP and its extensions) and they suffer from the following limitations: 1) It is generally impossible to sample large size neighborhoods for…”
• Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition (2017, methodology): “A multi-view discriminant analysis [45] and mutual component analysis [46] were further devel-”
• Learning Consistent Feature Representation for Cross-Modal Multimedia Retrieval (2015, methodology): “In the computer vision and the multimedia research field, the cross-modal learning and matching have many applications, such as the heterogeneity face recognition [13], [16], [19], [32], image labeling [35], [36], [47], image retrieval [9], [10], [12], [33], attribute based classification tasks [8],”
• Multi-view learning overview: Recent progress and new challenges (2017, methodology): “While GMvDA requires setting hyper-parameters for regularization, multi-view discriminant analysis (MvDA) [51] provides more direct derivation from LDA for multiple view projection matrices without any hyper-parameter.”