PCCA: A new approach for distance learning from sparse pairwise constraints

By Alexis Mignon, Frédéric Jurie. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

649 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c12c1d0979383a17a0a6f002bfb31ad86fbe61a1

How researchers see this paper

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

In Biomedical Engineering

1. Yi Yang
2. Liang Zheng
3. Qi Tian
4. Shaogang Gong
5. Xiaogang Wang
6. Tao A. Xiang
7. Zhedong Zheng
8. Xiatian Zhu

In Computer Vision and Pattern Recognition

1. Yi Yang
2. Xiaogang Wang
3. Luc Van Gool
4. Dacheng Tao
5. Liang Zheng
6. Qi Tian
7. Wanli Ouyang
8. Ming-Hsuan Yang

Citations in the corpus

• Partial Person Re-Identification (2015, background): “To address these challenges, most of recent works can be categorised into two groups: methods that extract invariant and discriminant features [5, 30, 4, 10, 20, 38, 14] and methods that learn robust metrics or subspace for matching [5, 9, 26, 42, 22, 27, 25, 15, 37, 36, 33, 21, 18].”
• Discriminative Deep Metric Learning for Face Verification in the Wild (2014, methodology): “where g(z) = 1 β log ( 1+exp(βz) ) is the generalized logistic loss function [25], which is a smoothed approximation of the hinge loss function [z]+ = max(z, 0), β is a sharpness parameter, ‖A‖F represents the Frobenius norm of the matrix A, and λ is a regularization parameter.”
• Large-Scale Metric Learning: A Voyage From Shallow to Deep (2018, methodology): “For example, in the spirit of PCCA, a two-layer discriminative network for face verification is proposed in [15].”
• Person Re-Identification by Camera Correlation Aware Feature Augmentation (2017, background): “[13], PCCA [6], LFDA [10], XQDA [12], PSD[15], Metric”
• Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification (2017, background): “As such, there is vast literature in learning discriminative distance metrics [35,42,105,51,55,77,43,61,53,19,48,108,91,5] and discriminant subspaces [63,47,107,84,43,46,64,94,15].”
• Similarity Learning with Spatial Constraints for Person Re-identification (2016, background): “The former type adopts the offthe-shelf distance metric such as Euclidean distance [10], Bhattacharyya distance[6], and covariance distance [22, 1], while the latter type tries to exploit the inherent invariance between image pairs [12, 27, 13, 24].”
• Person re-identification by Local Maximal Occurrence representation and metric learning (2014, neutral): “28 2012 CVPR [35] WELF6+PRDC 16.”
• Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification (2015, neutral): “28 2012 CVPR [20] PRDC 15.”
• Discriminative Autoencoders for Small Targets Detection (2014, methodology): “In practice, we use the slightly different version of the standard hinge loss, as proposed by [35] – the standard one should be Ld = ∑ x∈χ+∪χ− max(0, 1−t(x) · e(x)) – more adapted to our problem as the reconstruction errors are all positive.”
• An improved deep learning architecture for person re-identification (2015, methodology): “In addition to the methods listed in section 7.2 and 7.1, we compare our method against local Fisher discriminant analysis (LF) [23], PCCA [22], aPRDC [18], PRDC [32], eBiCov [19], LMNNR [1], PRSVM [2], and ELF [7].”
• Person Re-identification by Multi-Channel Parts-Based CNN with Improved Triplet Loss Function (2016, neutral): “0 PCCA[30] 19.”
• Learning a Discriminative Null Space for Person Re-identification (2016, background): “Apart from a few exceptions [12, 31] based on ranking or boosting, the second groups of methods can be further divided into two major sub-groups: those on learning distance metrics [17, 44, 28, 33] and those on learning discriminative subspaces [30, 24, 36, 22].”
• Distilled Person Re-Identification: Towards a More Scalable System (2019, background): “Person Reidentification has witnessed a fast growing development in recent years, from feature design [19, 15, 32, 31, 35, 69, 58] to distance metric learning [54, 19, 43, 25, 67, 36, 41, 30, 58, 33, 38, 31, 9, 68, 60, 63, 69, 29, 52, 6] and end-to-end deep learning [28, 1, 55, 57, 49, 22, 64, 65, 7”
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks (2016, methodology): “[16] proposed Pairwise Pairwise Constrained Component Analysis (PCCA) to learn a projection into a low dimensional space in which the distance between pairs of samples respects the desired constraints, exhibiting good generalization properties in the presence of high dimensional data.”
• Recurrent Attention Models for Depth-Based Person Identification (2016, background): “There have been many attempts to solve this problem by improving the feature representations [24, 68, 22, 78, 79, 37, 80] and by exploring new similarity metrics [40, 49, 60].”
• Person Re-identification by Salience Matching (2013, methodology): “PRDC [23], LMNNR [4], PCCA [18], and attribute-based PRDC (aPRDC) [13], a boosting approach (ELF) [8] and Rank SVM (RankSVM) [19].”