Learning Locally-Adaptive Decision Functions for Person Verification

By Z. Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith. 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

528 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3e9ab40e6e23f09d16c852b74d40264067ac6abc

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

Citations in the corpus

• Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification (2015, methodology): “Method KISSME LDML XQDA ITML MLAPG LADF LMNN PRDC Training Time 1.3 1.4 1.9 19.3 25.1 29.2 141.3 356.3 MEX Function No Yes No No No Yes Yes No dimensions the performance is almost comparable to other larger dimensions.”
• Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification (2016, methodology): “The proposed method performs better than most of the other competing methods except mFilter [42]+LADF [20], which is the combination of two methods.”
• Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification (2017, background): “They are mainly based on learning distance metrics or subspace [38, 14, 18, 22, 19, 20, 26], learning view-invariant and discriminative features [33, 23, 19], and deep learning frameworks [1, 32, 28, 27].”
• Learning a Discriminative Null Space for Person Re-identification (2016, methodology): “Therefore, the second group of methods focus on learning robust and discriminative distance metrics or subspaces for matching people across views [12, 17, 31, 44, 28, 33, 30, 21, 40, 39, 36, 27, 24, 23, 22, 29].”
• 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”
• Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification (2018, background): “…usually describes each pedestrian image or video footage with a single feature vector firstly and then match them in a task-specific metric space, where the feature vectors of same pedestrian are expected to have smaller dis-( tances than that of different pedestrians, e.g ., [20, 34, 21, 64, 54].”
• Person Re-Identification by Camera Correlation Aware Feature Augmentation (2017, methodology): “[8], [9], [10], [11], [12], [13], [14], [15], [16], [17], [18], [19], [20], [21].”
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks (2016, methodology): “Many metric leanring algorithms are proposed for this purpose [6], [8], [9], [13]–[17].”
• Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification (2017, unknown): “[7, 10, 18, 19, 22, 27, 41–43, 50, 51], or learning an effective distance metric [2, 16, 21, 22, 29, 47, 57].”
• Gated Siamese Convolutional Neural Network Architecture for Human Re-identification (2016, methodology): “Several Metric Learning algorithms such as Locally adaptive Decision Functions (LADF) [23], Cross-view Quadratic Discriminant Analysis (XQDA) [24], Metric Learning with Accelerated Proximal Gradient (MLAPG) [25], Local Fisher Discriminant Analysis (LFDA) [32] and its kernel variant (k-LFDA) [49] wer”
• Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification (2017, methodology): “In the meantime, metric learning methods such as large margin nearest neighbor (LMNN) [29], Ma-halanobis distance metric (RCA) [2], Locally Adaptive Decision Function (LADF) [13] and RankSVM [38] have also been applied to person re-id task.”
• Quality Aware Network for Set to Set Recognition (2017, unknown): “0 LADF [21] 47.”
• ABD-Net: Attentive but Diverse Person Re-Identification (2019, background): “Person Re-ID has two key steps: obtaining a feature embedding and performing matching under some distance metric [16, 17, 18].”
• Multi-scale Deep Learning Architectures for Person Re-identification (2017, methodology): “They focus on either designing cross-view robust features [7, 13, 26, 62, 32], or learning robust distance metrics [31, 33, 63, 25, 49, 60, 38, 32], or both [24, 32, 57, 59].”