Person Re-Identification Using Kernel-Based Metric Learning Methods

By Fei Xiong, Mengran Gou, Octavia I. Camps, Mario Sznaier. European Conference on Computer Vision, 2014

686 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3495faa862e53d1d82eb703216e1003763341666

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

In Computer Vision and Pattern Recognition

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

Citations in the corpus

• MARS: A Video Benchmark for Large-Scale Person Re-Identification (2016, background): “, HistLBP [39], gBiCov [27], LOMO [24], BoW [43], and SDALF [10].”
• Deep Transfer Learning for Person Re-Identification (2016, background): “Earlier works focus on either designing viewinsensitive feature representations [2], [3], or learning an effective distance metric [4], [5], or both [6].”
• Multi-scale Deep Learning Architectures for Person Re-identification (2017, background): “Typically, person re-id is formulated only as a verification task [24, 32, 57, 59].”
• Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification (2016, methodology): “There have been many kinds of hand-crafted features used for person re-identification, including local binary patterns (LBP) [36, 16], color histogram [16] and local maximal occurrence (LOMO) [21, 22].”
• Multi-Task Learning with Low Rank Attribute Embedding for Multi-Camera Person Re-Identification (2018, methodology): “We compare our algorithm with 11 supervised learning-based methods: Relaxed Pairwise Metric Learning (RPML) [8], Probabilistic Relative Distance Comparison (PRDC) [15], RankSVM (RSVM) [71], Salmatch [69], LMF [30], Pairwise Constrained Component Analysis (PCCA) [7], regularized PCCA (rPCCA) [12], Ke”
• Person Re-Identification by Deep Joint Learning of Multi-Loss Classification (2017, neutral): “…, 2013; Zhao et al. , 2013; Liao et al. , 2015; Matsukawa et al. , 2016a; Ma et al. , 2017] or matching distance metrics [Koestinger et al. , 2012; Xiong et al. , 2014; Zheng et al. , 2013; Wang et al. , 2014b; Paisitkri-angkrai et al. , 2015; Zhang et al. , 2016; Wang et al. , 2016b; Wang et al.…”
• Person Re-identification in the Wild (2016, methodology): “For example, IDEdet exceeds “HistLBP+DNS” by +6.2% in mAP when on average 3 bounding boxes are detected per image.”
• Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification (2018, background): “For example, in [2, 20, 29, 47, 56, 51, 54, 64, 70, 21], hand-crafted lo-cal features are integrated into a feature vector, and distance metric is learned by simultaneously maximizing inter-class margins and minimizing intra-class variations.”
• Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification (2018, methodology): “Most existing re-id studies follow the supervised learning paradigm such as optimising pairwise matching distance metrics [20, 52, 57, 49, 54, 47, 50, 5] or deep learning methods [27, 45, 51, 44, 4, 28].”
• Jointly Attentive Spatial-Temporal Pooling Networks for Video-Based Person Re-identification (2017, methodology): “tation learning [11, 19, 15, 38], distance metric learning [14, 41, 30, 36, 37, 21] and CNN-based schemes [33, 32, 24, 25].”