Symmetry-driven accumulation of local features for human characterization and re-identification

By Loris Bazzani, Marco Cristani, Vittorio Murino. Computer Vision and Image Understanding, 2013

326 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7ac27a7be0b0ab8c3178fa6053ea46de8542634f

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

Citations in the corpus

• A survey of approaches and trends in person re-identification (2014, unknown): “Current work in person Re-ID Re-ID has been a topic of intense research in the past five years [13] [14] [15] [16] [17].”
• Person Re-Identification Using Kernel-Based Metric Learning Methods (2014, result): “For sake of completeness, we also compared the best performance for the proposed algorithms against the best results as reported in the existing literature (even though as pointed above, the values reported elsewhere do not use the same set of features or experimental protocol) [1, 2, 6, 11,16–21,28”
• Saliency Weighted Features for Person Re-identification (2014, methodology): “We show our superior performance to state-of-the-art approaches: SDALF [6], TML [29], PatMatch [51] and SalMatch [51].”
• Generalizing a Person Retrieval Model Hetero- and Homogeneously (2018, methodology): “Hand-craft features can be directly applied for unsupervised person re-ID, for example, ELF [21], LOMO [22], and SDALF [23], which aim to design or learn robust feature for person re-ID.”
• Person re-identification by Local Maximal Occurrence representation and metric learning (2014, methodology): “, LOMO+XQDA 34.30%, Mid−level Filter 28.45%, SalMatch 20.00%, GenericMetric 19.67%, eSDC 15.98%, ITML 13.45%, LMNN 10.33%, L1−norm 9.90%, SDALF 9.84%, L2−norm Figure 8.”
• Hierarchical Gaussian Descriptor for Person Re-identification (2016, methodology): “Considering other methods which require more computational cost [6, 45, 47], the running time of the GOG descriptor is still appealing.”
• Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification (2015, background): “There are many other approaches beyond metric learning for person re-identification, such as the ensemble of local features (ELF) [6], SDALF [1], RankSVM [23], kBiCov [18], salience match [30], mid-level filter [32], local fisher discriminant analysis (LF) [22], to name a few.”
• Hierarchical Clustering With Hard-Batch Triplet Loss for Person Re-Identification (2019, background): “In the past, people tend to use traditional manual features [1, 13] to conduct unsupervised domain adaptation, but the performance on large datasets is usually poor.”