Person Re-Identification by Iterative Re-Weighted Sparse Ranking

By Giuseppe Lisanti, Iacopo Masi, Andrew D. Bagdanov, A. del Bimbo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015

321 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/d168c2bd29fcad2083586430dd76f54da69bc8a6

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. Luc Van Gool
4. Xiaogang Wang
5. Dacheng Tao
6. Qi Tian
7. Chunhua Shen
8. Tao A. Xiang

Citations in the corpus

• Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification (2017, methodology): “To directly utilize unlabeled data for RE-ID, several unsupervised RE-ID models [35, 29, 21, 13, 24] have been proposed.”
• Enhancing Person Re-identification in a Self-Trained Subspace (2017, methodology): “An effective feature representation [Matsukawa et al. 2016; Liao et al. 2015; Varior et al. 2016; Lisanti et al. 2015] is critical for person re-ID, which should be robust to complex variations in human appearances from different camera views.”
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks (2016, background): “[32] leverage low-level feature descriptors to approximate the appearance variants in order to discriminate individuals by using sparse linear reconstruction model.”
• Multi-scale Deep Learning Architectures for Person Re-identification (2017, background): “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].”
• Learning a Discriminative Null Space for Person Re-identification (2016, background): “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].”
• A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification (2019, methodology): “Traditional unsupervised methods focus on hand-crafted features (Farenzena et al. 2010; Liao et al. 2015; Lisanti et al. 2015), salience analysis (Zhao, Ouyang, and 2013; Wang, Gong, and Xiang 2014) and dictionary learning (Kodirov, Xiang, and Gong 2015).”
• Person Re-identification: Past, Present and Future (2016, methodology): “This dataset is relatively easy and the re-ID accuracy of the multi-shot scenario is nearly 100% [124].”
• Scalable Person Re-identification on Supervised Smoothed Manifold (2017, background): “Current research interests can be coarsely divided into two mainstreams: 1) those focus on designing robust visual descriptors [55, 13, 37, 26, 64] to accurately model the appearance of person; 2) those seek for a discriminative metric [65, 25, 54, 28, 18], under which instances of the same identity”
• Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification (2017, methodology): “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].”
• Unsupervised Cross-Dataset Transfer Learning for Person Re-identification (2016, methodology): “From these results, it is evident that: (1) Compared with existing unsupervised methods including SDALF, eSDC, GTS and ISR, our model is significantly better.”
• 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].”
• Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification (2018, methodology): “Dictionary Learning based methods DLLR [21], graphlearning-based model GL [20], sparse representation learning methods ISR [34], salience-learning-based GTS [51] and SDC[61].”