Similarity Learning with Spatial Constraints for Person Re-identification

By Dapeng Chen, Zejian Yuan, Badong Chen, Nanning Zheng. Computer Vision and Pattern Recognition, 2016

353 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e46da6432f028c25780f004ab1182c647f9ef655

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. Shiliang Zhang
5. Wanli Ouyang
6. Tao A. Xiang
7. Shaogang Gong
8. Wen Gao

In Computer Vision and Pattern Recognition

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

Citations in the corpus

• Unsupervised Person Re-identification (2017, background): “Liao et al. [37] propose the local maximal occurrence (LOMO) descriptor, which includes the color and SILTP histograms.”
• Attention-Aware Compositional Network for Person Re-identification (2018, background): “The first category mainly includes the traditional feature descriptors [53, 52, 51, 27, 7, 31, 35] and deep learning features [43, 41, 42, 12, 25, 40].”
• Person Re-Identification by Camera Correlation Aware Feature Augmentation (2017, neutral): “Ensemble [14], DNS [39], SCSP [40], and so forth.”
• Gated Siamese Convolutional Neural Network Architecture for Human Re-identification (2016, neutral): “SCSP [3] 53.”
• Complementary Relation Contrastive Distillation (2021, background): “There are a few recent works analyzing and exploiting the mutual relation between data samples [28, 34, 32, 33, 6, 5, 7, 25].”
• Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion (2017, methodology): “The proposed Spindle Net is compared with several state-of-the-art ReID approaches in recent two years, including the metric learning method WARCA-χ2 [11], the null space semi-supervised learning method NFST [32], the deep neural network PersonNet [28], the Siamese CNN with learnable gate S-CNN [25]”
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval (2017, methodology): “In the comparison, the metric learning based methods include Bow+Kissme [44], WARCA [15], LOMO+XQDA [18], Null Space [41], SCSP [4].”
• Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification (2017, background): “Other approaches handle the problem of pose variability by explicitly accounting for spatial constraints of the human body parts [12,97,39,96] or by predicting the pose from video [16,72].”
• Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification (2017, background): “Many hand-crafted features are proposed to capture visual features for pedestrians [1,5,6,12,16,28].”
• Deep Representation Learning With Part Loss for Person Re-Identification (2017, result): “, DeepReID [19], LSTM Siamese [35], and Gated Siamese [21], but is lower than some of existing methods [27], [51], [22].”
• SVDNet for Pedestrian Retrieval (2017, neutral): “1 SCSP[4] 51.”
• Random Erasing Data Augmentation (2017, neutral): “Rank 1 mAP BOW [32] 34.40 14.09 LOMO + XQDA [16] 43.79 22.22 WARCA [10] 45.16 - HistLBP+kLFDA [12] 46.50 - SCSP [2] 51.90 26.35 DNS [31] 61.02 35.68 Gated [22] 65.88 39.55 Re-rank [36] 77.11 63.63 SVDNet [21] 82.3 62.1 GAN [35] 83.97 66.07 APR [17] 84.29 69.14 PAN [34] 82.81 63.35 TriNet [8] 84.92…”