Person re-identification by probabilistic relative distance comparison

By Weishi Zheng, Shaogang Gong, Tao A. Xiang. Computer Vision and Pattern Recognition, 2011

747 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1c028833faf11dd565c749741eb97ce811b490de

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

Citations in the corpus

• Adaptive Transfer Network for Cross-Domain Person Re-Identification (2019, neutral): “[20, 38, 43, 36].”
• Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification (2019, background): “We compare VPM with the state-of-the-art methods on two public datasets, i.e., Partial-REID and Partial-iLIDS.”
• Unsupervised Salience Learning for Person Re-identification (2013, methodology): “The compared methods includes the classical metric learning approaches, such as LMNN [29], and ITML [29], and their variants modified for person re-identification, such as PRDC [29], attribute PRDC (denoted as aPRDC) [19], and PCCA [24].”
• Pose-Guided Feature Alignment for Occluded Person Re-Identification (2019, methodology): “Second, previous datasets, either do not focus on solving the occlusion problems [43], or depend on a strong assumption: only probe images are occluded [45, 44].”
• End-to-End Deep Learning for Person Search (2016, background): “…works of person re-identification focus on manually designing discriminative features [35, 11, 37], automatically learning features with convolutional neural networks (CNN) [18, 1], learning feature transforms across camera views [25, 24, 30], and learning distance metrics [40, 10, 26, 23, 21].”
• Person Re-identification by Attributes (2012, background): “These efforts have primarily focused on developing feature representations which are discriminative yet invariant to view angle and lighting [4], and improved learning methods to better discriminate identity [27].”
• Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “To further evaluate our method, we compare the results on Partial-REID and Partial-iLIDS datasets with existing state-of-the-art meth-ods.”
• Human Reidentification with Transferred Metric Learning (2012, methodology): “[4] proposed a Probabilistic Relative Distance Comparison model.”
• Query-adaptive late fusion for image search and person re-identification (2015, background): “Local features are Methods r = 1 r = 5 r = 10 r = 20 PRDC [41] 15.”
• Embedding Deep Metric for Person Re-identification: A Study Against Large Variations (2016, methodology): “We compare our model with IDLA [1], DeepFeature [6], visual word (visWord) [37], saliency matching (SalMatch), patch matching (PatMatch) [39], ELF [8], PRSVM [3], LMNNR [2], eBiCov [21], local Fisher discriminant analysis (LF) [28], PRDC [43], aPRDC [20], PCCA [25], mid-level filters (mFilter) [41] ”
• RGB-Infrared Cross-Modality Person Re-identification (2017, background): “including feature learning [27, 44, 21], distance metric learning [50, 14, 20, 26, 21, 22], and end-to-end learning [19, 1, 43].”
• Person Re-Identification Using Kernel-Based Metric Learning Methods (2014, background): “Our algorithm matches the best reported results for the VIPeR and iLIDS datasets, even though the reported PRDC [31] ranking was obtained under easier experiment settings(4).”
• Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-identification (2018, background): “Image-based person re-identification mainly focuses on two categories: extracting discriminative features [13, 9, 33, 19, 43] and learning robust metrics [37, 50, 18, 36, 2].”
• Learning Mid-level Filters for Person Re-identification (2014, methodology): “Existing person re-identification approaches work on three aspects: distance learning [29, 4, 12, 18, 30, 16, 14], feature design and selection [5, 3, 17, 15, 28, 7, 20, 25], and mid-level feature learning [11, 22, 10, 13].”
• PCCA: A new approach for distance learning from sparse pairwise constraints (2012, methodology): “In contrast, On-line Algorithm for Scalable Image Similarity (OASIS) [5] and Probabilistic Relative Distance Comparison (PRDC) [33] are specifically designed to work with pairwise constraints.”
• Person re-identification by Local Maximal Occurrence representation and metric learning (2014, methodology): “Besides robust features, metric learning has been widely applied for person re-identification [43] [4] [11] [5] [49] [18] [14] [24].”
• Clothing Attributes Assisted Person Reidentification (2015, methodology): “Recently, metric learning models have become popular in person reidentification, which include the probabilistic relative distance comparison model [7] and the relaxed Mahalanobis metric learning model [9].”
• Person Re-identification: What Features Are Important? (2012, methodology): “Comparison of the global feature importance/weights produced by the RankSVM[4], PRDC[5], and the attribute-sensitive feature importance discovered using the proposed method weights in the leg region than the torso region.”