Person re-identification based on metric learning: a survey

Zou, Guofeng; Fu, Guixia; Peng, Xiang; Liu, Yue; Gao, Mingliang; Liu, Zheng

doi:10.1007/s11042-021-10953-6

Cited by 25 publications

(5 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zou et al [145] was the first to review the metric learning algorithms. They categorized them into metric and metric learning methods.…”

Section: Deep Metric Learningmentioning

confidence: 99%

“…They categorized them into metric and metric learning methods. The metric methods refer to the calculation of similarity distance between the probe and gallery extracted features [145]. Metric is calculated either from distance metric (Mahalanobis distance, or asymmetric distance metric) or from similarity metric constructed through (hypergraphs, or matching functions), whereas the metric learning usually means constructing the metric matrix from loss objective function design.…”

Section: Deep Metric Learningmentioning

confidence: 99%

“…Zou et al [145] categorized the metric learning into classical and deep metric learning methods. Several classical metric learning techniques are widely used for video-based re-identification.…”

Section: Deep Metric Learningmentioning

confidence: 99%

See 2 more Smart Citations

Deep video-based person re-identification (Deep Vid-ReID): comprehensive survey

Saad,

Moussa,

Abdel-Kader

et al. 2024

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

Person re-identification (ReID) aims to find the person of interest across multiple non-overlapping cameras. It is considered an essential step for person tracking applications which is vital for surveillance. Person ReID could be investigated either using image-based or video-based. Video-based person ReID is considered more discriminating and realistic than image-based ReID due to the massive information extracted for each person. Different deep-learning techniques have been used for video-based ReID. In this survey, recently published articles are reviewed according to video-based ReID system pipeline: deep features learning, deep metric learning, and deep learning approaches. The deep feature learning approaches are categorized into spatial and temporal approaches, while deep metric learning is divided into metric and metric learning approaches. The deep learning approaches are differentiated into: supervised, unsupervised, weakly-supervised, and one-shot learning. A detailed analysis is held for the architectures of the state-of-the-art deep learning approaches. And their performance on four benchmark datasets is compared.

show abstract

“…Zou et al [145] was the first to review the metric learning algorithms. They categorized them into metric and metric learning methods.…”

Section: Deep Metric Learningmentioning

confidence: 99%

Section: Deep Metric Learningmentioning

confidence: 99%

See 1 more Smart Citation

Deep video-based person re-identification (Deep Vid-ReID): comprehensive survey

Saad,

Moussa,

Abdel-Kader

et al. 2024

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Deep metric learning has also been applied beyond image classification, to more challenging computer vision applications. A notable example is person re-identification (Re-ID), whose aim is to retrieve a person of interest across multiple non-overlapping cameras [121,122]. Metric learning is particularly effective for Re-ID, as this is an open-set classification task with different people in the training and test classes and often there is only one image available for the query person [123].…”

Section: Applicationsmentioning

confidence: 99%

Deep metric learning for few-shot image classification: A Review of recent developments

Yang

et al. 2023

Pattern Recognition

View full text Add to dashboard Cite

“…This research direction has attracted the attention of a large number of scholars and research institutions. Aiming to solve the problem of person re-identification, the research mainly focuses on the following two aspects: the expression of pedestrian characteristics [6][7][8][9][10][11][12] and similarity measurement learning [13][14][15][16][17][18]. The feature descriptors try to determine how to select visual features with good discrimination and robustness for pedestrian image matching.…”

Section: Introductionmentioning

confidence: 99%

Sparse and Low-Rank Joint Dictionary Learning for Person Re-Identification

Sun

Kong

2022

Mathematics

View full text Add to dashboard Cite

In the past decade, the scientific community has become increasingly interested in the re-identification of people. It is still a challenging problem due to its low-quality images; occlusion between objects; and huge changes in lighting, viewpoint and posture (even for the same person). Therefore, we propose a dictionary learning method that divides the appearance characteristics of pedestrians into a shared part, which comprises the similarity between different pedestrians, and a specific part, which reflects unique identity information. In the process of re-identification, by removing the shared part of a pedestrian’s visual characteristics and considering the unique part of each person, the ambiguity of the pedestrian’s visual characteristics can be reduced. In addition, considering the structural characteristics of the shared dictionary and special dictionary, low-rank, l0 norm and row sparsity constraints instead of their convex-relaxed forms are introduced into the dictionary learning framework to improve its representation and recognition capabilities. Therefore, we adopt the method of alternating directions to solve it. The experimental results of several commonly used datasets show the effectiveness of our proposed method.

show abstract

Person re-identification based on metric learning: a survey

Cited by 25 publications

References 72 publications

Deep video-based person re-identification (Deep Vid-ReID): comprehensive survey

Deep video-based person re-identification (Deep Vid-ReID): comprehensive survey

Deep metric learning for few-shot image classification: A Review of recent developments

Sparse and Low-Rank Joint Dictionary Learning for Person Re-Identification

Contact Info

Product

Resources

About