Person re-identification: A retrospective on domain specific open challenges and future trends

A Zahra, N Perwaiz, M Shahzad, MM Fraz - Pattern Recognition, 2023 - Elsevier
Abstract Person Re-Identification (Re-ID) is a critical aspect of visual surveillance systems,
which aims to automatically recognize and locate individuals across a multi-camera network …

Ice: Inter-instance contrastive encoding for unsupervised person re-identification

H Chen, B Lagadec, F Bremond - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Unsupervised person re-identification (ReID) aims at learning discriminative identity features
without annotations. Recently, self-supervised contrastive learning has gained increasing …

Idm: An intermediate domain module for domain adaptive person re-id

Y Dai, J Liu, Y Sun, Z Tong… - Proceedings of the …, 2021 - openaccess.thecvf.com
Unsupervised domain adaptive person re-identification (UDA re-ID) aims at transferring the
labeled source domain's knowledge to improve the model's discriminability on the unlabeled …

Online pseudo label generation by hierarchical cluster dynamics for adaptive person re-identification

Y Zheng, S Tang, G Teng, Y Ge, K Liu… - Proceedings of the …, 2021 - openaccess.thecvf.com
Adaptive person re-identification (adaptive ReID) targets at transferring learned knowledge
from the labeled source domain to the unlabeled target domain. Pseudo-label-based …

Generalizable person re-identification with relevance-aware mixture of experts

Y Dai, X Li, J Liu, Z Tong… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Abstract Domain generalizable (DG) person re-identification (ReID) is a challenging
problem because we cannot access any unseen target domain data during training. Almost …

Person re-identification via attention pyramid

G Chen, T Gu, J Lu, JA Bao… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In this paper, we propose an attention pyramid method for person re-identification. Unlike
conventional attention-based methods which only learn a global attention map, our attention …

Unrealperson: An adaptive pipeline towards costless person re-identification

T Zhang, L **e, L Wei, Z Zhuang… - Proceedings of the …, 2021 - openaccess.thecvf.com
The main difficulty of person re-identification (ReID) lies in collecting annotated data and
transferring the model across different domains. This paper presents UnrealPerson, a novel …

Meta pairwise relationship distillation for unsupervised person re-identification

H Ji, L Wang, S Zhou, W Tang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Unsupervised person re-identification (Re-ID) remains challenging due to the lack of ground-
truth labels. Existing methods often rely on estimated pseudo labels via iterative clustering …

Reliability modeling and contrastive learning for unsupervised person re-identification

Z Pang, C Wang, J Wang, L Zhao - Knowledge-Based Systems, 2023 - Elsevier
Unsupervised person re-identification (ReID) aims to learn discriminative identity features in
scenarios without a ground-truth. Fully unsupervised person ReID methods usually iterate …

Joint clustering and discriminative feature alignment for unsupervised domain adaptation

W Deng, Q Liao, L Zhao, D Guo… - … on Image Processing, 2021 - ieeexplore.ieee.org
Unsupervised Domain Adaptation (UDA) aims to learn a classifier for the unlabeled target
domain by leveraging knowledge from a labeled source domain with a different but related …