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 …

Source-free domain adaptive human pose estimation

Q Peng, C Zheng, C Chen - Proceedings of the IEEE/CVF …, 2023‏ - openaccess.thecvf.com
Abstract Human Pose Estimation (HPE) is widely used in various fields, including motion
analysis, healthcare, and virtual reality. However, the great expenses of labeled real-world …

Part-based pseudo label refinement for unsupervised person re-identification

Y Cho, WJ Kim, S Hong… - Proceedings of the IEEE …, 2022‏ - openaccess.thecvf.com
Unsupervised person re-identification (re-ID) aims at learning discriminative representations
for person retrieval from unlabeled data. Recent techniques accomplish this task by using …

Shape-erased feature learning for visible-infrared person re-identification

J Feng, A Wu, WS Zheng - … of the IEEE/CVF conference on …, 2023‏ - openaccess.thecvf.com
Due to the modality gap between visible and infrared images with high visual ambiguity,
learning diverse modality-shared semantic concepts for visible-infrared person re …

Discover cross-modality nuances for visible-infrared person re-identification

Q Wu, P Dai, J Chen, CW Lin, Y Wu… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Visible-infrared person re-identification (Re-ID) aims to match the pedestrian images of the
same identity from different modalities. Existing works mainly focus on alleviating the …

Self-paced contrastive learning with hybrid memory for domain adaptive object re-id

Y Ge, F Zhu, D Chen, R Zhao - Advances in neural …, 2020‏ - proceedings.neurips.cc
Abstract Domain adaptive object re-ID aims to transfer the learned knowledge from the
labeled source domain to the unlabeled target domain to tackle the open-class re …

Uncertainty modeling for out-of-distribution generalization

X Li, Y Dai, Y Ge, J Liu, Y Shan, LY Duan - arxiv preprint arxiv …, 2022‏ - arxiv.org
Though remarkable progress has been achieved in various vision tasks, deep neural
networks still suffer obvious performance degradation when tested in out-of-distribution …

Cluster contrast for unsupervised person re-identification

Z Dai, G Wang, W Yuan, S Zhu… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Thanks to the recent research development in contrastive learning, the gap of visual
representation learning between supervised and unsupervised approaches has been …

Unsupervised person re-identification via multi-label classification

D Wang, S Zhang - … of the IEEE/CVF conference on …, 2020‏ - openaccess.thecvf.com
The challenge of unsupervised person re-identification (ReID) lies in learning discriminative
features without true labels. This paper formulates unsupervised person ReID as a multi …