Occluded person re-identification with deep learning: a survey and perspectives

E Ning, C Wang, H Zhang, X Ning, P Tiwari - Expert systems with …, 2024‏ - Elsevier
Person re-identification (Re-ID) technology plays an increasingly crucial role in intelligent
surveillance systems. Widespread occlusion significantly impacts the performance of person …

Recent advances in vision transformer: A survey and outlook of recent work

K Islam - arxiv preprint arxiv:2203.01536, 2022‏ - arxiv.org
Vision Transformers (ViTs) are becoming more popular and dominating technique for
various vision tasks, compare to Convolutional Neural Networks (CNNs). As a demanding …

Dual cross-attention learning for fine-grained visual categorization and object re-identification

H Zhu, W Ke, D Li, J Liu, L Tian… - Proceedings of the …, 2022‏ - openaccess.thecvf.com
Recently, self-attention mechanisms have shown impressive performance in various NLP
and CV tasks, which can help capture sequential characteristics and derive global …

Pose-guided feature disentangling for occluded person re-identification based on transformer

T Wang, H Liu, P Song, T Guo, W Shi - Proceedings of the AAAI …, 2022‏ - ojs.aaai.org
Occluded person re-identification is a challenging task as human body parts could be
occluded by some obstacles (eg trees, cars, and pedestrians) in certain scenes. Some …

PHA: Patch-wise high-frequency augmentation for transformer-based person re-identification

G Zhang, Y Zhang, T Zhang, B Li… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
Although recent studies empirically show that injecting Convolutional Neural Networks
(CNNs) into Vision Transformers (ViTs) can improve the performance of person re …

Semi-attention partition for occluded person re-identification

M Jia, Y Sun, Y Zhai, X Cheng, Y Yang… - Proceedings of the AAAI …, 2023‏ - ojs.aaai.org
This paper proposes a Semi-Attention Partition (SAP) method to learn well-aligned part
features for occluded person re-identification (re-ID). Currently, the mainstream methods …

CLIP-ReID: exploiting vision-language model for image re-identification without concrete text labels

S Li, L Sun, Q Li - Proceedings of the AAAI Conference on Artificial …, 2023‏ - ojs.aaai.org
Pre-trained vision-language models like CLIP have recently shown superior performances
on various downstream tasks, including image classification and segmentation. However, in …

Enhancement, integration, expansion: Activating representation of detailed features for occluded person re-identification

E Ning, Y Wang, C Wang, H Zhang, X Ning - Neural Networks, 2024‏ - Elsevier
A proposed method, Enhancement, integration, and Expansion, aims to activate the
representation of detailed features for occluded person re-identification. Region and context …

Learning feature recovery transformer for occluded person re-identification

B Xu, L He, J Liang, Z Sun - IEEE Transactions on Image …, 2022‏ - ieeexplore.ieee.org
One major issue that challenges person re-identification (Re-ID) is the ubiquitous occlusion
over the captured persons. There are two main challenges for the occluded person Re-ID …

Erasing, transforming, and noising defense network for occluded person re-identification

N Dong, L Zhang, S Yan, H Tang… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Occlusion perturbation presents a significant challenge in person re-identification (re-ID),
and existing methods that rely on external visual cues require additional computational …