Semi-attention partition for occluded person re-identification
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 …
features for occluded person re-identification (re-ID). Currently, the mainstream methods …
An Open-World, Diverse, Cross-Spatial-Temporal Benchmark for Dynamic Wild Person Re-Identification
Person re-identification (ReID) has made great strides thanks to the data-driven deep
learning techniques. However, the existing benchmark datasets lack diversity, and models …
learning techniques. However, the existing benchmark datasets lack diversity, and models …
Towards Robust Person Re-Identification by Adversarial Training with Dynamic Attack Strategy
Recently, person re-identification has gained significant attention from both academic and
industry fields due to its potential applications in surveillance and security. However, the …
industry fields due to its potential applications in surveillance and security. However, the …
Inter-Camera Identity Discrimination for Unsupervised Person Re-Identification
M Xiong, K Hu, Z Lv, F Fang, Z Wang, R Hu… - ACM Transactions on …, 2024 - dl.acm.org
Unsupervised person re-identification (Re-ID) has garnered significant attention because of
its data-friendly nature, as it does not require labeled data. Existing approaches primarily …
its data-friendly nature, as it does not require labeled data. Existing approaches primarily …
Distribution-Guided Hierarchical Calibration Contrastive Network for Unsupervised Person Re-Identification
Y Li, W Tang, S Wang, S Qian… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The person re-identification task aims to retrieve the same identity under different cameras.
The main difficulties of the task lie in the collection of a large amount of annotated data and …
The main difficulties of the task lie in the collection of a large amount of annotated data and …