Tracklet self-supervised learning for unsupervised person re-identification

G Wu, X Zhu, S Gong - Proceedings of the AAAI conference on artificial …, 2020‏ - ojs.aaai.org
Existing unsupervised person re-identification (re-id) methods mainly focus on cross-domain
adaptation or one-shot learning. Although they are more scalable than the supervised …

Part-aware progressive unsupervised domain adaptation for person re-identification

F Yang, K Yan, S Lu, H Jia, D ** enhances pose alignment for person re-identification
P Wang, Z Zhao, F Su, X Zu… - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
Despite the remarkable progress in recent years, person Re-Identification (ReID)
approaches frequently fail in cases where the semantic body parts are misaligned between …

REVAMP2T: Real-Time Edge Video Analytics for Multicamera Privacy-Aware Pedestrian Tracking

C Neff, M Mendieta, S Mohan… - IEEE Internet of …, 2019‏ - ieeexplore.ieee.org
This article presents real-time edge video analytics for multicamera privacy-aware
pedestrian tracking (REVAMP 2 T), as an integrated end-to-end Internet of Things (IoT) …

Person re-identification with reinforced attribute attention selection

J Zhang, L Niu, L Zhang - IEEE Transactions on Image …, 2020‏ - ieeexplore.ieee.org
Person re-identification (Re-ID) aims to match pedestrian images across various scenes in
video surveillance. There are a few works using attribute information to boost Re-ID …

Ltreid: Factorizable feature generation with independent components for long-tailed person re-identification

P Wang, Z Zhao, F Su, H Meng - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
With the rapid increase of large-scale and real-world person datasets, it is crucial to address
the problem of long-tailed data distributions, ie, head classes have large number of images …

An end-to-end foreground-aware network for person re-identification

Y Liu, W Zhou, J Liu, GJ Qi, Q Tian… - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
Person re-identification is a crucial task of identifying pedestrians of interest across multiple
surveillance camera views. For person re-identification, a pedestrian is usually represented …

Boundary-restricted metric learning

S Chen, C Gong, X Li, J Yang, G Niu, M Sugiyama - Machine Learning, 2023‏ - Springer
Metric learning aims to learn a distance metric to properly measure the similarities between
pairwise examples. Most existing learning algorithms are designed to reduce intra-class …