Transreid: Transformer-based object re-identification

S He, H Luo, P Wang, F Wang, H Li… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Extracting robust feature representation is one of the key challenges in object re-
identification (ReID). Although convolution neural network (CNN)-based methods have …

Modality unifying network for visible-infrared person re-identification

H Yu, X Cheng, W Peng, W Liu… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Visible-infrared person re-identification (VI-ReID) is a challenging task due to large cross-
modality discrepancies and intra-class variations. Existing methods mainly focus on learning …

Combined depth space based architecture search for person re-identification

H Li, G Wu, WS Zheng - … of the IEEE/CVF conference on …, 2021‏ - openaccess.thecvf.com
Most works on person re-identification (ReID) take advantage of large backbone networks
such as ResNet, which are designed for image classification instead of ReID, for feature …

Rethinking the distribution gap of person re-identification with camera-based batch normalization

Z Zhuang, L Wei, L **e, T Zhang, H Zhang… - Computer Vision–ECCV …, 2020‏ - Springer
The fundamental difficulty in person re-identification (ReID) lies in learning the
correspondence among individual cameras. It strongly demands costly inter-camera …

Dc-former: Diverse and compact transformer for person re-identification

W Li, C Zou, M Wang, F Xu, J Zhao, R Zheng… - Proceedings of the …, 2023‏ - ojs.aaai.org
In person re-identification (ReID) task, it is still challenging to learn discriminative
representation by deep learning, due to limited data. Generally speaking, the model will get …

Person re-identification using heterogeneous local graph attention networks

Z Zhang, H Zhang, S Liu - … of the IEEE/CVF conference on …, 2021‏ - openaccess.thecvf.com
Recently, some methods have focused on learning local relation among parts of pedestrian
images for person re-identification (Re-ID), as it offers powerful representation capabilities …

Contrastive clothing and pose generation for cloth-changing person re-identification

VD Nguyen, P Mantini, SK Shah - Proceedings of the IEEE …, 2024‏ - openaccess.thecvf.com
Abstract Cloth-Changing Person Re-Identification (CCRe-ID) aims at matching an individual
across cameras after a long period of time presenting variations in clothing compounded …

Large-scale spatio-temporal person re-identification: Algorithms and benchmark

X Shu, X Wang, X Zang, S Zhang… - … on Circuits and …, 2021‏ - ieeexplore.ieee.org
Person re-identification (re-ID) in the scenario with large spatial and temporal spans has not
been fully explored. This fact partially occurs because existing benchmark datasets were …

Cross-modality transformer with modality mining for visible-infrared person re-identification

T Liang, Y **, W Liu, Y Li - IEEE Transactions on Multimedia, 2023‏ - ieeexplore.ieee.org
The visible-infrared person re-identification (VI-ReID) is a challenging ReID task, which aims
to retrieve and match the same identity's images between the heterogeneous visible and …