Median stable clustering and global distance classification for cross-domain person re-identification
Z Pang, J Guo, Z Ma, W Sun… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The person re-identification (ReID) method in a single-domain achieves appealing
performance, but its reliance on label information greatly limits its extensibility. Therefore, the …
performance, but its reliance on label information greatly limits its extensibility. Therefore, the …
Attention-aligned network for person re-identification
S Lian, W Jiang, H Hu - … on Circuits and Systems for Video …, 2020 - ieeexplore.ieee.org
Currently, attention mechanism receives enormous interest and has been extensively
employed in the fields of Person Re-Identification (RE-ID), as it gains superior performance …
employed in the fields of Person Re-Identification (RE-ID), as it gains superior performance …
Unsupervised domain adaptation by multi-loss gap minimization learning for person re-identification
Unsupervised domain adaptation (UDA) person re-identification (ReID) faces enormous
challenges due to the severe shift between the source and target domains, as well as the …
challenges due to the severe shift between the source and target domains, as well as the …
Multiscale omnibearing attention networks for person re-identification
Y Huang, S Lian, H Hu, D Chen… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
The past few years in the fields of Person Re-Identification (RE-ID) have seen attention
mechanism receives enormous interest as it has superior performance in obtaining …
mechanism receives enormous interest as it has superior performance in obtaining …
Learning image-adaptive lookup tables with spatial awareness for image harmonization
Image harmonization aims to address inharmony between the foreground and background
of composite images. Current methods mainly adopt the encoder-decoder reconstruction …
of composite images. Current methods mainly adopt the encoder-decoder reconstruction …
Dual-stream feature fusion network for person re-identification
W Zhang, Z Li, H Du, J Tong, Z Liu - Engineering Applications of Artificial …, 2024 - Elsevier
Person re-identification (Re-ID) has made significant progress in recent years. However, it
still faces numerous challenges in real scenarios. Although researchers have proposed …
still faces numerous challenges in real scenarios. Although researchers have proposed …
Heterogeneous dual network with feature consistency for domain adaptation person re-identification
To reduce the noisy pseudo-labels generated by clustering for unsupervised domain
adaptation (UDA) person re-identification (re-ID), the method of collaborative training …
adaptation (UDA) person re-identification (re-ID), the method of collaborative training …
Multiformer-based hybrid learning with outlier re-assignment for unsupervised person re-identification
Recent studies have shown the effectiveness of generating pseudo-labels by measuring
feature similarity in unsupervised person re-identification (ReID). However, most of these …
feature similarity in unsupervised person re-identification (ReID). However, most of these …
Unsupervised person re-identification using unified domanial learning
S Zhang, H Hu - Neural Processing Letters, 2023 - Springer
Recent deep learning-based person re-identification (RE-ID) approaches mainly adopt
supervised learning, by which the network is trained with labels and tested in the same …
supervised learning, by which the network is trained with labels and tested in the same …
Improved instance discrimination and feature compactness for end-to-end person search
S Hou, C Zhao, Z Chen, J Wu, Z Wei… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Person search aims to locate and retrieve specific pedestrians in scene images, including
two subtasks, pedestrian detection and person re-identification. Recently, triplet loss has …
two subtasks, pedestrian detection and person re-identification. Recently, triplet loss has …