An adaptive cross‐scale transformer based on graph signal processing for person re‐identification
Abstract Extracting robust feature representation is one of the key challenges for person re‐identification (ReID) task. Although convolution neural network (CNN)‐based methods have achieved great success, they still cannot handle the part occlusion and misalignment caused by limited receptive field...
Main Authors: | Wei Zhou, Yi Hou, Shijun Xu, Shilin Zhou |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-06-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12794 |
Similar Items
-
Unsupervised Domain Adaptive Person Re-Identification Method Based on Transformer
by: Xiai Yan, et al.
Published: (2022-09-01) -
Unsupervised Person Re-Identification via Multi-Order Cross-View Graph Adversarial Network
by: Xiang Fu, et al.
Published: (2021-01-01) -
Cross-Modality Person Re-Identification via Local Paired Graph Attention Network
by: Jianglin Zhou, et al.
Published: (2023-04-01) -
Adaptive Label Allocation for Unsupervised Person Re-Identification
by: Yihu Song, et al.
Published: (2022-03-01) -
Person Re-Identification Using Local Relation-Aware Graph Convolutional Network
by: Yu Lian, et al.
Published: (2023-09-01)