.png){kind=icon}
Return
Multi-level alignment network for unsupervised domain adaptive multi-modality object re-identification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2025.115015.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A new unsupervised domain adaptive multi-modality object re-identification task. • A new multi-level alignment network for unsupervised domain adaptive multi-modality object re-identification. • A new multi-level alignment strategy at the pseudo-label, domain, and modality level mitigates multi-modality inter-domain distribution shifts. • A new prototype-instance level distribution alignment considers the whole while reducing the impact of edge samples.
Journal
K
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
View more organizations
Cited Papers
ShareSaveLearning a generalizable re-identification model from unlabelled data with domain-agnostic expert
OAAI
OAAIShareSaveShareSave3C: Confidence-guided clustering and contrastive learning for unsupervised person re-identification
PREAI
ShareSaveDomain-adaptive person re-identification via domain alignment and mutual pseudo-label refinement.png)
MULTIMEDIA SYSTEMS
MULTIMEDIA SYSTEMSIF3.1
PREAI
ShareSave no more