Invariance Learning Under Uncertainty for Single Domain Generalization Person Re-Identification

Generalizing the person re-identification (re-ID) algorithms to unseen domains is an important research topic for intelligent video surveillance. However, during the training of single-source domain generalization (S-DG), some difficulties, such as data limitation, single data style, and label-speci...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on instrumentation and measurement 2024, Vol.73, p.1-11
Hauptverfasser:	Peng, Wanru, Chen, Houjin, Li, Yanfeng, Sun, Jia
Format:	Artikel
Sprache:	eng
Schlagworte:	Data augmentation Data models Feature extraction person re-identification (re-ID) Representation learning single-source domain generalization (S-DG) Training Training data Uncertainty
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!