Recurrent matching networks of spatial alignment learning for person re-identification

Person re-identification (re-id) usually refers to matching people across disjoint camera views. Many existing methods focus on extracting discriminative features or learning distance metrics to make the intraclass distance smaller than interclass distances. These methods subconsciously assume that...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Multimedia tools and applications 2020-12, Vol.79 (45-46), p.33735-33755
Hauptverfasser:	Lin, Lan, Zhang, Dan, Zheng, Xin, Ye, Mao, Guo, Jiuxia
Format:	Artikel
Sprache:	eng
Schlagworte:	Alignment Computer Communication Networks Computer Science Correspondence Data Structures and Information Theory Decision making Feature extraction Identification Learning Matching Misalignment Multimedia Multimedia Information Systems Neural networks Special Purpose and Application-Based Systems
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!