Fully Unsupervised Person Re-Identification via Multiple Pseudo Labels Joint Training

Person re-identification (re-ID) is the task of finding the matched person in a non-overlapping and multi-camera system. Because annotating images across multiple cameras is difficult and time-consuming, this paper focuses on fully unsupervised learning person re-ID that can learn person re-ID on un...

Celý popis

Podrobná bibliografie
Hlavní autoři: Qing Tang, Ge Cao, Kang-Hyun Jo
Médium: Článek
Jazyk:English
Vydáno: IEEE 2021-01-01
Edice:IEEE Access
Témata:
On-line přístup:https://ieeexplore.ieee.org/document/9645557/