EXAM: A Framework of Learning Extreme and Moderate Embeddings for Person Re-ID

EXAM: A Framework of Learning Extreme and Moderate Embeddings for Person Re-ID

Person re-identification (Re-ID) is challenging due to host of factors: the variety of human positions, difficulties in aligning bounding boxes, and complex backgrounds, among other factors. This paper proposes a new framework called EXAM (EXtreme And Moderate feature embeddings) for Re-ID tasks. Th...

Full description

Bibliographic Details
Main Authors: Guanqiu Qi, Gang Hu, Xiaofei Wang, Neal Mazur, Zhiqin Zhu, Matthew Haner
Format: Article
Language:English
Published: MDPI AG 2021-01-01
Series:Journal of Imaging
Subjects:
person Re-ID
deep learning
loss function
Online Access:https://www.mdpi.com/2313-433X/7/1/6

Internet

https://www.mdpi.com/2313-433X/7/1/6

Similar Items