Deep Cross-Modality Alignment for Multi-Shot Person Re-IDentification.

Zhichao Song Bingbing Ni Yichao Yan Zhe Ren Yi Xu Xiaokang Yang

Published in: ACM Multimedia (2017)

Keyphrases

person re identification
video surveillance
metric learning
sparse coding
feature representation
camera network
video sequences
visual features
visual recognition
machine learning
image sequences
multiscale
video data