Pyramidal Transformer with Conv-Patchify for Person Re-identification.

He Li Mang Ye Cong Wang Bo Du

Published in: ACM Multimedia (2022)

Keyphrases

person re identification
sparse coding
multiresolution
metric learning
video surveillance
camera network
image representation
feature representation
feature space
surveillance system
distance metric
visual recognition
riemannian manifolds
image features
object tracking
feature selection
object recognition