Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment.

Zihui Xue Kristen Grauman

Published in: CoRR (2023)

Keyphrases

fine grained
coarse grained
learning process
view invariant
learning algorithm
multi view
access control
action recognition
active learning
data lineage
image retrieval
viewpoint
spatio temporal
graphical models