Login / Signup
Cali-NCE: Boosting Cross-modal Video Representation Learning with Calibrated Alignment.
Nanxuan Zhao
Jianbo Jiao
Weidi Xie
Dahua Lin
Published in:
CVPR Workshops (2023)
Keyphrases
</>
cross modal
visual recognition
learning tasks
multi modal
video representation
search engine
similarity measure
spatio temporal
knn
image database