CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations.

Mohammadreza Zolfaghari Yi Zhu Peter V. Gehler Thomas Brox

Published in: CoRR (2021)

Keyphrases

multi modal
cross modal
semantic concepts
visual recognition
video search
perceptual information
multiple modalities
high dimensional
computer vision
video sequences
image annotation
multimedia
feature extraction