C
search
search
reviewers
reviewers
feeds
feeds
assignments
assignments
settings
logout
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning.
Simon Ging
Mohammadreza Zolfaghari
Hamed Pirsiavash
Thomas Brox
Published in:
CoRR (2020)
Keyphrases
</>
learning algorithm
inductive learning
neural network
information retrieval
active learning
supervised learning
image classification
background knowledge
text representation