Sign in
Vision Langauge Pre-training by Contrastive Learning with Cross-Modal Similarity Regulation.
Chaoya Jiang
Wei Ye
Haiyang Xu
Ming Yan
Shikun Zhang
Jie Zhang
Fei Huang
Published in:
CoRR (2023)
Keyphrases
</>
cross modal
learning algorithm
supervised learning
visual recognition
similarity measure
learning tasks
computer vision
high level
video sequences
active learning
co occurrence