Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts.

Yan Zeng Xinsong Zhang Hang Li

Published in: CoRR (2021)

Keyphrases

visual concepts
natural language
learning tasks
image content
computer vision
visual content
semantic concepts
training set
image collections
video content
keywords
image retrieval
supervised learning
image classification
training examples
machine learning
multimedia data
kernel methods
high level
semantic gap