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

Yan Zeng Xinsong Zhang Hang Li

Published in: ICML (2022)

Keyphrases

visual concepts
natural language
computer vision
object categories
image collections
training samples
video content
training set
image content
semantic concepts
keywords
image annotation
visual content
positive examples
metadata
text documents
visual information
search engine