RILS: Masked Visual Reconstruction in Language Semantic Space.

Shusheng Yang Yixiao Ge Kun Yi Dian Li Ying Shan Xiaohu Qie Xinggang Wang

Published in: CVPR (2023)

Keyphrases

semantic space
visual features
co occurrence
cross modal
latent semantic analysis
automatically extracted
semantic concepts
unsupervised manner
visual information
low dimensional
mapping function
natural language
high dimensional
image representation
semantic features