CLII: Visual-Text Inpainting via Cross-Modal Predictive Interaction.

Liang Zhao Qing Guo Xiaoguang Li Song Wang

Published in: CoRR (2024)

Keyphrases

cross modal
multi modal
multimedia retrieval
multiple modalities
perceptual information
visual recognition

text retrieval
image retrieval
visual data
visual similarity
multimedia databases

information retrieval
text mining
text documents
keywords
semantic information

visual information
text data
image database
multimedia information retrieval
high level