CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge.

Linli Yao Weijing Chen Qin Jin

Published in: WWW (2023)

Keyphrases

cross modal
web images
pre trained
semantic information
visual similarity
visual features
prior knowledge
multi modal
image search
multimedia retrieval
information retrieval
image retrieval
low level
video retrieval
visual data