MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning.

Bang Yang Fenglin Liu Xian Wu Yaowei Wang Xu Sun Yuexian Zou

Published in: ACL (1) (2023)

Keyphrases

visual features
visual information
information retrieval
digital libraries
visual perception
neural network
low level
visual cues
high level
statistically significant
learning processes
cross language
encoding schemes