MAVA: Multi-Level Adaptive Visual-Textual Alignment by Cross-Media Bi-Attention Mechanism.

Yuxin Peng Jinwei Qi Yunkan Zhuo

Published in: IEEE Trans. Image Process. (2020)

Keyphrases

cross media
attention mechanism
multimedia
visual information
visual attention
digital content
visual features
image retrieval
low level
relevance model
multi modal
e learning
visual content
cross language
multimedia information
visual attention model
metadata