Confidence-aware Non-repetitive Multimodal Transformers for TextCaps.

Zhaokai Wang Renda Bao Qi Wu Si Liu

Published in: CoRR (2020)

Keyphrases

multi modal
confidence measure
high confidence
multimodal interaction
multimodal data
information retrieval
multimedia
confidence level
computer vision
medical images
privacy preserving
music retrieval
repetitive patterns
multimodal information