Multimodal Fusion with Co-attention Mechanism.

Pei Li Xinde Li

Published in: FUSION (2020)

Keyphrases

attention mechanism
multimodal fusion
visual attention
audio visual
high robustness
relevance feedback
saliency map
multimodal interfaces
gait recognition
visual attention model
multi modal
eye tracking
eye movements
low level
information retrieval
hidden markov models
image sequences