BERT-hLSTMs: BERT and Hierarchical LSTMs for Visual Storytelling.

Jing Su Qingyun Dai Frank Guerin Mian Zhou

Published in: CoRR (2020)

Keyphrases

hierarchical structure
object based visual attention
visual information
virtual environment
visual features
coarse to fine
visual cues
visual feedback
multi modal
mobile robot
multimedia
neural network
video games
visual search
visual perception
visual processing
real time