What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention.

Antonino Furnari Giovanni Maria Farinella

Published in: ICCV (2019)

Keyphrases

multi modal
medical images
action selection
goal directed
visual saliency
computer vision
decision theoretic
neural network
bayesian networks
situation calculus
reasoning about actions
database
visual attention
activity recognition
video sequences
social networks
data mining
data sets
real time