Temporal Multimodal Fusion for Driver Behavior Prediction Tasks using Gated Recurrent Fusion Units.

Athma Narayanan Avinash Siravuru Behzad Dariush

Published in: CoRR (2019)

Keyphrases

multimodal fusion
high robustness
audio visual
relevance feedback
gait recognition
multimodal interfaces
spatio temporal
real time
keywords
image sequences
learning process
hidden markov models
multi modal
post processing