Context-driven Multi-stream LSTM (M-LSTM) for Recognizing Fine-Grained Activity of Drivers.

Ardhendu Behera Alexander Keidel Bappaditya Debnath

Published in: GCPR (2018)

Keyphrases

fine grained
multi stream
coarse grained
recurrent neural networks
access control
user intent
contextual information
human activities
audio visual
audio visual speech recognition