Video-based driver action recognition via hybrid spatial-temporal deep learning framework.

Yaocong Hu MingQi Lu Chao Xie Xiaobo Lu

Published in: Multim. Syst. (2021)

Keyphrases

spatial temporal
action recognition
deep learning
human actions
bag of words
activity recognition
temporal information
spatio temporal
computer vision
spatial and temporal
video shots
space time interest points
unsupervised learning
event detection
visual words
multiscale
three dimensional
machine learning