Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos.

Suman Saha Gurkirt Singh Michael Sapienza Philip H. S. Torr Fabio Cuzzolin

Published in: CoRR (2016)

Keyphrases

space time
human actions
deep learning
video sequences
dynamic scenes
input video
video representation
spatial and temporal
spatio temporal
machine learning
unsupervised feature learning
action recognition
unsupervised learning
video frames
viewpoint
image sequences
d objects
interesting events
three dimensional