Action Recognition by Learning Deep Multi-Granular Spatio-Temporal Video Representation.

Qing Li Zhaofan Qiu Ting Yao Tao Mei Yong Rui Jiebo Luo

Published in: ICMR (2016)

Keyphrases

action recognition
spatio temporal
video representation
human actions
video database
view invariant
action recognition in videos
bag of words
computer vision
space time
spatial and temporal
moving objects
video content
video analysis
prior knowledge
multiscale
feature extraction