Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition.

Kensho Hara Hirokatsu Kataoka Yutaka Satoh

Published in: ICCV Workshops (2017)

Keyphrases

action recognition
human actions
bag of words
human detection
computer vision
high level
learning algorithm
spatio temporal
activity recognition
image retrieval
viewpoint
body parts
spatial temporal
bag of features
view invariant
recognition of human actions