2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition.

Hengduo Li Zuxuan Wu Abhinav Shrivastava Larry S. Davis

Published in: CVPR (2021)

Keyphrases

recognition rate
object recognition
recognition accuracy
video sequences
automatic recognition
multimedia
human activities
computationally efficient
video frames
activity recognition
real time
spatio temporal
image processing
action recognition
space time
multiscale
visual recognition