Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation.

Ho Kei Cheng Yu-Wing Tai Chi-Keung Tang

Published in: NeurIPS (2021)

Keyphrases

space time
spatial and temporal
dynamic scenes
spatio temporal
video sequences
motion patterns
social networks
super resolution reconstruction
input video
network structure
high efficiency
multiple view geometry
image segmentation
three dimensional