Patch-based Object-centric Transformers for Efficient Video Generation.

Wilson Yan Ryo Okumura Stephen James Pieter Abbeel

Published in: CoRR (2022)

Keyphrases

video sequences
video surveillance
object model
real time
d objects
video data
moving objects
video frames
video content
video retrieval
multiple objects
multimedia
image retrieval
markov random field
spatial information