M2T: Masking Transformers Twice for Faster Decoding.

Fabian Mentzer Eirikur Agustsson Michael Tschannen

Published in: ICCV (2023)

Keyphrases

human visual system
database
decoding algorithm
multiscale
highly efficient
decoding process
artificial intelligence
information systems
image processing
image sequences
memory efficient
viterbi algorithm