Login / Signup
GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers.
Ali Modarressi
Mohsen Fayyaz
Yadollah Yaghoobzadeh
Mohammad Taher Pilehvar
Published in:
NAACL-HLT (2022)
Keyphrases
</>
low complexity
bit rate
rate distortion
multi layer
single layer
motion estimation
global information
video codec
computer vision
multimedia
image sequences
high quality
vector quantization
video coding
video compression
rate control