DCT-Based Decorrelated Attention for Vision Transformers.

Hongyi Pan Emadeldeen Hamdan Xin Zhu Koushik Biswas Ahmet Enis Çetin Ulas Bagci

Published in: CoRR (2024)

Keyphrases

computer vision
real time
mpeg video
visual field
focus of attention
vision system
image compression
machine learning
image processing
case study
visual attention
database
website
high level
database systems
expert systems
transform coefficients
data mining