All in Tokens: Unifying Output Space of Visual Tasks via Soft Token.

Jia Ning Chen Li Zheng Zhang Chunyu Wang Zigang Geng Qi Dai Kun He Han Hu

Published in: ICCV (2023)

Keyphrases

visual tasks
output space
input space
active vision
structured output
high dimensional
representative set
user defined
training set
dimensionality reduction
class labels
real time
dynamical systems
visual tracking
kernel function
low dimensional
higher order
neural network