Multi-modal interaction with token division strategy for RGB-T tracking.

Yujue Cai Xiubao Sui Guohua Gu Qian Chen

Published in: Pattern Recognit. (2024)

Keyphrases

multi modal
multi modality
color images
cross modal
audio visual
gray scale
depth data
high dimensional
video search
semantic concepts
humanoid robot
particle filter
image processing
color space
appearance model
mean shift
image classification
feature space
high level