Feature Disentanglement and Adaptive Fusion for Improving Multi-modal Tracking.

Zheng Li Weibo Cai Junhao Dong Jianhuang Lai Xiaohua Xie

Published in: PRCV (12) (2023)

Keyphrases

multi modal
multi modality
single modality
fusing multiple
audio visual
multiple features
image features
cross modal
semantic concepts
image annotation
data fusion
humanoid robot
mean shift
feature vectors
high dimensional
uni modal
metadata
graph cuts
object recognition
image sequences