Controllable Dense Captioner with Multimodal Embedding Bridging.

Yuzhong Zhao Yue Liu Zonghao Guo Weijia Wu Chen Gong Qixiang Ye Fang Wan

Published in: CoRR (2024)

Keyphrases

multi modal
multimodal interaction
real time
computer vision
robust image watermarking
stereo correspondence
nonlinear dimensionality reduction
multimodal information
genetic algorithm
three dimensional
input image
vector space
stereo matching
data hiding
optical flow fields
dense optical flow