ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map.

Yilin Ye Shishi Xiao Xingchen Zeng Wei Zeng

Published in: CoRR (2024)

Keyphrases

multi modal
single modality
cross modal
multi modality
video search
fusing multiple
auto annotation
audio visual
visual features
low level
image annotation
vector space
multiple modalities
dimensionality reduction
semantic concepts
euclidean space
multimedia
visual cues
visual information
uni modal
high dimensional