LookupViT: Compressing visual information to a limited number of tokens.

Rajat Koner Gagan Jain Prateek Jain Volker Tresp Sujoy Paul

Published in: CoRR (2024)

Keyphrases

visual information
low level
visual information retrieval
databases
domain knowledge
image classification
multi modal
semantic information
visual content
visual cues
visual descriptors