TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval.

Xiaohan Zou Changqiao Wu Lele Cheng Zhongyuan Wang

Published in: CoRR (2022)

Keyphrases

fine grained
cross modal
multi modal
multimedia retrieval
coarse grained
multimedia databases
image retrieval
access control
computer vision
natural language
multimedia
visual similarity
visual recognition
document retrieval
search engine
multimedia information retrieval
image content
retrieval systems
data lineage