BagFormer: Better cross-modal retrieval via bag-wise interaction.

Haowen Hou Xiaopeng Yan Yigeng Zhang

Published in: Eng. Appl. Artif. Intell. (2024)

Keyphrases

cross modal
multi modal
multimedia retrieval
image retrieval
visual similarity
multimedia databases
visual features
visual recognition
image database
bag of words
visual data
multimedia data
perceptual information
multimedia information retrieval
search engine
retrieval systems
feature space
web pages