Combining Global and Local Similarity for Cross-Media Retrieval

Combining Global and Local Similarity for Cross-Media Retrieval

This paper mainly studies the problem of image-text matching in order to make image and text better match. Existing cross-media retrieval methods only make use of the information of image and part of text, that is, matching the whole image with the whole sentence, or matching some image areas with s...

Full description

Bibliographic Details
Main Authors: Zhixin Li, Feng Ling, Canlong Zhang, Huifang Ma
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Convolutional neural network
self-attention network
attention mechanism
two-level network
cross-media retrieval
Online Access:https://ieeexplore.ieee.org/document/8970540/

Internet

https://ieeexplore.ieee.org/document/8970540/

Similar Items