Large Vision and Multimodal Models | Views : 0
下载量:
1
CSCD:
0
Celadon cross-modal knowledge graph construction via a visual-language model
- “In the field of protecting and inheriting celadon culture, experts have proposed a cross modal entity alignment method based on a pre trained visual language model, successfully constructing a cross modal knowledge graph of celadon and providing a new solution for the inheritance of celadon culture.”
- Vol. 30, Issue 5, Pages: 1318-1333(2025)
Received:25 April 2024,
Revised:14 June 2024,
Published:16 May 2025
DOI: 10.11834/jig.240234
移动端阅览