Login / Signup

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration.

Yuhao CuiZhou YuChunqi WangZhongzhou ZhaoJi ZhangMeng WangJun Yu
Published in: ACM Multimedia (2021)
Keyphrases
  • knowledge integration
  • natural language
  • learning systems
  • science learning
  • semantic information
  • domain specific
  • language learning
  • learning process
  • semi automatic
  • domain ontology
  • knowledge repository