访:尿

Sarah Alotaibi1, Suheer Al-Hadhrami1,2, Saad Al-Ahmadi1

  • 1Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia.

PubMed
概括

本研究引入了一种新的多层次视觉问题答案 (VQA) 框架,以帮助视觉障碍者. 双层架构通过将问题路由到专门的VQA模型来提高准确性.