晋赞霞,覃京燕,殷绪成.AI设计下的文本视觉问答技术[J].包装工程,2021,42(6):7-12. |
AI设计下的文本视觉问答技术 |
Text-based Visual Question Answering with AI Design |
投稿时间:2020-12-08 |
DOI:10.19554/j.cnki.1001-3563.2021.06.002 |
中文关键词: AI设计 AI 文本视觉问答 认知差异 |
英文关键词: AI design AI text-based visual question answering cognitive differences |
基金项目:长江学者奖励项目(FRF-TP-18-010C1);国家重大专项课题(2018YFB0704301);北科大顺德研究生项目(BK19AE011) |
|
摘要点击次数: |
全文下载次数: |
中文摘要: |
目的 分析基于AI设计的文本视觉问答模型的有效性,旨在利用AI设计更好地指导当前AI模型的构建,提升模型效果和用户体验。方法 以传统文本视觉问答框架为基础,结合AI设计改进当前模型。具体包括加强基于场景设计原则的关系挖掘,根据不同理解层次需求的答案 |
英文摘要: |
It analyzes the effectiveness of the text visual question answering model based on AI design, aiming to better guide the construction of current artificial intelligence models with AI design, and improve model performance and user experience. It is based on the traditional text visual question answering framework, and the current model can be improved by combining AI design. Specifically, it includes strengthening relationship mining based on the principles of scenario design, predicting answer |
查看全文
查看/发表评论 下载PDF阅读器 |
关闭 |