使用机器学习模型的视觉问题生成回答(VQG-VQA)

Atul Kachare, M. Kalla, Ashutosh Gupta
{"title":"使用机器学习模型的视觉问题生成回答(VQG-VQA)","authors":"Atul Kachare, M. Kalla, Ashutosh Gupta","doi":"10.37394/23202.2023.22.67","DOIUrl":null,"url":null,"abstract":"Presented automated visual question-answer system generates graphics-based question-answer pairs. The system consists of the Visual Query Generation (VQG) and Visual Question Answer (VQA) modules. VQG generates questions based on visual cues, and VQA provides matching answers to the VQG modules. VQG system generates questions using LSTM and VGG19 model, training parameters, and predicting words with the highest probability for output. VQA uses VGG-19 convolutional neural network for image encoding, embedding, and multilayer perceptron for high-quality responses. The proposed system reduces the need for human annotation and thus supports the traditional education sector by significantly reducing the human intervention required to generate text queries. The system can be used in interactive interfaces to help young children learn.","PeriodicalId":39422,"journal":{"name":"WSEAS Transactions on Systems and Control","volume":"20 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Visual Question Generation Answering (VQG-VQA) using Machine Learning Models\",\"authors\":\"Atul Kachare, M. Kalla, Ashutosh Gupta\",\"doi\":\"10.37394/23202.2023.22.67\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Presented automated visual question-answer system generates graphics-based question-answer pairs. The system consists of the Visual Query Generation (VQG) and Visual Question Answer (VQA) modules. VQG generates questions based on visual cues, and VQA provides matching answers to the VQG modules. VQG system generates questions using LSTM and VGG19 model, training parameters, and predicting words with the highest probability for output. VQA uses VGG-19 convolutional neural network for image encoding, embedding, and multilayer perceptron for high-quality responses. The proposed system reduces the need for human annotation and thus supports the traditional education sector by significantly reducing the human intervention required to generate text queries. The system can be used in interactive interfaces to help young children learn.\",\"PeriodicalId\":39422,\"journal\":{\"name\":\"WSEAS Transactions on Systems and Control\",\"volume\":\"20 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"WSEAS Transactions on Systems and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.37394/23202.2023.22.67\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Mathematics\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"WSEAS Transactions on Systems and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37394/23202.2023.22.67","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Mathematics","Score":null,"Total":0}
引用次数: 0

摘要

提出了自动可视化问答系统,生成基于图形的问答对。该系统由可视化查询生成(VQG)和可视化问答(VQA)两个模块组成。VQG根据视觉线索生成问题,VQA为VQG模块提供匹配的答案。VQG系统使用LSTM和VGG19模型生成问题,训练参数,预测输出概率最高的单词。VQA使用VGG-19卷积神经网络进行图像编码、嵌入,并使用多层感知器进行高质量响应。提出的系统减少了对人工注释的需求,从而通过显著减少生成文本查询所需的人工干预来支持传统教育部门。该系统可用于交互式界面,帮助幼儿学习。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Visual Question Generation Answering (VQG-VQA) using Machine Learning Models
Presented automated visual question-answer system generates graphics-based question-answer pairs. The system consists of the Visual Query Generation (VQG) and Visual Question Answer (VQA) modules. VQG generates questions based on visual cues, and VQA provides matching answers to the VQG modules. VQG system generates questions using LSTM and VGG19 model, training parameters, and predicting words with the highest probability for output. VQA uses VGG-19 convolutional neural network for image encoding, embedding, and multilayer perceptron for high-quality responses. The proposed system reduces the need for human annotation and thus supports the traditional education sector by significantly reducing the human intervention required to generate text queries. The system can be used in interactive interfaces to help young children learn.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
WSEAS Transactions on Systems and Control
WSEAS Transactions on Systems and Control Mathematics-Control and Optimization
CiteScore
1.80
自引率
0.00%
发文量
49
期刊介绍: WSEAS Transactions on Systems and Control publishes original research papers relating to systems theory and automatic control. We aim to bring important work to a wide international audience and therefore only publish papers of exceptional scientific value that advance our understanding of these particular areas. The research presented must transcend the limits of case studies, while both experimental and theoretical studies are accepted. It is a multi-disciplinary journal and therefore its content mirrors the diverse interests and approaches of scholars involved with systems theory, dynamical systems, linear and non-linear control, intelligent control, robotics and related areas. We also welcome scholarly contributions from officials with government agencies, international agencies, and non-governmental organizations.
期刊最新文献
Creating Fuzzy Models from Limited Data Well-posedness of the Optimal Control Problem Related to Degenerate Chemo-attraction Models Performance Analysis of MPBC with PI and Fuzzy Logic Controllers Applied to Solar Powered Electric Vehicle Application A Model-Based Adaptive Control of Turning Maneuver for Catamaran Autonomous Surface Vessel Voltage Stability in a Photovoltaic-based DC Microgrid with GaN-Based Bidirectional Converter using Fuzzy Controller for EV Charging Applications
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1