检索结果-南通市图书馆

human-object interaction detection via interactive visual-semantic graph learning

Science China(Information Sciences) 2022年第6期65卷 81-82页

作者： Tongtong WU Fuqing DUAN Liang CHANG Ke LU College of Artificial Intelligence Beijing Normal University School of Computer and Control Engineering University of Chinese Academy of Sciences

Dear editor,human-object interaction(HOI) detection is an important human-centric visual understanding task with several applications in visual monitoring, intelligent robot, etc. It aims at localizing and inferring interaction relationships between humans and objects in images. As a result of their success in object detection, many object detectors can be used to localize human and object instances. Therefore, the key to HOI detection mainly lies in the second part, namely interaction recognition.

关键词： human-object interaction Context modeling Graph Learning Interactive Graph Visual-Semantic Graph

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

human-object interaction Recognition Based on Modeling Context

引用

Journal of Beijing Institute of Technology 2017年第2期26卷 215-222页

作者： Shuyang Li Wei Liang Qun Zhang School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China

This paper proposes a method to recognize human-object interactions by modeling context between human actions and interacted ***-object interaction recognition is a challenging task due to severe occlusion between human and objects during the interacting *** that human actions and interacted objects provide strong context information,*** actions are usually related to some specific objects,the accuracy of recognition is significantly improved for both of *** the proposed method,both global and local temporal features from skeleton sequences are extracted to model human *** the meantime,kernel features are utilized to describe interacted ***,all possible solutions from actions and objects are optimized by modeling the context between *** results of experiments demonstrate the effectiveness of our method.

关键词： human-object interaction action recognition object recognition modeling context

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

An Intelligent Framework for Recognizing Social human-object interactions

引用

Computers, Materials & Continua 2022年第10期73卷 1207-1223页

作者： Mohammed Alarfaj Manahil Waheed Yazeed Yasin Ghadi Tamara al Shloul Suliman A.Alsuhibany Ahmad Jalal Jeongmin Park Department of Electrical Engineering College of EngineeringKing Faisal UniversityAl-Ahsa31982Saudi Arabia Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science and Software Engineering Al Ain UniversityAl Ain15551UAE Department of humanities and Social Science Al Ain UniversityAl Ain15551UAE Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Engineering Tech University of KoreaSiheung-si15073Gyeonggi-doKorea

human object interaction(HOI)recognition plays an important role in the designing of surveillance and monitoring systems for healthcare,sports,education,and public *** involves localizing the human and object targets and then identifying the interactions between ***,it is a challenging task that highly depends on the extraction of robust and distinctive features from the targets and the use of fast and efficient ***,the proposed system offers an automated body-parts-based solution for HOI *** system uses RGB(red,green,blue)images as input and segments the desired parts of the images through a segmentation technique based on the watershed ***,a convex hullbased approach for extracting key body parts has also been *** identifying the key body parts,two types of features are ***,the entire feature vector is reduced using a dimensionality reduction technique called t-SNE(t-distributed stochastic neighbor embedding).Finally,a multinomial logistic regression classifier is utilized for identifying class labels.A large publicly available dataset,MPII(Max Planck Institute Informatics)human Pose,has been used for system *** results prove the validity of the proposed system as it achieved 87.5%class recognition accuracy.

关键词： Dimensionality reduction human-object interaction key point detection machine learning watershed segmentation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：