检索结果-南通市图书馆

Improving Targeted Multimodal Sentiment Classification with Semantic Description of Images

computers, Materials & Continua 2023年第6期75卷 5801-5815页

作者： Jieyu An Wan Mohd Nazmee Wan Zainon Zhang Hao School of Computer Sciences Universiti Sains MalaysiaPenang11800Malaysia

Targeted multimodal sentiment classification(TMSC)aims to identify the sentiment polarity of a target mentioned in a multimodal post.The majority of current studies on this task focus on mapping the image and the text to a high-dimensional space in order to obtain and fuse implicit representations,ignoring the rich semantic information contained in the images and not taking into account the contribution of the visual modality in the multimodal fusion representation,which can potentially influence the results of TMSC tasks.This paper proposes a general model for Improving Targeted Multimodal Sentiment Classification with Semantic Description of Images(ITMSC)as a way to tackle these issues and improve the accu-racy of multimodal sentiment analysis.Specifically,the ITMSC model can automatically adjust the contribution of images in the fusion representation through the exploitation of semantic descriptions of images and text similarity relations.Further,we propose a target-based attention module to capture the target-text relevance,an image-based attention module to capture the image-text relevance,and a target-image matching module based on the former two modules to properly align the target with the image so that fine-grained semantic information can be extracted.Our experimental results demonstrate that our model achieves comparable performance with several state-of-the-art approaches on two multimodal sentiment datasets.Our findings indicate that incorporating semantic descriptions of images can enhance our understanding of multimodal content and lead to improved sentiment analysis performance.

关键词： Targeted sentiment analysis multimodal sentiment classification visual sentiment textual sentiment social media

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

A unified user behavior model for trajectory-based tasks with different types of path constraints

引用

Science China(Information sciences) 2023年第10期66卷 316-318页

作者： Hao ZHANG Jin HUANG Huawei TU Feng TIAN Guozhong DAI Hongan WANG Beijing Key Laboratory of Human-computer Interaction Institute of Software Chinese Academy of Sciences school of computer Science and Technology University of Chinese Academy of Sciences school of Artificial Intelligence University of Chinese Academy of Sciences Department of computer Science and Information Technology La Trobe University

An important research branch of human-computer interaction(HCI) is to develop predictive models for human performance in fundamental interactions [1]. On today’s graphical user interface(GUI), users often implicitly perform various trajectory-based interactions, such as navigating through menus [2], entering the boundary of a button,

关键词：

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

Regularized two-stage submodular maximization under streaming

引用

Science China(Information sciences) 2022年第4期65卷 102-111页

作者： Ruiqi YANG Dachuan XU Longkun GUO Dongmei ZHANG Beijing Institute for Scientific and Engineering Computing Beijing University of Technology school of Mathematical sciences University of Chinese Academy Sciences school of computer Science and Technology Qilu University of Technology school of computer Science and Technology Shandong Jianzhu University

In the problem of maximizing regularized two-stage submodular functions in streams, we assemble a family ■ of m functions each of which is submodular and is visited in a streaming style that an element is visited for only once. The aim is to choose a subset S of size at most ■ from the element stream ■, so as to maximize the average maximum value of these functions restricted on S with a regularized modular term. The problem can be formally cast as ■, where c:■ is a non-negative modular function and ■ is a non-negative monotone non-decreasing submodular function. The well-studied regularized problem of ■ is exactly a special case of the above regularized two-stage submodular maximization by setting m=1 and ■=k. Although f(·)-c(·) is submodular, it is potentially negative and non-monotone and admits no constant multiplicative factor approximation. Therefore, we adopt a slightly weaker notion of approximation which constructs S such that f(S)-c(S)≥ρ·f(O)-c(O) holds against optimum solution O for some ρ∈(0, 1). Eventually, we devise a streaming algorithm by employing the distorted threshold technique, achieving a weaker approximation ratio with ρ=0.2996 for the discussed regularized two-stage model.

关键词： submodular maximization streaming model two-stage threshold technique approximation algorithms

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

Sagbi-Gröbner Bases Under Composition

引用

Journal of Systems Science & Complexity 2023年第5期36卷 2214-2224页

作者： KANWAL Nazish KHAN Junaid Alam Department of sciences&Humanities FAST-National University of Computer&Emerging SciencesKarachicampusPakistan Department of Mathematical sciences School of Mathematics and Computer ScienceInstitute of Business AdministrationKarachiPakistan

The process of substituting variables in a polynomial with other polynomials is dubbed polynomial composition.The behaviour of Gröbner bases and Sagbi bases under composition is well known.In this paper,the authors provide a sufficient and necessary condition on a setΘof polynomials under which the Sagbi-Gröbner basis computation commutes with composition.This has natural applications to the computations of Sagbi-Gröbner bases for subsets of composed polynomials of subalgebra.

关键词： Polynomial composition sagbi bases Sagbi-Gr?bner bases

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

Defined Contribution Pension Planning with the Return of Premiums Clauses and HARA Preference in Stochastic Environments

引用

Acta Mathematicae Applicatae Sinica 2023年第2期39卷 396-423页

作者： Hao CHANG Xing-jiang CHEN school of Mathematical sciences Tiangong UniversityTianjin 300387China Department of Mathematical sciences School of EngineeringComputer and Mathematical SciencesAuckland University of TechnologyAucklandNew Zealand

This paper studies a defined contribution(DC)pension fund investment problem with return of premiums clauses in a stochastic interest rate and stochastic volatility environment.In practice,most of pension plans were subject to the return of premiums clauses to protect the rights of pension members who died before retirement.In the mathematical modeling,we assume that a part of pension members could withdraw their premiums if they died before retirement and surviving members could equally share the difference between accumulated contributions and returned premiums.We suppose that the financial market consists of a risk-free asset,a stock,and a zero-coupon bond.The interest rate is driven by a stochastic affine interest rate model and the stock price follows the Heston’s stochastic volatility model with stochastic interest rates.Different fund managers have different risk preferences,and the hyperbolic absolute risk aversion(HARA)utility function is a general one including a power utility,an exponential utility,and a logarithm utility as special cases.We are concerned with an optimal portfolio to maximize the expected utility of terminal wealth by choosing the HARA utility function in the analysis.By using the principle of dynamic programming and Legendre transform-dual theory,we obtain explicit solutions of optimal strategies.Some special cases are also derived in detail.Finally,a numerical simulation is provided to illustrate our results.

关键词： defined contribution pension plan return of premiums clauses stochastic interest rate HARA preference Legendre transform-dual theory stochastic optimal control

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

Counterfactual Reasoning over Community Detection:A Case Study of the Public Science Day Community

引用

Journal of Social Computing 2023年第2期4卷 125-138页

作者： Wenkang Jiang Hongbo He Lei Lin Qirui Tang Runqiang Wang the computer Network Information Center Chinese Academy of Sciences the school of computer Science and Technology University of Chinese Academy of SciencesBeijing 100083China the computer Network Information Center Chinese Academy of SciencesBeijing 100083China

With the rapid rise of new media platforms such as Weibo and Tiktok,communities with science communication characteristics have progressively grown on social networks.These communities pursue essential objectives such as increased visibility and influence.For the success of the public understanding of science in China,case studies of science communication communities on social media are becoming increasingly valuable as a point of reference.The authenticity of user influence plays an important role in the analysis of the final outcome during the process of community detection.By integrating counterfactual reasoning theory into a community detection algorithm,we present a novel paradigm for eliminating influence bias in online communities.We consider the community of Public Science Day of the Chinese Academy of sciences as a case study to demonstrate the validity of the proposed paradigm.In addition,we examine data on science communication activities,analyze the key elements of activity communication,and provide references for not only augmenting the communication impact of similar types of popular science activities but also advancing science communication in China.Our main finding is that the propagation channel for the science communication experiment exhibits multi-point scattered propagation and lacks a continuous chain in the process of propagation.

关键词： causal inference counterfactual reasoning community detection science communication social networks

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

Multi-Distributed Speech Emotion Recognition Based on Mel Frequency Cepstogram and Parameter Transfer

引用

Chinese Journal of Electronics 2022年第1期31卷 155-167页

作者： LIN Long TAN Liang school of computer Science Sichuan Normal University Institute of Computing Technology Chinese Academy of Sciences

Speech emotion recognition(SER) is the use of speech signals to estimate the state of emotion. At present, machine learning is one of the main research methods of SER, the test and training data S of traditional machine learning all have the same distribution and feature space, but the data of speech is accessed from different environments and devices, with different distribution characteristics in real life. Thus, the traditional machine learning method is applied to the poor performance of SER. This paper proposes a multi-distributed SER method based on Mel frequency cepstogram(MFCC) and parameter transfer. The method is based on single-layer long short-term memory(LSTM), pre-trained inceptionv3 network and multi-distribution corpus. The speech pre-processed MFCC is taken as the input of single-layer LSTM, and input to the pre-trained inception-v3 network.The features are extracted through the pre-trained inception-v3 model. Then the features are sent to the newly defined the fully connected layer and classification layer,let the parameters of the fully connected layer be finetuned, finally get the classification result. The experiment proves that the method can effectively complete the classification of multi-distribution speech emotions and is more effective than the traditional machine learning framework of SER.

关键词： Speech emotion recognition (SER) Machine learning Mel frequency cepstogram (MFCC) Parameter transfer Long short-term memory (LSTM) Inception-v3

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

ASYMPTOTIC STABILITY OF SHOCK WAVES FOR THE OUTFLOW PROBLEM OF A HEAT-CONDUCTIVE IDEAL GAS WITHOUT VISCOSITY

引用

Acta Mathematica Scientia 2023年第4期43卷 1735-1766页

作者：范丽丽侯美晨 school of Mathematics and computer Science Wuhan Polytechnic UniversityWuhan 430023China school of Mathematical sciences University of Chinese Academy of SciencesBeijing 100049China

This paper is concerned with an ideal polytropic model of non-viscous and heatconductive gas in a one-dimensional half space. We focus our attention on the outflow problem when the flow velocity on the boundary is negative and we prove the stability of the viscous shock wave and its superposition with the boundary layer under some smallness conditions.Our waves occur in the subsonic area. The intrinsic properties of our system are more challenging in mathematical analysis, however, in the subsonic area, the lack of a boundary condition on the density provides us with a special manner for defining the shift for the viscous shock wave, and helps us to construct the asymptotic profiles successfully. New weighted energy estimates are introduced and the perturbations on the boundary are handled by some subtle estimates.

关键词： non-viscous shock wave outflow problem boundary layer

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

Information Protocol Equilibrium in n-insider Perfect Competition with a Random Deadline

引用

Acta Mathematicae Applicatae Sinica 2024年

作者： Qi-hong NIE Ji-xiu QIU Ji-ze LI Yong-hui ZHOU school of Big Data and computer sciences Guizhou Normal University school of Mathematical sciences Guizhou Normal University

This paper studies a model of n insiders with perfect information trading on a risky asset with value normally distributed and disclosed at a random deadline. We propose a concept of information protocol equilibrium under semi-strong efficient pricing, consisting of an n-profile of insider trading strategies with terminal residual information protocols, and find that if a common protocol on terminal residual information before trading is obeyed by all insiders, then, in the market with more than two insiders there exists a uique equilibrium only when it requires to release common partial information eventually, or it does not exist if it requires to release all or not any; but in the market with a single insider, the insider may release all private information eventually to make a maximal profit. Thereby, the existence and uniqueness of information protocol equilibrium among n insiders are deduced. Finally, numerical results illustrate some market characteristics of equilibria with different information protocols required before trading.

关键词：

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

Affective State Recognition Using Thermal-Based Imaging: A Survey

引用

computer Systems Science & Engineering 2021年第4期37卷 47-62页

作者： Mustafa M.M.Al Qudah Ahmad S.A.Mohamed Syaheerah L.Lutfi School of Computer Sciences Universiti Sains MalaysiaPenang11800Malaysia

The thermal-based imaging technique has recently attracted the attention of researchers who are interested in the recognition of human affects dueto its ability to measure the facial transient temperature, which is correlated withhuman affects and robustness against illumination changes. Therefore, studieshave increasingly used the thermal imaging as a potential and supplemental solution to overcome the challenges of visual (RGB) imaging, such as the variation oflight conditions and revealing original human affect. Moreover, the thermal-basedimaging has shown promising results in the detection of psychophysiological signals, such as pulse rate and respiration rate in a contactless and noninvasive way.This paper presents a brief review on human affects and focuses on the advantages and challenges of the thermal imaging technique. In addition, this paper discusses the stages of thermal-based human affective state recognition, such asdataset type, preprocessing stage, region of interest (ROI), feature descriptors,and classification approaches with a brief performance analysis based on a number of works in the literature. This analysis could help beginners in the thermalimaging and affective recognition domain to explore numerous approaches usedby researchers to construct an affective state system based on thermal imaging.

关键词： Thermal-based imaging affective state recognition spontaneous emotion feature extraction and classification

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

在线全文

在线全文

在线全文

在线全文

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

在线全文

在线全文

在线全文

在线全文

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：