检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Qingao Wang Xingang Wang Jinxiao Yang Yurun Bi Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Multimodal sentiment analysis(MSA) aims to synthesize multiple pieces of information, including textual, visual, and auditory information, to more accurately infer sentiment polarity. Due to the existence of complex and diverse affective causal relationships between different modalities, they interact with each other and constitute a multidimensional expression of human emotions. In the face of unbalanced data, i.e., when there are significant differences in the number of samples between different categories, the attention mechanism of the model tends to focus on spurious correlations in the training data, seriously impairing the model’s generalization ability and leading to bias, unbalanced prediction, and false correlation identification problems. To address the above problems, this study proposes a new multimodal fusion method based on the "within-sample sampling" and "cross-sample sampling" front door adjustment methods in causal inference strategies: the multi-head causal attention fusion method (MCAF). This method aims to capture potential causal relationships between different modalities through different attention heads, helping the model focus more on key causal features and avoid paying too much attention to false correlations in the training data. This helps improve the generalization performance of the model, make the decision-making process of the model more interpretable, and enhance the accuracy and robustness of the model for multimodal sentiment analysis tasks, making it more suitable for practical application scenarios.

关键词： Analytical models Sentiment analysis Visualization Correlation Neural networks Training data Predictive models

来源：评论

学校读者我要写书评

暂无评论

TSFE: Research on Transformer and Feature Enhancement Methods for Image-Text Retrieval

TSFE: Research on Transformer and Feature Enhancement Method...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Jinxiao Yang Xingang Wang Qingao Wang Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In recent years, cross-modal retrieval has a wide range of applications in fields such as information retrieval and multimedia processing, where the key is to find relevant data in another modality through one modal query. In cross-modal graphic retrieval, mutual attention mechanisms are commonly used to interact image and text features. However, this interaction mechanism makes it difficult to extract separate visual and textual features for subsequent indexing steps, especially in large-scale retrieval tasks. Furthermore, in image representation, non-semantic information in image features can lead to inaccuracies in the alignment of image and text features. Therefore this paper proposes a Transformer and Feature Enhancement Method (TSFE) for Image-Text Retrieval. The method better fuses the underlying features and the higher level features by using a hierarchical Transformer coding structure on two separate branches, image and text, to proofread and localise the final output features. The Feature Enhanced Attention (FEA) module is designed in order to infer non-semantic information in the image and enhance the features of salient regions. Channel-space attention and max pooling is introduced on top of Transformer encoder self-attention to filter redundant and interfering information from channel and spatial dimensions. Experiments on Flickr30k dataset and MS-COCO dataset in this paper show improved performance in cross-modal retrieval, thus validating the effectiveness and sophistication of the proposed method.

关键词： Visualization Semantics Pipelines Noise Image representation Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

LESaET: Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER

LESaET: Low-Dimensional Embedding Method for Link Prediction...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Lichao Ding Jing Zhao Kai Lu Zenghao Hao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Knowledge graphs (KGs) provide a structured representation of the real world through entity-relation triples. However, current KGs are often incomplete, typically containing only a small fraction of all possible facts. This involves inferring missing content from existing information, a task known as link prediction. Existing methods in the field of link prediction struggle with controlling the dimensionality of embedding vectors or suffer from overly complex models. In order to tackle these challenges, we introduce a method in this paper, named Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER (LESaET). LESaET leverages both self-attention mechanisms and tensor factorization to learn expressive contextual-enhanced representations of KGs. Specifically, LESaET employs the multi-head self-attention mechanism of Transformer as an encoder to capture the mutual information between entities and relationships, and utilizes Enhanced-TuckER as a decoder, ultimately achieving expressive low-dimensional embeddings for link prediction tasks. LESaET demonstrates competitive performance compared to advanced methods on standard datasets.

关键词： Tensors Stacking Knowledge graphs Predictive models Transformers Vectors Decoding Standards Mutual information Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Overcoming Data Limitations and Cross-Modal Interaction Challenges in Medical Visual Question Answering

Overcoming Data Limitations and Cross-Modal Interaction Chal...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yurun Bi Xingang Wang Qingao Wang Jinxiao Yang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Medical Visual Question Answering (Med-VQA) is a sophisticated multimodal technology within the medical domain that utilizes natural language processing and artificial intelligence techniques. It serves as a tool in the medical field to provide information and answers, aiming to correctly respond to medical questions related to specific professional medical images. The primary goal is to assist patients in understanding their physical condition and provide decision support for healthcare professionals. While Generalized Visual Question Answering has seen significant advancements, challenges persist in the medical domain. Firstly, medical data has inherent limitations, such as the scarcity of annotated medical datasets and the complexity of medical images (including factors like noise, artifacts, and low contrast). Secondly, in terms of cross-modal fusion, there exists an intricate relationship between medical images and textual information. The complexity of the relationship between medical images and medical text, as well as the incorporation of global contextual details, pose challenges. To address these issues, this paper proposes the Feature-Enhanced Network with Conditional Mixing. This innovative approach aims to overcome the scarcity and complexity of medical images without the need for additional datasets. Simultaneously, to tackle the challenge of cross-modal fusion and information interaction and to address the complex relationship between medical images and text, we propose the Cross-Adaptive Fusion Network. Experimental results conducted on the VQA-RAD dataset demonstrate noticeable improvements in accuracy compared to mainstream Med-VQA models.

关键词： Visualization Accuracy Noise Neural networks Medical services Question answering (information retrieval) Data models

来源：评论

学校读者我要写书评

暂无评论

RAC-Based One-Stop Professional Course Teaching Model Exploration and Practice - Taking the Course of "Microcomputer Principles and Interface Technology" as an Example 6th

RAC-Based One-Stop Professional Course Teaching Model Explor...

引用

6th International Conference on computer science and Educational Informatization, CSEI 2024

作者： Wan, Xiaorong Li, Yingna Luo, Chuan Li, Chuan You, Jinguo Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Computer Technology Applications Kunming650500 China

ISBN: (纸本)9789819637379

In the context of the country’s requirement for academic disciplines to be aligned and mutually reinforcing with industry chains, innovation chains, and talent chains, the integration of education and industry has become an important direction for the reform of higher education. In response to the iterative demand for edge intelligence in the Intelligent Internet of Things (AIOT), the course "Microcomputer Principles and Interface Technology" is deeply integrated with industry and education, establishing a hierarchical model of resource, capability, and commercialization (RAC) layers. It adopts a "one-stop" teaching mainline that starts with microcomputer theory knowledge, relies on hardware development boards, project orientation, competition innovation, and product commercialization training "five points and one line", connects knowledge product channels, integrates ideological and political education in courses, and constructs a multi-dimensional and comprehensive evaluation system to achieve the integration of industry and education from universities to enterprises, classrooms to markets, and from knowledge to products. The innovative teaching mode of this course has achieved significant results in innovative practice. This innovative teaching mode can effectively achieve the knowledge, ability, and quality goals of cultivating new engineering talents, and effectively improve the quality of talent cultivation and teaching. This teaching reform and innovation provide a reference and idea for further exploring the talent cultivation mode of schools and enterprises. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Opinion-Tree-guided Contrastive Learning for Aspect Sentiment Quadruple Prediction

Opinion-Tree-guided Contrastive Learning for Aspect Sentimen...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Zhijun Li Zhenyu Yang Yiwen Li Xiaoyang Li Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In recent years, aspect sentiment quadruple prediction (ASQP) has become a popular task in the field of aspect-based sentiment analysis. When modeling comment statements, it is often necessary to consider structural information between sentiment labels. Existing approaches categorize these labels by encoding text and dependency tree structures separately and then incorporating their representations, but this approach fails to effectively capture the structural information between sentiment labels. To address this problem, we propose a method for ASQP called Opinion-Tree-guided Contrastive Learning (OTCL), which embeds structural information directly into the text instead of modeling it separately. Specifically, OTCL utilizes the opinion tree structure to guide the construction of positive samples of the input text during training. By associating the input text with its positive samples, the text encoder can learn to generate textual representations associated with the opinion tree structure. We validate the effectiveness of our method on two commonly used datasets.

关键词： Training Sentiment analysis Federated learning Contrastive learning Predictive models Encoding Task analysis

来源：评论

学校读者我要写书评

暂无评论

Gamification using Octalysis Framework in Knowledge Management System for Vocational High Schools during the Covid-19 Pandemic

Gamification using Octalysis Framework in Knowledge Manageme...

引用

International Conference on Informatics and Computing (ICIC)

作者： Mgs. Afriyan Firdaus Dwi Rosa Indah Yoppy Sazaki Eka Prasetyo Ariefin Muhammad Fachri Nuriza Muhammad Rafly Information System Department Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia Data Structure and Accounting Information System Laboratory Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia Informatics Management Department Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia

ISBN: (纸本)9798350345728

Knowledge management systems enable teachers and students to interact directly in the knowledge transfer process during the Covid-19 pandemic. In addition, applying the gamification concept in vocational disciplines could enhance the quality of teaching to increase motivation and student learning outcomes which tend to decline. Octalysis Framework, which supports the gamification concept, consists of eight cores that focus on creativity, self-expression, social dynamics, logic, thinking, and ownership depicted in an octagon making an application more fun and helpful to motivate users to enjoy and be involved in an activity. This condition is crucial and urgent in the Covid-19 pandemic that requires online and student-centered learning. This study discussed the application of Octalysis Framework-based Gamification in a computer Learning Knowledge Management system in Vocational High Schools during the Covid-19 Pandemic. The Gamification concept with the Octalysis Framework was implemented in the Knowledge Management System. Some game mechanics in a non-game context consisting of four phases, namely the Discovery, Onboarding, Scaffolding, and Endgame was applied to improve student performance and motivation in learning. Meanwhile, The Knowledge Management System software achieved an overall quality score of 5.14 out of 6 (85.6 percent of quality achieved) covering functionality, reliability, usability, efficiency, maintainability, and portability characteristics of the ISO 9126 quality indicator.

关键词： COVID-19 Pandemics ISO Standards Games Knowledge management System software Software reliability

来源：评论

学校读者我要写书评

暂无评论

HGTA: News Recommendation Based on Hierarchical Granular Semantic Embeddings and Threshold Attention

HGTA: News Recommendation Based on Hierarchical Granular Sem...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yiwen Li Zhenyu Yang Zhijun Li Xiaoyang Li Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Personalized news recommendation helps users find interesting content among much news information. Most existing news recommendation techniques densely interact a user’s historical clicked news with candidate news to capture their reading interest. However, during this process, even if certain historical clicked news is weakly correlated with the candidate news, the model still interacts with it, generating more noise information when constructing user interests. Simultaneously, the news representation learning process using neural networks is a fine-grained to coarse-grained learning process; i.e., as the network deepens, the fine-grained original news information is easily lost. Therefore, to solve the above problems, this paper proposes a news recommendation model based on hierarchical granular semantic embeddings and threshold attention (HGTA). In HGTA, we propose a threshold attention module to filter unimportant historical clicked news by setting an attention score threshold, i.e., interacting only with historical clicked news that is strongly correlated with the candidate news when capturing user interests. Thus, the model attention is focused, and the noisy interaction information is reduced. Furthermore, when training the neural network, to prevent the loss of fine-grained information, we design a hierarchical granular information extraction module to capture both coarse- and fine-grained news features to better enrich the news semantics. Experiments conducted on the large real-world Microsoft News Dataset (MIND) show that our model achieves highly competitive results in terms of popular metrics. Our code is published at the following URL: https://***/liyiweneven/HGTA.

关键词： Uniform resource locators Training Representation learning Federated learning Semantics Neural networks Noise

来源：评论

学校读者我要写书评

暂无评论

Unknown-Aware Bilateral Dependency Optimization for Defending Against Model Inversion Attacks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Peng, Xiong Liu, Feng Wang, Nannan Lan, Long Liu, Tongliang Cheung, Yiu-Ming Han, Bo Hong Kong Baptist University Department of Computer Science Hong Kong The University of Melbourne School of Computing and Information Systems Australia Xidian University State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Shaanxi Xi'an710071 China National University of Defense Technology State Key Laboratory of High Performance Computing School of Computer Hunan Changsha410000 China The University of Sydney Sydney AI Centre School of Computer Science Faculty of Engineering Australia

By abusing access to a well-trained classifier, model inversion (MI) attacks pose a significant threat as they can recover the original training data, leading to privacy leakage. Previous studies mitigated MI attacks by imposing regularization to reduce the dependency between input features and outputs during classifier training, a strategy known as unilateral dependency optimization. However, this strategy contradicts the objective of minimizing the supervised classification loss, which inherently seeks to maximize the dependency between input features and outputs. Consequently, there is a trade-off between improving the model's robustness against MI attacks and maintaining its classification performance. To address this issue, we propose the bilateral dependency optimization strategy (BiDO), a dual-objective approach that minimizes the dependency between input features and latent representations, while simultaneously maximizing the dependency between latent representations and labels. BiDO is remarkable for its privacy-preserving capabilities. However, models trained with BiDO exhibit diminished capabilities in out-of-distribution (OOD) detection compared to models trained with standard classification supervision. Given the open-world nature of deep learning systems, this limitation could lead to significant security risks, as encountering OOD inputs—whose label spaces do not overlap with the in-distribution (ID) data used during training-is inevitable. To address this, we leverage readily available auxiliary OOD data to enhance the OOD detection performance of models trained with BiDO. This leads to the introduction of an upgraded framework, unknown-aware BiDO (BiDO+), which mitigates both privacy and security concerns. As a highlight, with comparable model utility, BiDO-HSIC+ reduces the FPR95 by 55.02% and enhances the AUCROC by 9.52% compared to BiDO-HSIC, while also providing superior MI robustness. © 1979-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping

arXiv

引用

arXiv 2024年

作者： Lin, Qinliang Luo, Cheng Niu, Zenghao He, Xilin Xie, Weicheng Hou, Yuanbo Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Key Laboratory of Intelligent Information Processing China WAVES Research Group Ghent University Belgium University of Leicester United Kingdom

Adversarial examples generated by a surrogate model typically exhibit limited transferability to unknown target systems. To address this problem, many transferability enhancement approaches (e.g., input transformation and model augmentation) have been proposed. However, they show poor performances in attacking systems having different model genera from the surrogate model. In this paper, we propose a novel and generic attacking strategy, called Deformation-Constrained Warping Attack (DeCoWA), that can be effectively applied to cross model genus attack. Specifically, DeCoWA firstly augments input examples via an elastic deformation, namely Deformation-Constrained Warping (DeCoW), to obtain rich local details of the augmented input. To avoid severe distortion of global semantics led by random deformation, DeCoW further constrains the strength and direction of the warping transformation by a novel adaptive control strategy. Extensive experiments demonstrate that the transferable examples crafted by our DeCoWA on CNN surrogates can significantly hinder the performance of Transformers (and vice versa) on various tasks, including image classification, video action recognition, and audio recognition. Code is made available at https://***/LinQinLiang/DeCoWA. © 2024, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：