检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Ouxiang Hao, Yanbin Wang, Zhicai Zhu, Bin Wang, Shuo Zhang, Zaixi Feng, Fuli School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China School of Computing and Information Systems Singapore Management University Singapore School of Information Science and Technology University of Science and Technology of China Hefei China Department of Computer Science and Engineering University of Science and Technology of China Hefei China

Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. To alleviate these issues, leveraging on diffusion models' remarkable synthesis capabilities, we propose Diffusion-based Model Inversion (Diff-MI) attacks. Specifically, we introduce a novel target-specific conditional diffusion model (CDM) to purposely approximate target classifier's private distribution and achieve superior accuracy-fidelity balance. Our method involves a two-step learning paradigm. Step-1 incorporates the target classifier into the entire CDM learning under a pretrain-thenfinetune fashion, with creating pseudo-labels as model conditions in pretraining and adjusting specified layers with image predictions in fine-tuning. Step-2 presents an iterative image reconstruction method, further enhancing the attack performance through a combination of diffusion priors and target knowledge. Additionally, we propose an improved max-margin loss that replaces the hard max with top-k maxes, fully leveraging feature information and soft labels from the target classifier. Extensive experiments demonstrate that Diff-MI significantly improves generative fidelity with an average decrease of 20% in FID while maintaining competitive attack accuracy compared to state-of-the-art methods across various datasets and models. Our code is available at: https://***/Ouxiang-Li/Diff-MI. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Solving Multivariate Polynomial Matrix Diophantine Equations with Gr?bner Basis Method

引用

Journal of Systems science & Complexity 2022年第1期35卷 413-426页

作者： XIAO Fanghui LU Dong WANG Dingkang College of Mathematics and Statistics Hunan Normal UniversityChangsha 410006China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing 100191China School of Mathematical Sciences Beihang UniversityBeijing 100191China. KLMM Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China

Different from previous viewpoints,multivariate polynomial matrix Diophantine equations are studied from the perspective of modules in this paper,that is,regarding the columns of matrices as elements in modules.A necessary and sufficient condition of the existence for the solution of equations is *** powerful features and theoretical foundation of Gr?bner bases for modules,the problem for determining and computing the solution of matrix Diophantine equations can be ***,the authors make use of the extension on modules for the GVW algorithm that is a signature-based Gr?bner basis algorithm as a powerful tool for the computation of Gr?bner basis for module and the representation coefficients problem directly related to the particular solution of *** a consequence,a complete algorithm for solving multivariate polynomial matrix Diophantine equations by the Gr?bner basis method is presented and has been implemented on the computer algebra system Maple.

关键词： Gr?bner basis matrix Diophantine equation module multivariate polynomial

来源：评论

学校读者我要写书评

暂无评论

LLM Based Cross Modality Retrieval to Improve Recommendation Performance

LLM Based Cross Modality Retrieval to Improve Recommendation...

引用

International Conference on Automation and computing (ICAC)

作者： Fahad Anwaar Adil Mehmood Khan Muhammad Khalid Ammad Khalil Muhammad Awais Centre of Excellence for Data Science Artificial Intelligence and Modelling (DAIM) University of Hull Hull U.K. School of Computer Science University of Hull Hull U.K. University of Education Lahore Pakistan School of Computing Science University of East Anglia UK

ISBN: (数字)9798350360882

ISBN: (纸本)9798350360899

The metadata of items and users play an important role in improving the decision-making process in the Recommender System. In recent times, web scraping-based techniques have been widely utilized to extract explicit user and item meta-data from different social platforms to improve recommendation performance. Currently, Large Language Models (LLMs) have the great potential to replace the traditional web scraping-based paradigm in Recommender Systems. In this paper, we investigated the impact of LLMs and web scraping-based extraction of explicit data on the performance of the Recommender System. Firstly, a cross-modality retrieval-based LLM Gemini is explored to generate semantically enriched textual descriptions of items from digital images. The Gemini LLM is prompted with few-shot prompting on the MovieLens dataset to generate a textual description of movies based on the corresponding movie poster. Secondly, the textual descriptions for each movie in the MovieLens dataset are scraped from the OMDB API. Finally, the cross-modality retrieval-based and scraping-based textual descriptions of items are incorporated into a hybrid Recommender System to assess the quality of explicit data in terms of recommendation performance. The experimental results on the MovieLens dataset demonstrate that LLM-generated content is more effective, achieving a 0.5134 RMSE in enhancing the performance of the Recommender System.

关键词： Measurement Accuracy TV Digital images Large language models Text to image Manuals Metadata Motion pictures Recommender systems

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Hypergraph-Based Convolution Network with Dual Spatiotemporal Attention for Pm2.5 Forecasting

SSRN

引用

SSRN 2025年

作者： Gao, Haipeng Qian, Chonghui Su, Yang Zhang, Wei Huang, Hengjun School of Statistics and Data Science Lanzhou University of Finance and Economics Lanzhou730020 China Key Laboratory of Digital Economy and Social Computing Science of Gansu Lanzhou730020 China School of Computer and Cyber Sciences Augusta University AugustaGA United States

Accurate PM2.5 prediction is crucial for effective environmental management and public health protection, particularly given the severe risks posed by extreme and heavy air pollution to human society and the environment. This is particularly important during significant fluctuations, where rapid-response ecological measures are essential. However, existing models predominantly rely on predefined graph structures and pairwise spatial relationships, limiting their ability to capture the complex and dynamic interactions inherent in PM2.5 pollution. Furthermore, such models often assume equal contributions from neighboring nodes, neglecting heterogeneity and compromising predictive accuracy. To address these limitations, we propose an Adaptive Hypergraph-based Convolution Network with a Dual Spatiotemporal Attention mechanism (AHCNA-DA) for PM2.5 forecasting. This framework leverages representation learning and hypergraph structures to capture and integrate pairwise as well as higher-order spatial interactions, producing richer spatial-feature representations. The dual spatiotemporal attention mechanism dynamically assigns time-varying weights to neighboring nodes based on their relevance to target nodes, effectively mitigating the impact of irrelevant inputs. Additionally, AHCNA-DA integrates a dilated convolution network with multi-scale kernels to capture temporal patterns effectively across varying scales. Extensive experiments on the 2023 China National Air Quality dataset show significant improvements in predictive accuracy, especially for stronger fluctuations, with an R2 of 0.9224, outperforming baseline models. Our findings underscore the effectiveness of AHCNA-DA in enhancing PM2.5 prediction accuracy, contributing to more informed decision-making in environmental management. © 2025, The Authors. All rights reserved.

关键词： Direct air capture

来源：评论

学校读者我要写书评

暂无评论

Causal association of modifiable factors with cardiometabolic multimorbidity: an exposome-wide Mendelian randomization investigation

引用

Cardiovascular Diabetology 2025年第1期24卷 1-16页

作者： Li, Dun Lin, Jing Yang, Hongxi Zhou, Lihui Li, Yujian Xu, Zhe Sun, Li Zhang, Xinyu Xu, Weili Wang, Yaogang School of Public Health Tianjin Medical University Tianjin 300070 China School of Nursing Tianjin Medical University Tianjin 300070 China School of Basic Medical Sciences Tianjin Medical University Tianjin 300070 China School of Integrative Medicine Public Health Science and Engineering College Tianjin University of Traditional Chinese Medicine Tianjin 301617 China Aging Research Center Department of Neurobiology Health Care Sciences and Society Karolinska Institutet Stockholm University Stockholm 17165 Sweden National Institute of Health Data Science at Peking University Peking University Beijing 100191 China

Background: Cardiometabolic multimorbidity (CMM), characterized by the co-existence of two or more cardiometabolic diseases (CMDs) including type 2 diabetes (T2D), coronary artery disease (CAD), and stroke, persists as a global health challenge. However, the causal associations of modifiable factors with CMDs and CMM remains to be systematically investigated. Methods: In this study, a three-stage design Mendelian randomization (MR) investigation was conducted, using two-sample MR with potential sample overlap correction and multiple testing, multivariable MR analysis, and multi-response MR, with modifiable factors covering domains of socioeconomic factors, behavioral factors, biochemical factors, and physical measures as exposures, and CMM and CMDs as outcomes. Updated large-scale genome-wide association study (GWAS) data based on systematic collection from GWAS Catalog were applied. Results: Our major findings suggested that, 13 of 23 modifiable factors across four domains, including educational attainment (odds ratio: 0.858, 95% confidence interval: 0.834–0.883), household income (0.794, 0.720–0.875), lifetime smoking behavior (1.201, 1.145–1.260), leisure screen time (1.255, 1.186–1.327), low-density lipoprotein cholesterol levels (1.062, 1.046–1.079), total cholesterol levels (1.045, 1.029–1.062), Apolipoprotein B (1.035, 1.019–1.051), fasting glucose (1.096, 1.038–1.157), glycated hemoglobin (HbA1c) (1.062, 1.037–1.089), systolic blood pressure (1.125, 1.104–1.146), diastolic blood pressure (1.104, 1.083–1.126), forced expiratory volume in 1 s (FEV₁) (0.953, 0.931–0.975), and body mass index (BMI) (1.243, 1.210–1.277) were evaluated with relatively robust effects on CMM. Furthermore, household income, lifetime smoking behavior, HbA1c, systolic blood pressure, and FEV₁ with CMM were detected as independent associations within a single domain. Similar results were observed in each CMD. Moreover, the multi-response MR provided reinforcing evi

关键词： Cardiometabolic diseases Cardiometabolic multimorbidity Causal inference Mendelian randomization Modifiable factor

来源：评论

学校读者我要写书评

暂无评论

AI Applications in Medical Reporting and Diagnosis

AI Applications in Medical Reporting and Diagnosis

引用

Mobile, Intelligent, and Ubiquitous computing Conference (MIUCC), International

作者： Manal Makram Ammar Mohammcd Department of Data Science FGSSR Cairo University Cairo Egypt Dept. of CS FGSSR Cairo University School of Computing and Digital Tech ESLSCA University Cairo Egypt

ISBN: (数字)9798350367775

ISBN: (纸本)9798350367782

The integration of artificial intelligence (AI) in healthcare is revolutionizing diagnosis and patient care by improving clinical documentation and the management of electronic health records that depend on medical image interpretation, increasing accuracy, and reducing time. Egypt ranks first in liver disease and second in liver cancer mortality worldwide in 2020. Large language models, a subset of AI techniques, can assist in disease diagnosis. LLM models with multimodal capabilities can classify and describe patient scan images and extract information from clinical notes. These models can extract vital diagnoses with the support of prompt engineering, as one of these models can answer questions, summarize information, and translate complex medical terminology into plain language, enabling patients to understand their medical reports and diagnoses. There are two primary approaches to achieving this. First, fine-tuning can adapt the model to medical data, which can be resource-intensive. The second approach, pre-trained LLM models can be utilized to leverage pre-trained models to perform the necessary tasks, focusing on effectively using prompts to guide the model for precise and relevant outputs. This study highlights the role of generative AI models by focusing on prompt engineering, and how carefully crafting prompts can enhance the effectiveness of LLM models in medical applications with high accuracy. It demonstrates this through experiments using pre-trained models based on semantic similarity with GPT-4o and BioGPT. Implementing a zero-shot model for liver tumor classification is one of the prompt engineering techniques. The performance metrics achieved were impressive, accuracy, precision, recall, and F1-scores are 88, 81, 88, and 83 percent, respectively.

关键词： Adaptation models Accuracy Biological system modeling Computational modeling Focusing Ubiquitous computing Prompt engineering data mining Medical diagnostic imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

A Survey on Usage of Multimedia databases for Emotion Elicitation: A Quantitative Report on How Content Diversity Can Improve Performance

A Survey on Usage of Multimedia Databases for Emotion Elicit...

引用

Proceedings of the International Convention MIPRO

作者： M. Horvat P. Jerčić Department of Applied Computing Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Graz University of Technology Institute of Interactive Systems and Data Science Graz Austria

Affective picture databases provide a standardized set of images to elicit controlled and consistent emotional responses in research participants. They are a valuable tool for studying various emotion-related phenomena across several research domains. These domains include emotion perception, emotion regulation, and the neural basis of emotion. However, affective picture databases have diverse schemas, structures, and content, making them difficult to use. Searching and retrieving optimal pictures relevant to affective stimulation may be challenging and time-consuming. In this context, we surveyed domain experts about their practices and experiences working with affective multimedia databases such as IAPS, NAPS, OASIS, GAPED, and others. The survey identified a need for novel data observatory software. This finding motivates the authors’ intention to develop and validate such software platform that relies on AI. Such a platform would describe better, retrieve, and integrate various semi-structured affective multimedia datasets. The results prominently indicate the overwhelming dissatisfaction regarding stimuli content diversity and cultural bias, specifically regarding emotional and semantic context. The main driver of satisfaction from users of existing automated retrieval software is the quality of semantic descriptors available. This points to the direction AI should take in novel data observatory software. This survey follows up on a similar survey conducted ten years ago and explores the differences in researchers’ opinions and experiences during that time. The complete aggregated results are publicly available at https://***/mhorvat/stimdbsurvey.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech

arXiv

引用

arXiv 2024年

作者： Liu, Rui He, Shuwei Hu, Yifan Li, Haizhou Inner Mongolia University China Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore

Visual Text-to-Speech (VTTS) aims to take the environmental image as the prompt to synthesize the reverberant speech for the spoken content. The challenge of this task lies in understanding the spatial environment from the image. Many attempts have been made to extract global spatial visual information from the RGB space of an spatial image. However, local and depth image information are crucial for understanding the spatial environment, which previous works have ignored. To address the issues, we propose a novel multi-modal and multi-scale spatial environment understanding scheme to achieve immersive VTTS, termed M2SE-VTTS. The multi-modal aims to take both the RGB and Depth spaces of the spatial image to learn more comprehensive spatial information, and the multi-scale seeks to model the local and global spatial knowledge simultaneously. Specifically, we first split the RGB and Depth images into patches and adopt the Gemini-generated environment captions to guide the local spatial understanding. After that, the multi-modal and multi-scale features are integrated by the local-aware global spatial understanding. In this way, M2SE-VTTS effectively models the interactions between local and global spatial contexts in the multi-modal spatial environment. Objective and subjective evaluations suggest that our model outperforms the advanced baselines in environmental speech generation. The code and audio samples are available at: https://***/AI-S2-Lab/M2SE-VTTS. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Zarankiewicz's Problem for Intersection Hypergraphs of Geometric Objects

arXiv

引用

arXiv 2024年

作者： Chan, Timothy M. Keller, Chaya Smorodinsky, Shakhar Siebel School of Computing and Data Science University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Computer Science Ariel University Israel Department of Computer Science Ben-Gurion University of the NEGEV Be'er Sheva84105 Israel

The hypergraph Zarankiewicz's problem, introduced by Erdős in 1964, asks for the maximum number of hyperedges in an r-partite hypergraph with n vertices in each part that does not contain a copy of Kt,t, ...,t. Erdős obtained a near optimal bound of O(nr−1/tr−1) for general hypergraphs. In recent years, several works obtained improved bounds under various algebraic assumptions - e.g., if the hypergraph is semialgebraic. In this paper we study the problem in a geometric setting - for r-partite intersection hypergraphs of families of geometric objects. Our main results are essentially sharp bounds for families of axis-parallel boxes in Rd and families of pseudo-discs. For axis-parallel boxes, we obtain the sharp bound Od,t(nr−1( log n/log log n)d−1). The best previous bound was larger by a factor of about (log n)d(2r−1−2). For pseudo-discs, we obtain the bound Ot(nr−1(log n)r−2), which is sharp up to logarithmic factors. As this hypergraph has no algebraic structure, no improvement of Erdős' 60-year-old O(nr−1/tr−1) bound was known for this setting. Futhermore, even in the special case of discs for which the semialgebraic structure can be used, our result improves the best known result by a factor of Ω˜(n2r-2/3r-2). To obtain our results, we use the recently improved results for the graph Zarankiewicz's problem in the corresponding settings, along with a variety of combinatorial and geometric techniques, including shallow cuttings, biclique covers, transversals, and *** Codes 05C35, 05C65 Copyright © 2024, The Authors. All rights reserved.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Variable Window Attention Network for Continuous Sign Language Recognition

Multi-scale Variable Window Attention Network for Continuous...

引用

2024 International Conference on Cyber-Physical Social Intelligence, ICCSI 2024

作者： Zhang, Nan Wei, Chao Guo, Leming Cheng, Zeyu Zhao, Zhao Wu, Yangcan Xue, Wanli Tianjin University of Technology School of Computer Science and Engineering Tianjin China Tianjin Emergency Centre Tianjin China Tianjin University of Technology School of Mechanical Engineering Tianjin China Shaanxi Big Data Group Co. Ltd Shaanxi China Industry Research Institute Co Shaanxi Logistics Group Shaanxi China

ISBN: (纸本)9798350376739

Sign language is primarily conveyed through hands and face movements. Therefore, a pivotal challenge in continuous sign language recognition (CSLR) is the meticulous modeling and interpreting of visual cues emanating from hands and facial movements. However, contemporary CSLR methods have exhibited limitations in adequately capturing information from both the hands and facial regions, often overlooking the continuity, and correlations across multiple consecutive frames. To mitigate these shortcomings, we propose the Multi-scale Variable Window Attention Network (MVAN). This framework fuses the strengths of an improved Efficient Multi-scale Attention (iEMA) with Variable Window Adaptation (VWA) attention. Specifically, iEMA first scans information spatially at multiple scales to simultaneously capture information from areas such as hands and faces, and models spatial continuity interactions between them, enhancing spatial features. Secondly, VWA dynamically changes its window size at the temporal level to adaptively capture complex temporal changes in hands and face movements in successive frames. Thus, VWA can effectively model the continuity and correlation between hands and face movements to have the ability to capture sign language movements of different lengths. Comprehensive experimental results demonstrate that our proposed MVAN strengthens the visual feature extraction of hands and face, improving the recognition performance. © 2024 IEEE.

关键词： Convolutional neural networks

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：