检索结果-内蒙古大学图书馆

IEEE Transactions on artificial intelligence 2024年第3期5卷 1052-1066页

作者： Zhang, Shunli Yang, Laurence T. Zhang, Yue Lu, Zhixing Cui, Zongmin School of Computer and Big Data Science Jiujiang University Jiujiang332005 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Hainan University Haikou570228 China Department of Computer Science St. Francis Xavier University AntigonishNSB2G2W5 Canada

Imposing data-driven with physical laws for user activity prediction could effectively solve various physical problems such as smart care, surveillance, and human-robot. In the growing field of artificial intelligence, the application of activity prediction based on the physical coupled hidden Markov model (CHMM) and tensor theory with physical properties has attracted increasing attentions. However, existing CHMMs usually only consider the time-series characteristic of data, while ignoring physical characteristics of user activity such as periodicity, timing, and correlation. Moreover, they are all matrix-based models, which could not holistically analyze the dependencies among physical states. The aforementioned disadvantages lead to lower prediction accuracy of the CHMM. To remove these disadvantages, three physics-informed tensor-based CHMMs are first constructed by incorporating prior physical knowledge. Then, the corresponding forward-backward algorithms are designed for resolving the evaluation problem of the CHMM. These algorithms could overall model multiple physical features by imposing physics and prior knowledge into the CHMM during training to improve the precision of probabilistic computing. The algorithms reduce the dependence of the model on training data by adding physical features. Finally, the comparative experiments show that our algorithms have better performances than existing prediction methods in precision and efficiency. In addition, further self-comparison experiments verify that our algorithms are effective and practical. Impact Statement-Through the analysis of users' behavior habits, consumption habits, preferences, etc., users? potential needs may be discovered. This discovery could help predict users' activities. If a waiter predicts the user's next activity. He gives her/him unexpected services to meet users' next needs. Obviously, it would significantly improve user satisfaction. In addition, connecting the front and rear products co

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Text-Region Matching for Multi-Label Image Recognition with Missing Labels 24

Text-Region Matching for Multi-Label Image Recognition with ...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ma, Leilei Xie, Hongxing Wang, Lei Fu, Yanping Sun, Dengdi Zhao, Haifeng School of Computer Science and Technology Anhui University Anhui Hefei China School of Artificial Intelligence Anhui University Anhui Hefei China School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing China

ISBN: (纸本)9798400706868

Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with missing labels, leveraging VLP prompt-tuning technology. However, they usually cannot match text and vision features well, due to complicated semantics gaps and missing labels in a multi-label image. To tackle this challenge, we propose Text-Region Matching for optimizing Multi-Label prompt tuning, namely TRM-ML, a novel method for enhancing meaningful cross-modal matching. Compared to existing methods, we advocate exploring the information of category-aware regions rather than the entire image or pixels, which contributes to bridging the semantic gap between textual and visual representations in a one-to-one matching manner. Concurrently, we further introduce multimodal contrastive learning to narrow the semantic gap between textual and visual modalities and establish intra-class and inter-class relationships. Additionally, to deal with missing labels, we propose a multimodal category prototype that leverages intra- and inter-category semantic relationships to estimate unknown labels, facilitating pseudo-label generation. Extensive experiments on the MS-COCO, PASCAL VOC, Visual Genome, NUS-WIDE, and CUB-200-211 benchmark datasets demonstrate that our proposed framework outperforms the state-of-the-art methods by a significant margin. Our code is available here. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhanced DeepFake Detection Using CNN and EfficientNet-Based Ensemble Models for Robust Facial Manipulation Analysis 1

Enhanced DeepFake Detection Using CNN and EfficientNet-Based...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Das, Subhranil Kumari, Rashmi Tripathi, Utkarsh Parashar, Shivi Dubey, Adetya Yadav, Akanksha Singh, Raghwendra Kishore Dehradun India School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India School of Computer Science and Artificial Intelligence SR University Warangal India

ISBN: (纸本)9798331518578

Deepfakes are generally powered by Generative adversarial networks (GANs) that has been newly introduced a new dimension of realism in the manipulation of digital media particularly in some delicate features such as eyes, lips, and skin texture. These sophisticated manipulations pose significant threats to digital security, privacy, and trust in media. Detecting these alterations, especially in still images, has become a critical focus of research. This paper presents a Convolutional neural network (CNN)-based approach to detecting facial feature manip- ulations in deepfake images. Leveraging CNN architectures like ResNet, we focus on identifying subtle pixel-level inconsistencies in facial regions. Preprocessing steps, including face cropping, alignment, and normalization, are applied to enhance the model's focus on manipulated features. datasets such as Face Forensics++ are utilized for training and evaluation. Our model demonstrates a high level of accuracy in distinguishing real from fake images based on facial feature manipulations, outperforming baseline models in several key metrics, including precision and recall. The results highlight the effectiveness of CNNs in detecting fine- grained alterations and their potential for real-world application in combating deepfake threats. This research contributes to the ongoing efforts in deepfake detection by proposing a robust and scalable method to detect facial manipulations, ultimately enhancing the security and authenticity of digital media. Future work will explore the integration of multimodal detection tech- niques to further improve the robustness of the system. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective

Quantifying and Mitigating Unimodal Biases in Multimodal Lar...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Chen, Meiqi Cao, Yixin Zhang, Yan Lu, Chaochao State Key Laboratory of General Artificial Intelligence Peking University Beijing China School of Intelligence Science and Technology Peking University China School of Computer Science Fudan University China Shanghai Artificial Intelligence Laboratory China

ISBN: (纸本)9798891761681

Recent advancements in Large Language Models (LLMs) have facilitated the development of Multimodal LLMs (MLLMs). Despite their impressive capabilities, MLLMs often suffer from over-reliance on unimodal biases (e.g., language bias and vision bias), leading to incorrect answers in complex multimodal tasks. To investigate this issue, we propose a causal framework to interpret the biases in Visual Question Answering (VQA) problems. Within this framework, we conduct an in-depth causal analysis to assess the causal effect of these biases on MLLM predictions. Based on the analysis, we introduce 1) a novel MORE dataset with 12,000 challenging VQA instances requiring multi-hop reasoning and overcoming unimodal biases. 2) a causality-enhanced agent framework CAVE that guides models to comprehensively integrate information from different modalities and mitigate biases. Our experiments show that MLLMs perform poorly on MORE, indicating strong unimodal biases and limited semantic understanding. However, when integrated with our CAVE, promising improvements in reasoning and bias mitigation can be seen. These findings provide important insights for the development of more robust MLLMs and contribute to the broader goal of advancing multimodal AI systems capable of deeper understanding and reasoning. Our project page is at https://***/OpenCausaLab/MORE. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deconvolution of spatial transcriptomics data based on multi-head dynamic GAT and optimal transport

Deconvolution of spatial transcriptomics data based on multi...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Chen, Yuqi Yang, Feng Jiang, Peng Wang, Yuan Zhang, Qiang Liu, Juan Wuhan University Institute of Artificial Intelligence School of Computer Science Wuhan China

ISBN: (纸本)9798350386226

The majority of spatial transcriptomics datasets are characterized by low resolution, wherein each spot generally encompasses multiple cells. This limitation poses challenges for exploring biological insights at the cellular level. Consequently, the development and application of robust deconvolution methods for spatial transcriptomics data are imperative to address this challenge. Addressing the limitations of previous deconvolution methods - such as the lack of consideration cell type labels from single-cell sequencing data and the inability to adaptively capture local relationship among points - we propose a novel spatial transcriptomics data deconvolution model based on label-guided Multi-Head Dynamic Graph Attention Networks with Optimal Transport(MHDGATOT). Our approach leverages an advanced multi-head dynamic graph attention network to adaptively capture inter-data relationships and generate effective low-dimensional embeddings. Subsequently, we employ optimal transport based on fused gromov-wasserstein to derive the transport matrix between spatial transcriptomics data and single-cell sequencing data, facilitating the accurate deconvolution of spatial transcriptomics datasets. Experimental validation substantiates the effectiveness of our model. © 2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy Denoising Medical Imaging 11

Enhancing Diagnostic Accuracy Denoising Medical Imaging

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Mohmmad, Sallauddin Mahender, Nagurla Aaleti, Bharath Shashank, Adupa Niveditha, Rollankanti Laxmi Rahman, Mohammed Zeeshan Azeez Ur School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India

ISBN: (纸本)9798350350357

Medical image processing is faced with the challenge of accurate diagnosis founded on image noise, blurriness, and lack of proper preprocessing. In this paper, our model introduced various denoising techniques in medical image processing, from customary methods like Non-Local Means and Wavelet-Based Denoising to modern approaches such as autoencoders and the resultant images classified using the U-Net architecture. Autoencoders, akin to smart filters, exhibit assurance in efficiently annihilating unwanted artifacts while holding essential image features. The model's primary goal is to leverage autoencoders to enhance the clarity and Precision of medical image data and address challenges originating from image copying and quality loss. By utilizing U-Net neural networks, this analysis achieved an accuracy of 97.15%, Precision (97.87%), and recall (96.67%). © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Diffusion Priors for Variational Likelihood Estimation and Image Denoising 38

Diffusion Priors for Variational Likelihood Estimation and I...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Cheng, Jun Tan, Shan School of Artificial Intelligence and Automation Huazhong University of Science and Technology China

Real-world noise removal is crucial in low-level computer vision. Due to the remarkable generation capabilities of diffusion models, recent attention has shifted towards leveraging diffusion priors for image restoration tasks. However, existing diffusion priors-based methods either consider simple noise types or rely on approximate posterior estimation, limiting their effectiveness in addressing structured and signal-dependent noise commonly found in real-world images. In this paper, we build upon diffusion priors and propose adaptive likelihood estimation and MAP inference during the reverse diffusion process to tackle real-world noise. We introduce an independent, non-identically distributed likelihood combined with the noise precision (inverse variance) prior and dynamically infer the precision posterior using variational Bayes during the generation process. Meanwhile, we rectify the estimated noise variance through local Gaussian convolution. The final denoised image is obtained by propagating intermediate MAP solutions that balance the updated likelihood and diffusion prior. Additionally, we explore the local diffusion prior inherent in low-resolution diffusion models, enabling direct handling of high-resolution noisy images. Extensive experiments and analyses on diverse real-world datasets demonstrate the effectiveness of our method. Code is available at https://***/HUST-Tan/DiffusionVI. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Feature Fusion Detector Based on Graph Reasoning for Object Detection of Transmission Line External Force Damage Risk 42

A Feature Fusion Detector Based on Graph Reasoning for Objec...

引用

42nd Chinese Control Conference, CCC 2023

作者： Gong, Yilin Chen, Haiyong School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin300132 China

ISBN: (纸本)9789887581543

It is significant to accurately identify the risk target of external force damage to ensure the safe operation of transmission lines. The rapid development of cameras and UAVs provides a hardware basis for identifying the risk objects of external force damage. At the same time, the recent object detection networks have developed rapidly, providing methods for identifying these risk objects. However, in some networks, the fusion of features with different depths without processing will lead to the loss of small weak parts and confusion about similar features. In this paper, we propose a bidirectional stripe thinning module based on graph modeling and reasoning. It adaptively captures random spatial dependence and long-range channel dependence with directional information. Specifically, we designed a mechanism of shallow feature projection to effectively project spatial information into the graph space. The reasoning between graph nodes realizes the dynamic correlation of target-related features and improves the feature representation of small targets. In addition, we propose a new Feature Fusion Detector based on Graph Reasoning(FF-GR detector), which embeds Graph Inference modules based on Shallow Spatial Features (GISSF) in specific layers and achieves good performance. Finally, the experimental results show that the mAP0.5 of the FF-GR detector on the external risk data set reaches 80.2%, which is superior to the current advanced methods. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Phasmatodea Population Evolution Algorithm Based on Spiral Mechanism and Its Application to data Clustering

引用

computers, Materials & Continua 2025年第4期83卷 475-496页

作者： Jeng-Shyang Pan Mengfei Zhang Shu-Chuan Chu Xingsi Xue Václav Snášel College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao266590China School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China Department of Information Management Chaoyang University of TechnologyTaichung41349TaiwanChina Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou350118China Faculty of Electrical Engineering and Computer Science VŠB-Technical University of OstravaOstrava70833Czech Republic

data clustering is an essential technique for analyzing complex datasets and continues to be a central research topic in data *** clustering algorithms,such as K-means,are widely used due to their simplicity and *** paper proposes a novel Spiral Mechanism-Optimized Phasmatodea Population Evolution Algorithm(SPPE)to improve clustering *** SPPE algorithm introduces several enhancements to the standard Phasmatodea Population Evolution(PPE)***,a Variable Neighborhood Search(VNS)factor is incorporated to strengthen the local search capability and foster population ***,a position update model,incorporating a spiral mechanism,is designed to improve the algorithm’s global exploration and convergence ***,a dynamic balancing factor,guided by fitness values,adjusts the search process to balance exploration and exploitation *** performance of SPPE is first validated on CEC2013 benchmark functions,where it demonstrates excellent convergence speed and superior optimization results compared to several state-of-the-art metaheuristic *** further verify its practical applicability,SPPE is combined with the K-means algorithm for data clustering and tested on seven *** results show that SPPE-K-means improves clustering accuracy,reduces dependency on initialization,and outperforms other clustering *** study highlights SPPE’s robustness and efficiency in solving both optimization and clustering challenges,making it a promising tool for complex data analysis tasks.

关键词： Phasmatodea population evolution algorithm data clustering meta-heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cybersecurity: A Deep Learning Strategy for Phishing Website Detection 2

Enhancing Cybersecurity: A Deep Learning Strategy for Phishi...

引用

2nd International Conference on data science and Information System, ICDSIS 2024

作者： Sravan, Padala Vardhan, Thangellapelli Harsha Sanjana, Gabbeta Sai Sowmya, Boinpelly Bhavana, Gottimukkula Parvez, Mohammed Ashpaak Sr University School Of Computer Science & Artificial Intelligence Telangana Warangal India

ISBN: (纸本)9798350381665

Phishing remains a critical threat to individuals' sensitive information in this era of digital security. This approach deceives people to enter their personal information on malicious websites, thus contributing to various digital crimes. The current study explores sophisticated machine learning techniques, notably Multi-Layer Perceptron's, to detect phishing with three times the tracking precision. We used an engineered dataset containing both phishing and legitimate URLs and trained the MLP model on stringent features. It based its methodology on various MLP architecture adjustments, layer configurations, and learning rates to track the phishing to a three-time better level than the traditional rule-based systems. The outcomes showed the increased phishing detection levels of the MLP model over traditional rule-based systems. Therefore, MLPs have impressive potential in cybersecurity, guaranteeing the protection of digital activity from various phishing attacks. The study effectively encapsulates the research, highlighting the MLP's superior capability as a sophisticated tool in the cybersecurity arsenal. © 2024 IEEE.

关键词： Cybersecurity

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：