检索结果-内蒙古大学图书馆

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

Chinese Journal of Electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Aerial Image Object Detector Based on Mask Information Enhancement

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Zhou, Liming Zhao, Shuai Liu, Zhehao Zhang, Wanjun Qiao, Baojun Liu, Yang Henan University Henan Key Laboratory of Big Data Analysis and Processing Henan Kaifeng China Henan University School of Computer and Information Engineering Henan Kaifeng China

Object detection in UAV imagery is highly valuable in both military and civilian domains. However, deploying conventional detectors is challenging due to limited computing resources on UAV platforms. Additionally, UAV images often contain densely arranged objects, demanding higher accuracy from detectors. In response to these challenges, we proposed the lightweight aerial object detection method based on mask feature enhancement, named BFDet. First, to enhance the feature extraction capability of the model under limited parameters, we designed the Balanced Channel Attention Layer (BCA Layer). The BCA Layer improves the extraction of high-quality channel information during feature processing. Second, to enhance model performance while minimizing parameters, we designed a feature extraction network utilizing the Efficient Feature Extraction Module (EFEM) and the Downsampling Module (DM) as its backbone. This design reduces the number of parameters while improving the extraction of discriminative features. Third, to enrich the semantic information of features, we proposed a Progressive Space Pyramid Pooling (PSPP) module, obtaining features with rich semantic information to enhance model performance. Finally, to tackle the challenge of detecting densely packed objects, we proposed a Mask Information Enhancement Module (MIEM) to obtain the fine-grained features, enhancing the model's discriminative ability in dense scenes. The proposed BFDet underwent extensive experimentation on both the Vis-Drone and UAVDT datasets. The mAP0.5 and FPS values of BFDet reach 51.4% and 33 respectively on the VisDrone dataset, and the parameter number is only 5.6M. © 1963-2012 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Numerical study of microorganisms swimming near a convex wall in a Giesekus fluid

引用

Physical Review E 2025年第1期111卷 015103-015103页

作者： Chenlin Zhu Fangyuan Peng Dingyi Pan Zhaosheng Yu Zhaowu Lin Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou 310018 China

The motion of microorganisms in complex fluids stands out as a prominent subject within fluid mechanics. In our study, we utilize the fictitious domain method to investigate the locomotion of squirmers along a convex wall in Giesekus viscoelastic fluids. This study examines the influence of fluid elasticity and wall curvature on squirmer particles, analyzing their movement patterns in detail. Near the convex wall, three distinct behavioral characteristics emerge: scattering, orbiting forward, and orbiting backward. The findings reveal that, compared with Newtonian fluids, squirmers exhibit a stronger tendency to be attracted toward the wall in viscoelastic fluids. This behavior is attributed to the elastic stress of the fluid, which generates a reverse torque on microbial particles, altering their movement direction and hindering their escape from the wall. Notably, as the wall curvature decreases, the likelihood of particles escaping diminishes.

关键词： Forward scattering

来源：评论

学校读者我要写书评

暂无评论

A study of MySQL protocol-based database proxy approval system for fortress machine

引用

International Journal of data Science 2025年第1期10卷 96-117页

作者： Zhang, Xian Luo, Xinhui Yin, Dong Qu, Taiguo Li, Hao Huaihua University Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Huaihua Tourism School Hunan Huaihua418099 China

With the increase of enterprise informatisation, database security and compliance operation management have become increasingly important. Therefore, it is essential to design an efficient database proxy approval system. In this paper, we develop a database proxy approval system based on the MySQL protocol for fortress machines, which provides a real-time customised configuration scheme for high-risk commands, designs a real-time approval process for six types of high-risk commands, and creates a simple and efficient matching algorithm for high-risk commands. We designed a large number of experiments to test the system’s connection success rate, operation stability, response time, CPU resource consumption, matching algorithm performance, and other aspects. The experimental results show that this database proxy approval system has good configuration flexibility, high accuracy, and good time performance. This system has a wide range of applications in electric power, finance, petroleum, and other fields. © 2025 Inderscience Enterprises Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

arXiv

引用

arXiv 2025年

作者： Huang, Junjia Yan, Pengxiang Cai, Jinhang Liu, Jiyang Wang, Zhao Wang, Yitong Wu, Xinglong Li, Guanbin Sun Yat-sen University China ByteDance Intelligent Creation Peng Cheng Laboratory China Guangdong Key Laboratory of Big Data Analysis and Processing China

Text-driven image generation using diffusion models has recently gained significant attention. To enable more flexible image manipulation and editing, recent research has expanded from single image generation to transparent layer generation and multi-layer compositions. However, existing approaches often fail to provide a thorough exploration of multi-layer structures, leading to inconsistent inter-layer interactions, such as occlusion relationships, spatial layout, and shadowing. In this paper, we introduce DreamLayer, a novel framework that enables coherent text-driven generation of multiple image layers, by explicitly modeling the relationship between transparent foreground and background layers. DreamLayer incorporates three key components, i.e., Context-Aware Cross-Attention (CACA) for global-local information exchange, Layer-Shared Self-Attention (LSSA) for establishing robust inter-layer connections, and Information Retained Harmonization (IRH) for refining fusion details at the latent level. By leveraging a coherent full-image context, DreamLayer builds inter-layer connections through attention mechanisms and applies a harmonization step to achieve seamless layer fusion. To facilitate research in multi-layer generation, we construct a high-quality, diverse multi-layer dataset including 400k samples. Extensive experiments and user studies demonstrate that DreamLayer generates more coherent and well-aligned layers, with broad applicability, including latent-space image editing and image-to-layer decomposition. Copyright © 2025, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Optimizing Indoor Network Element Layout for Enhanced Signal Coverage and Security in Location-Based Services 7th

Optimizing Indoor Network Element Layout for Enhanced Signa...

引用

7th International Conference on Attacks and Defenses for Internet-of-Things, ADIoT 2024

作者： Yu, Xiaomin Yu, Xiaokun College of Computer and Control Engineering Qiqihar University Qiqihar China Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar University Qiqihar China Heilongjiang Jiaotong Polytechnic Qiqihar China

ISBN: (纸本)9783031855924

Recently, with the rapid development of communication technology, location-based services (LBS) in indoor environments have penetrated into various aspects of people’s daily lives. Wireless local area networks (WLAN) have become the preferred choice for location-based services due to their broad deployment and low cost. However, the typical non-line-of-sight characteristics of indoor environments result in severe fluctuations in received signal strength (RSS), signal coverage vulnerabilities can exacerbate environmental interference, making positioning results more vulnerable to attacks or tampering. The layout of indoor network elements is a key factor that constrains signal coverage rate. This paper focuses on the optimization of indoor network element layout, proposes an indoor network element layout optimization model based on signal coverage and quality in indoor environments and introduces an Adaptive Simulation Annealing Non-inertial Opposite Particle Swarm Optimization algorithm (ASA-NRPSO). Firstly, a reverse strategy is introduced into the particle flight process of the Particle Swarm Optimization (PSO) algorithm, and high-quality particles are selected for the next generation iteration. In the selection of the reverse strategy, the simulated annealing idea is integrated to adaptively select the reverse strategy based on the needs of the particles at different stages, which avoids the particles falling into local optima. The inertia term in the particle swarm velocity update formula is replaced with group information for non-inertial updates. This can more fully utilize the global information of the population to guide the movement of the next generation of particles and improve the convergence speed of the particle swarm. The elite mutation strategy is used to increase the diversity of particles and improve the global search capability of the algorithm. This method ensures the rapid generation of network element layout to improve the signal coverage rate

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

Advances in Robust Federated Learning: A Survey With Heterogeneity Considerations

引用

IEEE Transactions on big data 2025年第3期11卷 1548-1567页

作者： Chen, Chuan Liao, Tianchi Deng, Xiaojun Wu, Zihou Huang, Sheng Zheng, Zibin Sun Yat-sen University School of Computer Science and Engineering Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Sun Yat-sen University School of Software Engineering Zhuhai519000 China Sun Yat-sen University School of Computer Science and Engineering Guangzhou510006 China Sun Yat-sen University School of Systems Science and Engineering Guangzhou510006 China Sun Yat-sen University School of Software Engineering Zhuhai Key Laboratory of Trusted Large Language Models Zhuhai519000 China

In the field of heterogeneous federated learning (FL), the key challenge is to efficiently and collaboratively train models across multiple clients with different data distributions, model structures, task objectives, computational capabilities, and communication resources. This diversity leads to significant heterogeneity, which increases the complexity of model training. In this paper, we first outline the basic concepts of heterogeneous FL and summarize the research challenges in FL in terms of five aspects: data, model, task, device and communication. In addition, we explore how existing state-of-the-art approaches cope with the heterogeneity of FL, and categorize and review these approaches at three different levels: data-level, model-level, and architecture-level. Subsequently, the paper extensively discusses privacy-preserving strategies in heterogeneous FL environments. Finally, the paper discusses current open issues and directions for future research, aiming to promote the further development of heterogeneous FL. © 2015 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Research on resource scheduling method based on Kubernetes

Research on resource scheduling method based on Kubernetes

引用

IEEE Information Technology and Mechatronics Engineering Conference (ITOEC)

作者： Haoyang Song Liming Zhou Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (数字)9798331529482

ISBN: (纸本)9798331529499

With the continuous development of cloud computing, the demand for cloud services in all walks of life is increasing. The scale of cloud computing services based on container technology is constantly growing, and Kubernetes has been widely used as a mainstream tool for container orchestration. It supports functions such as automatic deployment and service discovery, dramatically simplifies the container deployment process, and improves the availability and reliability of applications in cloud environments. However, the default scheduling strategy of Kubernetes adopts the greedy idea of first-come-first-served when facing multi-pod tasks, and schedules Pods to working nodes one by one. This scheduling scheme will lead to unbalanced cluster load and low resource utilization. To solve this problem, this paper introduces the selection, crossover, and mutation ideas in genetic algorithms into the artificial fish school algorithm, improves the foraging behavior in the artificial fish school algorithm, and constructs a custom scheduling strategy based on the enhanced artificial fish school algorithm. Experiments have shown that compared with the default scheduling strategy of Kubernetes, the customized scheduling strategy in this paper can effectively improve the load balancing of the cluster and improve the utilization of cluster hardware resources in the scenario of multi-pod scheduling.

关键词： Cloud computing Schedules Clustering algorithms Containers Fish Load management Scheduling Hardware Fish schools Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

GraphSparseNet: a Novel Method for Large Scale Trafffic Flow Prediction

arXiv

引用

arXiv 2025年

作者： Kong, Weiyang Wu, Kaiqi Zhang, Sen Liu, Yubao Sun Yat-Sen University Guangzhou China Sun Yat-Sen University Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Traffic flow forecasting is a critical spatio-temporal data mining task with wide-ranging applications in intelligent route planning and dynamic traffic management. Recent advancements in deep learning, particularly through Graph Neural Networks (GNNs), have significantly enhanced the accuracy of these forecasts by capturing complex spatio-temporal dynamics. However, the scalability of GNNs remains a challenge due to their exponential growth in model complexity with increasing nodes in the graph. Existing methods to address this issue, including sparsification, decomposition, and kernel-based approaches, either do not fully resolve the complexity issue or risk compromising predictive accuracy. This paper introduces GraphSparseNet (GSNet), a novel framework designed to improve both the scalability and accuracy of GNN-based traffic forecasting models. GraphSparseNet is comprised of two core modules: the Feature Extractor and the Relational Compressor. These modules operate with linear time and space complexity, thereby reducing the overall computational complexity of the model to a linear scale. Our extensive experiments on multiple real-world datasets demonstrate that GraphSparseNet not only significantly reduces training time by 3.51x compared to state-of-the-art linear models but also maintains high predictive performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Scalability

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：