检索结果-内蒙古大学图书馆

Adversarial multi-image steganography via texture evaluation and multi-scale image enhancement

Multimedia Tools and Applications 2025年第9期84卷 5793-5823页

作者： Li, Fengyong Li, Longwei Zeng, Yishu Yu, Jiang Qin, Chuan College of Computer Science and Technology Shanghai University of Electric Power Shanghai201306 China School of Information and Computer Shanghai Business School Shanghai201400 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200092 China

Multi-image steganography refers to a data-hiding scheme where a user tries to hide confidential messages within multiple images. Different from the traditional steganography which only requires the security of an individual image, multi-image steganography considers an overall security for a batch of images. However, existing multi-image steganography all faces a nontrivial problem: how to optimally allocate payload into multiple images to guarantee the security of batch images. To address this problem, this paper proposes an adversarial multi-image steganographic scheme. A multi-scale texture evaluation mechanism is firstly calculated to determine the embeddable cover images. Subsequently, a series of multi-scale filters are introduced to enhance the image content, which can be used to guide the optimal payload assignment of each image. Furthermore, an adversarial embedding mechanism is designed by dynamically adjusting the random gradient mapping of batch images, and finally achieving secure multi-image steganography. Our proposed scheme can optimize the overall steganographic security performance of multiple images, while ensuring the anti-steganalysis capability of a single image. Extensive experiments demonstrate that our scheme can achieve superior performance for multi-image steganography over different large-scale image sets, and outperforms state-of-the art schemes in terms of both single-image and multi-image anti-steganalysis capability. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Few-shot image semantic segmentation based on meta-learning: A review

引用

Journal of Intelligent and Fuzzy Systems 2024年第5-6期47卷 351-367页

作者： Liu, Yu Zhu, Ye Chong, Haoze Yu, Ming School of Electronic and Information Engineering Hebei University of Technology Tianjin China School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China College of Computer and Information Engineering Tianjin Agricultural University Tianjin China

Deep learning-based image semantic segmentation approaches heavily rely on large-scale training datasets with dense annotations and often suffer from scarce semantic labels for unseen categories. This limitation has spurred a research trend in Few-shot image Semantic Segmentation (FSS), which makes it possible to segment objects of new categories using only a few labeled samples. Although more and more FSS methods are emerging and gradually integrated into practical applications, a deep understanding of its achievements and issues is still missing. In this survey, we focus on the recent developments of FSS, specifically on FSS methods based on meta-learning. According to different network architectures, we summarize the related research into three classes, that are Convolutional Neural Network-based (CNN-based) models, Graph Neural Network-based (GNN-based) models, and Transformer-based models. Then, we explore the specific implementations of these models, including parameter-based methods, metric-based methods, attention-based methods, and optimization-based methods. Furthermore, we illustrate datasets and analyze the experimental results of various kinds of methods. Toward the end of the paper, we discuss the limitations of FSS and present its applications and challenges to provide further research directions. © 2024 - IOS Press. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Shared Decision-Making Model among One Patient and Multiple Doctors

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第1期8卷 132-156页

作者： Liu, Yong Lin, Kai-Biao Lu, Ping Lin, Min School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China School of Electromechanical and Information Engineering Putian University Putian351100 China

Shared decision-making (SDM) is an effective decision-making method in clinical practice. However, the pressure of negotiation and decision makes it difficult to apply widely. To alleviate the pressure of artificial SDM and promote the realization of clinical SDM, this article presents a fuzzy constraint-based negotiation and decision method for the patient-doctors SDM. The proposed method includes a negotiation model and a decision-making model. The negotiation model quantifies the negotiation process between patient agent (PA) and doctor agents (DAs) in SDM. It consists of the negotiation behavior and the negotiation protocol of agents. The decision-making model quantifies the decision process of SDM. It translates the negotiation results into treatment plans and assists PA in making decisions. The main contributions are as follows: 1) the agent technology is applied to make one-to-many SDM efficient and intelligent;2) the distributed and fuzzy constraint theories are used to design an interconnected, autonomous, and distributed multi-agents negotiation system for SDM;3) the decision-making model is presented to assist doctors and patients in making decisions. The evaluation results of the negotiation and decision models demonstrate that our method is feasible and effective. © 2023, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

SSF: Sparse point cloud object detection based on self-adaptive voxel encoding and focal-sparse convolution

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 11041-11054页

作者： Zhang, Yu Wang, Zilong Zhu, Yongjian Li, Jianxin School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai China College of Engineering Physics Shenzhen Technology University Guangdong Province Shenzhen China

Point cloud object detection is gradually playing a key role in autonomous driving tasks. To address the issue of insensitivity to sparse objects in point cloud object detection, we have made improvements to the voxel encoding and 3D backbone network of the PVRCNN++. We have introduced adaptive pooling operations during voxel feature encoding to expand the point cloud information within each voxel, followed by the utilization of multi-layer perceptrons to extract richer point cloud features. On the 3D backbone network, we have employed adaptive sparse convolution operations to make the backbone network's channel count more flexible, allowing it to accommodate a wider range of input data types. Furthermore, we have integrated Focal Loss to tackle the issue of class imbalance in detection tasks. Experimental results on the public KITTI dataset demonstrate significant improvements over the PVRCNN++, particularly in pedestrian and bicycle detection tasks. Specifically, we have observed 1% increase in detection accuracy for pedestrians and 2.1% improvement for bicycles. Our detection performance also surpasses that of other comparative detection algorithms. © 2024 - IOS Press. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

PEP: An Accurate and Efficient Pupil Detection Framework Based on Pupil Edge Points

引用

IEEE Sensors Journal 2025年第12期25卷 22385-22396页

作者： Zhang, Wei Liu, Yu Lv, Linfeng Wang, Xiang Li, Ziqiang Liu, Lei Li, Bin Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230026 China Carnegie Mellon University Department of Electrical and Computer Engineering Pittsburgh United States Nanjing University of Information Science and Technology School of Computer Science Nanjing China

With the rapid development of headmounted devices, eye tracking as an emerging human-computer interaction technology, has gained increasing importance. However, pupil detection, the core algorithm in eye tracking, suffered low accuracy in complex scenarios and long runtime, which limits the frame rate. This paper proposes PEP (neural network based on Pupil Edge Points), an efficient pupil detection framework that not only achieves high detection accuracy but also significantly reduces computational costs, thereby addressing the performance bottlenecks of existing methods in challenging environments. The core innovation of the PEP framework lies in its focus on detecting edge-representative points (the points at the edge of the pupil) along the pupil edge, a method more precise than traditional full-region segmentation and better suited for accurate pupil ellipse fitting. Additionally, PEP enhances the accuracy of pupil edge point predictions through two key features: (1) a loss function that includes natural ellipse prior regularization term and (2) a data augmentation strategy that randomly masks edges. We evaluated PEP against state-of-the-art (SOTA) model-based and learning-based methods across multiple datasets. The evaluation results show that PEP achieved superior overall performance regarding pupil detection rate and accuracy. Moreover, PEP’s parameter number and computational cost are 80% lower than other learning-based methods, making it highly efficient. The proposed framework is practical, scalable, and demonstrates exceptional potential for pupil detection and gaze-tracking applications. © 2001-2012 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Exploring the Latest Applications of OpenAI and ChatGPT: An In-Depth Survey

引用

computer Modeling in engineering & Sciences 2024年第3期138卷 2061-2102页

作者： Hong Zhang Haijian Shao School of Electrical Information Engineering Jiangsu University of TechnologyChangzhou213001China Department of Electrical and Computer Engineering University of NevadaLas Vegas89154USA

OpenAI and ChatGPT, as state-of-the-art languagemodels driven by cutting-edge artificial intelligence technology,have gained widespread adoption across diverse industries. In the realm of computer vision, these models havebeen employed for intricate tasks including object recognition, image generation, and image processing, leveragingtheir advanced capabilities to fuel transformative breakthroughs. Within the gaming industry, they have foundutility in crafting virtual characters and generating plots and dialogues, thereby enabling immersive and interactiveplayer experiences. Furthermore, these models have been harnessed in the realm of medical diagnosis, providinginvaluable insights and support to healthcare professionals in the realmof disease detection. The principal objectiveof this paper is to offer a comprehensive overview of OpenAI, OpenAI Gym, ChatGPT, DALL E, stable diffusion,the pre-trained clip model, and other pertinent models in various domains, encompassing CLIP Text-to-Image,education, medical imaging, computer vision, social influence, natural language processing, software development,coding assistance, and Chatbot, among others. Particular emphasis will be placed on comparative analysis andexamination of popular text-to-image and text-to-video models under diverse stimuli, shedding light on thecurrent research landscape, emerging trends, and existing challenges within the domains of OpenAI and *** a rigorous literature review, this paper aims to deliver a professional and insightful overview of theadvancements, potentials, and limitations of these pioneering language models.

关键词： OpenAI ChatGPT DALL E stable diffusion OpenAI Gym text-to-image text-to-video

来源：评论

学校读者我要写书评

暂无评论

DAUNet: Detail-Aware U-Shaped Network for 2D Human Pose Estimation

引用

computers, Materials & Continua 2024年第11期81卷 3325-3349页

作者： Xi Li Yuxin Li Zhenhua Xiao Zhenghua Huang Lianying Zou College of Information and Artificial Intelligence Nanchang Institute of Science and TechnologyNanchang330108China School of Electrical and Information Engineering Wuhan Institute of TechnologyWuhan430205China School of Computer Science and Technology Hubei Business CollegeWuhan430079China

Human pose estimation is a critical research area in the field of computer vision,playing a significant role in applications such as human-computer interaction,behavior analysis,and action *** this paper,we propose a U-shaped keypoint detection network(DAUNet)based on an improved ResNet subsampling structure and spatial grouping *** network addresses key challenges in traditional methods,such as information loss,large network redundancy,and insufficient sensitivity to low-resolution *** is composed of three main ***,we introduce an improved BottleNeck block that employs partial convolution and strip pooling to reduce computational load and mitigate feature ***,after upsampling,the network eliminates redundant features,improving the overall ***,a lightweight spatial grouping attention mechanism is applied to enhance low-resolution semantic features within the feature map,allowing for better restoration of the original image size and higher *** results demonstrate that DAUNet achieves superior accuracy compared to most existing keypoint detection models,with a mean PCKh@0.5 score of 91.6%on the MPII dataset and an AP of 76.1%on the COCO ***,real-world experiments further validate the robustness and generalizability of DAUNet for detecting human bodies in unknown environments,highlighting its potential for broader applications.

关键词： Human pose estimation keypoint detection U-shaped network architecture spatial grouping mechanism

来源：评论

学校读者我要写书评

暂无评论

A voting-based trustworthy distributed IoT attack detection model

引用

Personal and Ubiquitous Computing 2025年第1期29卷 103-118页

作者： Sharma, Priya Sharma, Sanjay Kumar Dani, Diksha University School of Information & Communication Technology Gautam Buddha University Greater Noida India Department of Computer Engineering SVKM’s NMIMS Mukesh Patel School of Technology Management & Engineering Mumbai India

Besides the enhancement of the Internet of Things (IoT) distributed environment, anomalous activities are also escalating rapidly. Therefore, improving the trustworthiness of distributed networks is required for the extensive adoption of IoT infrastructure. Establishing a security mechanism in IoT networks is a challenging task as communication links are lossy and connected devices are resource-dependent. Conventional security techniques such as intrusion detection systems (IDS) are insufficient to shelter the IoT-distributed environment due to less computational capacity, restricted upgraded devices, and mismatched protocols. This paper proposes a novel machine learning-based trustworthy model for IoT attack detection. The proposed system combines the capability of Ada-boost and Gradient-boost to classify anomalous activities with low computational capacity proficiently and within a minimum time frame. Experiments were conducted on Distributed Smart Space Orchestration System (DS2OS) IoT dataset to assess the significance of the novel attack detection model. The demonstration shows that the proposed model obtains 98.28% training accuracy, 98.26% testing accuracy, and 99.25% AUC score. A confusion matrix has also been calculated to check the authenticity of the results—a comparison of the proposed model with individual learners and existing models proves that the proposed model outperformed. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Ordered Clustering-Based Semantic Music Recommender System Using Deep Learning Selection

引用

computers, Materials & Continua 2025年第5期83卷 3025-3057页

作者： Weitao Ha Sheng Gang Yahya D.Navaei Abubakar S.Gezawa Yaser A.Nanehkaran School of Computer Science and Technology Weinan Normal UniversityWeinan714099China School of Information&Engineering Yancheng Teachers UniversityYancheng224002China Department of Computer and Technology Engineering Qazvin BranchIslamic Azad UniversityQazvin34199-15195Iran School of Information Engineering Sanming UniversitySanming365004China Department ofManagement Information Systems Faculty of Economics and Administrative SciencesCankayaUniversityAnkara06790Türkiye

Music recommendation systems are essential due to the vast amount of music available on streaming platforms,which can overwhelm users trying to find new tracks that match their *** systems analyze users’emotional responses,listening habits,and personal preferences to provide personalized suggestions.A significant challenge they face is the“cold start”problem,where new users have no past interactions to guide *** improve user experience,these systems aimto effectively recommendmusic even to such users by considering their listening behavior and music *** paper introduces a novel music recommendation system that combines order clustering and a convolutional neural network,utilizing user comments and rankings as ***,the system organizes users into clusters based on semantic similarity,followed by the utilization of their rating similarities as input for the convolutional neural *** network then predicts ratings for unreviewed music by ***,the system analyses user music listening behaviour and music *** popularity can help to address cold start users as ***,the proposed method recommends unreviewed music based on predicted high rankings and popularity,taking into account each user’s music listening *** proposed method combines predicted high rankings and popularity by first selecting popular unreviewedmusic that themodel predicts to have the highest ratings for each *** these,the most popular tracks are prioritized,defined by metrics such as frequency of listening across *** number of recommended tracks is aligned with each user’s typical listening *** experimental findings demonstrate that the new method outperformed other classification techniques and prior recommendation systems,yielding a mean absolute error(MAE)rate and rootmean square error(RMSE)rate of approximately 0.0017,a hit rate of 82.45%,an average normalized discounted cumulative gain

关键词： Music recommender system order clustering deep learning

来源：评论

学校读者我要写书评

暂无评论

ASL-OOD:Hierarchical Contextual Feature Fusion with Angle-Sensitive Loss for Oriented Object Detection

引用

computers, Materials & Continua 2025年第2期82卷 1879-1899页

作者： Kexin Wang Jiancheng Liu Yuqing Lin Tuo Wang Zhipeng Zhang Wanlong Qi Xingye Han Runyuan Wen Northwest Institute of Mechanical and Electrical Engineering Xianyang712099China School of Information Engineering Chang’an UniversityXi’an710064China School of Computer Science and Technology Xidian UniversityXi’an710071China

Detecting oriented targets in remote sensing images amidst complex and heterogeneous backgrounds remains a formidable challenge in the field of object *** frameworks for oriented detection modules are constrained by intrinsic limitations,including excessive computational and memory overheads,discrepancies between predefined anchors and ground truth bounding boxes,intricate training processes,and feature alignment *** overcome these challenges,we present ASL-OOD(Angle-based SIOU Loss for Oriented Object Detection),a novel,efficient,and robust one-stage framework tailored for oriented object *** ASL-OOD framework comprises three core components:the Transformer-based Backbone(TB),the Transformer-based Neck(TN),and the Angle-SIOU(Scylla Intersection over Union)based Decoupled Head(ASDH).By leveraging the Swin Transformer,the TB and TN modules offer several key advantages,such as the capacity to model long-range dependencies,preserve high-resolution feature representations,seamlessly integrate multi-scale features,and enhance parameter *** improvements empower the model to accurately detect objects across varying *** ASDH module further enhances detection performance by incorporating angle-aware optimization based on SIOU,ensuring precise angular consistency and bounding box *** approach effectively harmonizes shape loss and distance loss during the optimization process,thereby significantly boosting detection *** evaluations and ablation studies on standard benchmark datasets such as DOTA with an mAP(mean Average Precision)of 80.16 percent,HRSC2016 with an mAP of 91.07 percent,MAR20 with an mAP of 85.45 percent,and UAVDT with an mAP of 39.7 percent demonstrate the clear superiority of ASL-OOD over state-of-the-art oriented object detection *** findings underscore the model’s efficacy as an advanced solution for challenging remote sensing object detection tasks.

关键词： Oriented object detection transformer deep learning

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：