检索结果-内蒙古大学图书馆

Global video object segmentation with spatial constraint module

Computational Visual Media 2023年第2期9卷 385-400页

作者： Yadang Chen Duolin Wang Zhiguo Chen Zhi-Xin Yang Enhua Wu Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of MacaoMacao 999078China State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of SciencesBeijing 100190China Faculty of Science and Technology University of MacaoMacao 999078China

We present a lightweight and efficient semisupervised video object segmentation network based on the space-time memory *** some extent,our method solves the two difficulties encountered in traditional video object segmentation:one is that the single frame calculation time is too long,and the other is that the current frame’s segmentation should use more information from past *** algorithm uses a global context(GC)module to achieve highperformance,real-time *** GC module can effectively integrate multi-frame image information without increased memory and can process each frame in real ***,the prediction mask of the previous frame is helpful for the segmentation of the current frame,so we input it into a spatial constraint module(SCM),which constrains the areas of segments in the current *** SCM effectively alleviates mismatching of similar targets yet consumes few additional *** added a refinement module to the decoder to improve boundary *** model achieves state-of-the-art results on various datasets,scoring 80.1%on YouTube-VOS 2018 and a J&F score of 78.0%on DAVIS 2017,while taking 0.05 s per frame on the DAVIS 2016 validation dataset.

关键词： video object segmentation semantic segmentation global context(GC)module spatial constraint

来源：评论

学校读者我要写书评

暂无评论

Adversarially Robust Object Detection via Deviation Calibration and Content Preservation

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5900-5911页

作者： Zhang, Xu Peng, Bo Lei, Jianjun Xue, Chao Yao, Yuxuan Huang, Qingming Tianjin University School of Electrical and Information Engineering Tianjin300072 China Tiandy Technologies Tianjin300384 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing101408 China

Object detection has achieved a promising development in recent years and played an important role in various applications. However, the performance of object detection networks generally drops significantly when subjected to adversarial attacks. As an effective technique for defending against adversarial attacks, adversarially robust object detection has attracted increasing interest. In this paper, a novel deviation-calibrated and content-preserved network (DCCP-Net) is proposed for adversarially robust object detection by effectively exploring and mitigating the essential negative impact of noise disturbance in the feature space. Specifically, a deviation-calibrated robust feature enhancement module is designed to enhance the feature robustness of adversarial images by removing noise disturbance and supplementing rectified information. Besides, by enabling adversarial image features to imitate corresponding clean image features, a content-preserved consistency information imitation mechanism is proposed to obtain more accurate content information of adversarial images. Extensive experiment results have verified the superiority of the proposed DCCP-Net. © 1991-2012 IEEE.

关键词： Feature extraction Noise Training Object detection Detectors Robustness Perturbation methods Accuracy Calibration Convolution

来源：评论

学校读者我要写书评

暂无评论

Design of Cost Efficient VBIR Technique Using ICA and IVCA

引用

SN computer science 2024年第5期5卷 1-20页

作者： Pradeep Kumar, B.P. Srinidhi, N.N. Shiva Darshan, S.L. Naresh, E. Department of ECE HKBKCE Karnataka Bangalore 560045 India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering National Institute of Technology Warangal Warangal 506004 India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

With an emphasis on early-stage contrast agent transit through tumour vasculature, this study presents Adaptive Complex Independent Components Analysis (ACICA) as a unique method for evaluating intravascular responsiveness in prostatic tissue. Furthermore, a new SVM clustering method is introduced that outperforms the conventional k-means clustering for image retrieval based on vision. The study emphasises how dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) may be improved in conjunction with quantitative analysis. Within the field of DCE-MRI, ACICA stands out as a unique intravascular attention measurer. Utilising the spatial independence of extravascular and intravascular magnetic resonance imaging (MR) data, ACICA offers a strong foundation for DCE-MRI image analysis. It incorporates pharmacokinetic modelling to optimise the time lag, especially useful for arterial curves, and a reference region (RR)-based technique to adjust the intravascular concentration curve. The model's evaluation yields outstanding results, with recall and accuracy ranging from 83 to 99% and 82.8% to 99.6%, respectively. The average recall and precision across datasets are 92.86% and 92.82%).All things considered, this study demonstrates the effectiveness of ACICA in evaluating intravascular responsiveness and presents viable paths for enhancing clinical results and diagnostic precision in the treatment of prostate cancer. © The Author(s) 2024.

关键词： Adaptive complex independent components analysis Computed tomography Dynamic contrast enhancement Magnetic resonance imaging Visual-based image retrieval

来源：评论

学校读者我要写书评

暂无评论

Mental Health Disorder Prediction Using Recurrent Neural Network Algorithm

Mental Health Disorder Prediction Using Recurrent Neural Net...

引用

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Mariappan, Umasree Balakrishnan, D. Merline, G. Sandhia, M. Reddy, Dubba Saitej Gagan Teja, Sattineni P.S.R. Engineering College Department of Information Technology Tamil Nadu Sivakasi626140 India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnankoil626126 India Sri Vidya College of Engineering & Technology Department of Electronics and Communication Engineering Tamil Nadu Virudhunagar626005 India Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Tamil Nadu Coimbatore641114 India

ISBN: (纸本)9798350361537

Mental health disorders pose a significant challenge to healthcare professionals due to their complex and multifactorial nature. Early identification and accurate prediction of mental health disorders play a crucial role in timely intervention and effective treatment planning. The objective of this study is to explore the potential of deep learning algorithms in predicting mental health disorders, specifically focusing on depression, anxiety, and schizophrenia. The study utilizes a dataset containing clinical and demographic information of patients diagnosed with these disorders. The dataset was pre-processed using feature scaling algorithm, and features dimensionality reduction is done using t-Distributed Stochastic Neighbor Embedding (t-SNE) to train and evaluate deep learning models. These models were trained on large-scale datasets, allowing for the identification of complex patterns and relationships within the data. The training on dataset is done by using the Recurrent Neural Networks. The performance of the models was evaluated using standard evaluation metrics, such as accuracy, precision, recall, and F1-score. The results indicate that deep learning algorithms have shown promising results in predicting mental health disorders. The models achieved high accuracy rates, with some models surpassing the performance of traditional machine learning algorithms. Performance evaluation of the model is conducted using relevant metrics such as precision, recall, and F1-score, on a separate validation or test dataset from which it is proved that the proposed methodology attains 6% performance improvement than the existing methodology. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

RIS-Assisted Integrated Sensing and Communication Systems: Joint Reflection and Beamforming Design

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2024年 5卷 908-927页

作者： Ismail, Mohamed I. Shaheen, Abdullah M. Fouda, Mostafa M. Alwakeel, Ahmed S. Modern Academy for Engineering and Technology Department of Electronic Engineering and Communication Technology Cairo4410242 Egypt Suez University Faculty of Engineering Department of Electrical Engineering Suez8151650 Egypt Idaho State University College of Science and Engineering Department of Electrical and Computer Engineering PocatelloID83209 United States

The Integrated Sensing and Communication (ISAC) system merged with Reconfigurable Intelligent Surface (RIS) has recently received much attention. This paper proposes an intelligent metaheuristic version of Enhanced Artificial Ecosystem Optimizer (EAEO) for a suggested beamforming optimization framework in ISAC systems with RIS. Two RIS are utilized in the presented model to enhance the received signal-to-noise ratio (SNR) for multiple-input multiple-output (MIMO) communication systems. Also, each element of each RIS scatters the incoming signal with a controllable phase-shift, without increasing its power. The signal is transmitted by a Dual-Function Base Station (DFBS) that is integrated with the RIS, which performs both communication and sensing functions simultaneously. The ISAC system is designed to optimize the signal transmission through the RIS by maximizing the SNR to increase the overall performance. In the proposed EAEO version, a Fitness-Distance-Balance Model (FDBM) is combined with the standard Artificial Ecosystem Optimizer (AEO) to improve the quality of the solutions in multidimensional and nonlinear optimization scenarios. The simulation results show that the proposed EAEO algorithm improves the SNR of different users for different numbers of RIS elements. The SNR reaches 25 dB when using 200 RIS elements. Moreover, the proposed EAEO is tested on the IEEE Congress on Evolutionary Computation 2017 (IEEE CEC'17) test suite. A comparative analysis is conducted compared to the standard AEO and several recent algorithms. The proposed EAEO derives great effectiveness and robustness over the others as it provides a higher rate of success in achieving the global optimum point. © 2020 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A novel ontological-based trust aware hybrid key management scheme (OTAHKMS) to enhance network lifetime and energy usage in wireless sensor networks (WSNs)

引用

International Journal of Information technology (Singapore) 2024年第3期16卷 1429-1435页

作者： Barve, Amit Pallavi, R. Deepak, Shashikant Murugan, R. Yadav, Dhananjay Singh, Ashutosh Kr. Sharma, Meenakshi Shalini, S. Department of Computer Science and Engineering Faculty of Engineering and Technology Parul University Gujarat Vadodara India Department of Computer Science Engineering Presidency University Karnataka Bangalore India Department of UGDX ATLAS SkillTech University Mumbai India Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Noida India Department of Electronics and Communication Engineering Noida Institute of Engineering and Technology UP Noida India Department of Education Sanskriti University UP Mathura India Department of Computer Science and Engineering Dayananda Sagar Academy of Technology and Management Bangalore India

Security, heterogeneity, and interoperability are the prominent concerns in wireless sensor networks (WSNs) with restricted amounts of resources such as energy, transmission range, and processing of packets. Moreover, secured and trusted communication among WSNs is required to enhance network lifetime and security, thereby reducing energy consumption in the network. Thus, the given paper presents an ontological-based trust aware hybrid key management scheme (OTAHKMS) for WSNs. The proposed approach is a two-fold approach, where the first phase involves the encryption process for maintaining data confidentiality and integrity, while the second phase involves the use of ontology for capturing trust relationships and representing contextual information among several nodes in the network. The performance of the proposed trusted approach is validated and compared with existing cited works based on evaluation metrics such as communication trust value (CTV), network throughput (NT), packet delivery ratio (PDR), and energy consumption (EC). The results show that the proposed ontological-based trusted approach efficiently outperforms existing protocols, thereby enhancing network lifetime and energy usage in WSNs. © 2024, The Author(s), under exclusive licence to Bharati vidyapeeth's Institute of computer Applications and Management.

关键词： Encryption Packets transmission Security Trust validation Wireless sensor networks (WSNs)

来源：评论

学校读者我要写书评

暂无评论

A Content-Based Filtering Approach for Personalized Movie Recommendations 2

A Content-Based Filtering Approach for Personalized Movie Re...

引用

2nd International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2025

作者： Vashisht, Rohit Sharma, Rahul Kumar Pant, Maneesh Thakral, Gagan Naresh, Prashant Department of Computer Science & Information Technology KIET Group of Institutions Ghaziabad India Department of Computer Science & Engineering KIET Group of Institutions Ghaziabad India Department of Information Technology JSS Academy of Technical Education Noida India

ISBN: (纸本)9798331530389

The recommendation system of today has made it simple to locate the necessities. Movie recommendation systems are designed to assist movie buffs by making recommendations for films to see, saving them the trouble and effort of having to sort through hundreds or even millions of options. The Recommender System has become a major area of research because it helps people find things online by making suggestions that are similar to what they are looking for. In this paper, we introduce a system called MOVIEHOPE for recommending movies. It uses a content-based filtering method that uses the user's preferences and the item's description to make a profile. In CBF, we use keywords to describe items instead of the user's profile to show what they like or do not like. In plain English, the CBF algorithm likes or recommends things that were liked in the past. It looks at how items have been rated before and suggests the best item that fits. © 2025 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

An Efficient Depth Estimation Technique for Visual Perception

An Efficient Depth Estimation Technique for Visual Perceptio...

引用

2024 IEEE International Conference on Recent Advances in science and engineering technology, ICRASET 2024

作者： Deepa Shubham, A. Shetty, Bhuvan Aravind Dhanush Kumar, Archana Praveen Department of Information Science and Engineering Karnataka Nitte India Manipal Institute of Technology Manipal Academy of Higher Education Department of Computer Science and Engineering Karnataka Manipal576104 India

ISBN: (纸本)9798350388602

In the realm of computer vision and 3D reconstruction, the accurate conversion of images into depth maps is crucial. This paper focuses on depth estimation techniques to assess their accuracy and reliability in generating depth maps from 2D images. Subsequently, the depth maps were transformed into 3D representations using Open3D in Python, enabling the visualization and reconstruction of three-dimensional scenes. Despite challenges such as noise and artifacts, the reconstruction process yielded promising results, highlighting the potential of image-based 3D reconstruction techniques. This study contributes to the advancement of computer vision technologies by providing insights into improving depth estimation accuracy and enhancing the fidelity of reconstructed 3D models. Additionally, the successful reconstruction of 3D scenes underscores the practical utility of image-based 3D reconstruction methodologies in various domains, including robotics, augmented reality, and autonomous driving. © 2024 IEEE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

FedBully: A Cross-Device Federated Approach for Privacy Enabled Cyber Bullying Detection using Sentence Encoders

引用

Journal of Cyber Security and Mobility 2023年第4期12卷 465-496页

作者： Shetty, Nisha P. Muniyal, Balachandra Priyanshu, Aman Das, Vedant Rishi Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal576104 India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal576104 India

Cyberbullying has become one of the most pressing concerns for online platforms, putting individuals at risk and raising severe public concerns. Recent studies have shown a significant correlation between declining mental health and cyberbullying. Automated detection offers a great solution to this problem;however, the sensitivity of client-data becomes a concern during data collection, and as such, access may be restricted. This paper demonstrates FedBully, a federated approach for cyberbullying detection using sentence encoders for feature extraction. This paper introduces concepts of secure aggregation to ensure client privacy in a cross-device learning system. Optimal hyper-parameters were studied through comprehensive experiments, and a computationally and communicationally inexpensive network is proposed. Experiments reveal promising results with up to 93% classification AUC (Area Under the Curve) using only dense networks to fine-tune sentence embeddings on IID datasets and 91% AUC on non-IID datasets, where IID refers to Independent and Identically Distributed data. The analysis also shows that data independence profoundly impacts network performance, with AUC decreasing by a mean of 5.1% between Non-IID and IID. A rich and extensive study has also been performed on client network size and secure aggregation protocols, which prove the robustness and practicality of the proposed model. The novel approach presented offers an efficient and practical solution to training a cross-device cyberbullying detector while ensuring client-privacy. © 2023 River Publishers.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Fusion of Sparse Direct Method and Feature-based Approach in Stereo Point-Line SLAM Algorithm

Fusion of Sparse Direct Method and Feature-based Approach in...

引用

2024 International Conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Wang, Hao Xu, Zhen Leng, Kuang China Nanhu Academy of Electronics and Information Technology Zhejiang Jiaxing China School of Electronic Engineering and Computer Science University of Science and Technology of China Anhui Hefei China School of Management University of Science and Technology of China Anhui Hefei China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

The development of autonomous driving and augmented reality has led to increased demands for accuracy and speed in visual SLAM. Traditional feature-based visual SLAM performs real-time image analysis with high complexity and computation requirements, necessitating devices with exceptionally high arithmetic power. This poses challenges for deployment on low-power devices. Additionally, relying solely on photometric errors makes the system too sensitive to the environment. To tackle these issues, our algorithm integrates the feature-based method and the sparse direct method. We employ the sparse joint method for pose estimation in the tracking thread, considering both accuracy and speed. In case of tracking failure, we extract feature point lines for tracking. Furthermore,to enhance system robustness in low-texture environments and fuse point-line features, we employ adaptive weighted extraction of point-line features, considering computational resources. Our experimental results, based on public datasets, demonstrate that this algorithm achieves faster operation speeds in simple environments and higher accuracy compared to other SLAM algorithms in complex environments and fast camera movement scenes. © 2025 SPIE.

关键词： Stereo image processing

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：