检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Qi Luo, Zhouhang Yu, Tao Huang, Hui College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen China

View transformation robustness (VTR) is critical for deep-learning-based multi-view 3D object reconstruction models, which indicates the methods’ stability under inputs with various view transformations. However, existing research seldom focuses on view transformation robustness in multi-view 3D object reconstruction. One direct way to improve the models’ VTR is to produce data with more view transformations and add them to model training. Recent progress on large vision models, particularly Stable Diffusion models, has provided great potential for generating 3D models or synthesizing novel view images with only a single image input. To fully utilize the power of Stable Diffusion models without causing extra inference computation burdens, we propose to generate novel views with Stable Diffusion models for better view transformation robustness. Instead of synthesizing random views, we propose a reconstruction error-guided view selection method, which considers the reconstruction errors’ spatial distribution of the 3D predictions and chooses the views that could cover the reconstruction errors as much as possible. The methods are trained and tested on sets with large view transformations to validate the 3D reconstruction models’ robustness to view transformations. Extensive experiments demonstrate that the proposed method can outperform state-of-the-art 3D reconstruction methods and other view transformation robustness comparison methods. Codel will be available at: https://***/zqyq/VTR. © 2024, CC BY-NC-ND.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Strong stabilized joint probabilistic data association method of autoregulatory gating in vehicle nonlinear multi-target tracking 4

Strong stabilized joint probabilistic data association metho...

引用

4th International Conference on Mechanical engineering, Intelligent Manufacturing, and Automation Technology, MEMAT 2023

作者： Han, Guoxin Liu, Fuyun Deng, Jucai Liu, Huiqi Bai, Weihua College of Mechanical and Electrical Engineering Guilin University of Electronic Technology Guilin China College of Computer Science and Software Zhaoqing University Zhaoqing China Commercial Vehicle Technology Center Liuzhou Dongfeng Automobile Company Ltd. Liuzhou China

ISBN: (纸本)9781510674820

This paper proposed a strong stabilized joint probabilistic data association approach based on numerical stability optimization and autoregulatory gating strategy for multi-target tracking of vehicles with multi-maneuvering states in a nonlinear cluttered environment. The approach utilized an enhanced square-root cubature Kalman filter to achieve the optimization for joint probabilistic data association, which advanced the accuracy and stability of nonlinear state estimation during the multi-target tracking. On this basis, an autoregulation method of association gate based on tracking error sensitivity was proposed to improve the data association gating strategy, which effectively advanced the success rate of target association and tracking accuracy. The virtual simulation traffic scenes of intelligent driving were constructed by PreScan to better reproduce the multi-target tracking problem. The results of the simulations show that the method has clear advantages in terms of target tracking precision, numerical stability and environmental adaptability. © 2024 SPIE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Automatic Eyewitness Identification During Disasters by Forming a Feature-Word Dictionary

引用

computers, Materials & Continua 2022年第9期72卷 4755-4769页

作者： Shahzad Nazir Muhammad Asif Shahbaz Ahmad Hanan Aljuaid Shahbaz Ahmad Yazeed Ghadi Zubair nawaz Department of Computer Science National Textile UniversityFaisalabadPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman University(PNU)P.O.Box 84428Riyadh 11671Saudi Arabia Department of Software Engineering and Computer Science Al Ain UniversityAbu DhabiUnited Arab Emirates Department of Data Science University of the PunjabPakistan

Social media provide digitally interactional technologies to facilitate information sharing and exchanging ***,in case of disasters,a massive corpus is placed on platforms such as *** accounts can benefit humanitarian organizations and agencies,but identifying the eyewitness Tweets related to the disaster from millions of Tweets is *** approaches have been developed to address this kind of *** recent state-of-the-art system was based on a manually created dictionary and this approach was further refined by introducing linguistic ***,these approaches suffer from limitations as they are dataset-dependent and not *** this paper,we proposed a method to identify eyewitnesses from *** experiment,we utilized 13 features discovered by the pioneer of this domain and can classify the tweets to determine the *** each feature,a dictionary of words was created with the Word Dictionary Maker algorithm,which is the crucial contribution of this *** algorithm inputs some terms relevant to a specific feature for its initialization and then creates the words ***,keyword matching for each feature in tweets is *** a feature exists in a tweet,it is termed as 1;otherwise,***,for 13 features,we created a file that reflects features in each *** classify the tweets based on features,Naïve Bayes,Random Forest,and Neural Network were *** approach was implemented on different disasters like earthquakes,floods,hurricanes,and Forest *** results were compared with the state-of-the-art linguistic rule-based system with 0.81 F-measure *** the same time,the proposed approach gained a 0.88 value of *** results were comparable as the proposed approach is not ***,it can be used for the identification of eyewitness accounts.

关键词： Word dictionary social media eyewitness identification disasters

来源：评论

学校读者我要写书评

暂无评论

Dynamic Searchable Scheme with Forward Privacy for Encrypted Document Similarity 22

Dynamic Searchable Scheme with Forward Privacy for Encrypted...

引用

22nd IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2023

作者： Al Sibahee, Mustafa A. Luo, Chengwen Zhang, Jin Huang, Yijing Abduljabbar, Zaid Ameen Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Iraq University College Computer Technology Engineering Department Basrah61004 Iraq University of Basrah College of Education for Pure Sciences Department of Computer Science Basrah61004 Iraq Huazhong University of Science and Technology Shenzhen Institute Shenzhen518000 China

ISBN: (纸本)9798350381993

Document retrieval plays an essential role in many real-world applications especially when the data storage is outsourced. Due to the great advantages offered by cloud computing, clients tend to outsource their personal data to remote servers maintained by external service providers. This raises serious privacy concerns about outsourced data because such providers are usually considered untrusted entities. The majority of previous schemes of document similarity search share the same limitation: they focus mainly on static collections. Dynamic searchable schemes (DSE) allow adding or removing documents at the expense of more leakage than static schemes. To thwart certain attacks, DSE schemes should support forward privacy property, which ensures that newly added documents cannot be related to previously issued search queries. We design and implement dynamic secure similarity search schemes with forward privacy for textual documents utilizing simhash method for hamming similarity. Our scheme provides an efficient search time and a sufficient level of privacy. To show the practicality of our proposed scheme, we performed excremental results with large document collections. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Neuro-Fuzzy Approach to Road Traffic Congestion Prediction

引用

computers, Materials & Continua 2022年第10期73卷 295-310页

作者： Mohammed Gollapalli Atta-ur-Rahman Dhiaa Musleh Nehad Ibrahim Muhammad Adnan Khan Sagheer Abbas Ayesha Atta Muhammad Aftab Khan Mehwash Farooqui Tahir Iqbal Mohammed Salih Ahmed Mohammed Imran BAhmed Dakheel Almoqbil Majd Nabeel Abdullah Omer Department of Computer Information System(CIS) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia Department of Computer Science(CS) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia Pattern Recognition and Machine Learning Lab Department of Software EngineeringGachon UniversityInchonKorea Department of Computer Science National College of Business Administration and EconomicsLahorePunjab54000Pakistan Department of Computer Science Government College University(GCU)LahorePunjab54000Pakistan Department of Computer Engineering(CE) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia College of Business Administration Imam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia Department of Networks and Communications(NC) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal UniversityDammam31441Saudi Arabia

The fast-paced growth of artificial intelligence applications provides unparalleled opportunities to improve the efficiency of various *** as the transportation sector faces many obstacles following the implementation and integration of different vehicular and environmental aspects *** congestion is among the major issues in this regard which demands serious attention due to the rapid growth in the number of vehicles on the *** address this overwhelming problem,in this article,a cloudbased intelligent road traffic congestion prediction model is proposed that is empowered with a hybrid Neuro-Fuzzy *** aim of the study is to reduce the delay in the queues,the vehicles experience at different road junctions across the *** proposed model also intended to help the automated traffic control systems by minimizing the congestion particularly in a smart city environment where observational data is obtained from various implanted Internet of Things(IoT)sensors across the *** due preprocessing over the cloud server,the proposed approach makes use of this data by incorporating the neuro-fuzzy ***,it possesses a high level of accuracy by means of intelligent decision making with minimum error *** results reveal the accuracy of the proposed model as 98.72%during the validation phase in contrast to the highest accuracies achieved by state-of-the-art techniques in the literature such as 90.6%,95.84%,97.56%and 98.03%,*** far as the training phase analysis is concerned,the proposed scheme exhibits 99.214% accuracy. The proposed prediction modelis a potential contribution towards smart cities environment.

关键词： Neuro-fuzzy machine learning congestion prediction AI cloud computing smart cities

来源：评论

学校读者我要写书评

暂无评论

Electronically Steerable Mobile Optical-Wireless Mesh-Network

Electronically Steerable Mobile Optical-Wireless Mesh-Networ...

引用

Annual IEEE Systems Conference

作者： Suman Bhunia Yicheng Qian Mahmudur Khan Department of Computer Science and Software Engineering Miami University Oxford Ohio USA Department of Electrical & Computer Engineering and Computer Science York College of Pennsylvania USA

ISBN: (数字)9798350358803

ISBN: (纸本)9798350358810

Free Space Optical (FSO) Communication provides better communication coverage and higher data rate. However, FSO requires neighboring nodes to schedule their transceiver towards each other for communication, which makes multi-hop communication challenging. In this paper, we present an FSO mesh network system that enables data transfer among multiple nodes. Each node is equipped with a multi-transceiver FSO communication module and a low-bitrate long-range (LoRa) omnidirectional radio frequency (RF) communication module. Scheduling remains a significant challenge for wireless communication using highly directional transceivers such as FSO. Hence, we propose a distributed coordination and communication method that utilizes a supplementary omnidirectional LoRa channel for distributed coordination among the nodes in the mesh network. In the proposed scheme, a per-packet beam scheduling is proposed where the assisting low bandwidth omnidirectional channel helps the higher data rate directional channel to coordinate and face the line of sight. Our proposed method enables communication via both single-hop and multi-hop FSO links. We also present the implementation of a proof-of-concept prototype of an RF-FSO communication module comprising multiple FSO transceivers and a LoRa transceiver using commercial off-the-shelf devices (COTS). We demonstrate the effectiveness of our proposed FSO mesh network system through real test-bed experiments using the developed prototype.

关键词： Wireless communication Radio frequency Mesh networks Schedules Free-space optical communication Protocols Wireless mesh networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Approach for Detecting Student Engagement Through Facial Emotions 2

Deep Learning Based Approach for Detecting Student Engagemen...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Lima, Mariam Ahmed, Kazi Rifat Jahan, Nusrat Mahmud, Imran Parvez, Md. Shahriar Revathi, P. Daffodil International University Department of Software Engineering Dhaka Bangladesh Daffodil International University Department of Information Technology & Management Dhaka Bangladesh Holy Cross College Department of Computer Science Tamilnadu Tiruchirapalli India

ISBN: (纸本)9798350373110

In today's educational system, maintaining students' interest is of the utmost importance. Researchers have been motivated to investigate approaches that can automatically measure engagement as a result of this. Using facial expressions to determine whether or not a student is interested in a certain topic and to give individualized assistance is the purpose of this research project. Using the well-known VGG16 model, This study provide a framework for evaluating degrees of engagement based on facial signals. This framework is built on face detection which used the FER2013 dataset, produced encouraging findings with a considerable accuracy of 96.16%. The objective of this study is to provide educators and online platforms with a dependable instrument that can assess and address student involvement. This will be accomplished by using deep learning algorithms that are particularly intended to do facial expression interpretation. The findings of this study provide a contribution to the growing subject of using technology to enhance learning settings by highlighting the benefits of automated systems in terms of increasing student engagement and academic accomplishment. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Secure Scheme for Locating Disease-Causing Genes Based on Multi-Key Homomorphic Encryption

引用

Tsinghua science and Technology 2022年第2期27卷 333-343页

作者： Tanping Zhou Wenchao Liu Ningbo Li Xiaoyuan Yang Yiliang Han Shangwen Zheng Tanping Zhou is with the College of Cryptography Engineering Engineering University of People’s Armed PoliceXi’an 710086China TCA Laboratory State Key Laboratory of Computer ScienceInstitute of SoftwareChinese Academy of SciencesBeijing 100080China the College of Cryptography Engineering Engineering University of People’s Armed PoliceXi’an 710086China the People’s Armed Police Command College China Tianjin 300100China

Genes have great significance for the prevention and treatment of some diseases.A vital consideration is the need to find a way to locate pathogenic genes by analyzing the genetic data obtained from different medical institutions while protecting the privacy of patients’genetic *** this paper,we present a secure scheme for locating disease-causing genes based on Multi-Key Homomorphic Encryption(MKHE),which reduces the risk of leaking genetic ***,we combine MKHE with a frequency-based pathogenic gene location *** medical institutions use MKHE to encrypt their genetic *** cloud then homomorphically evaluates specific gene-locating circuits on the encrypted genetic ***,whereas most location circuits are designed only for locating monogenic diseases,we propose two location circuits(TH-intersection and Top-q)that can locate the disease-causing genes of polygenic ***,we construct a directed decryption protocol in which the users involved in the homomorphic evaluation can appoint a target user who can obtain the final decryption *** experimental results show that compared to the JWB+17 scheme published in the journal science,our scheme can be used to diagnose polygenic diseases,and the participants only need to upload their encrypted genetic data once,which reduces the communication traffic by a few hundred-fold.

关键词： public key encryption Multi-Key Homomorphic Encryption(MKHE) fully homomorphic encryption disease-causing genes secure location of disease-causing genes

来源：评论

学校读者我要写书评

暂无评论

PP-TIL: Personalized Planning for Autonomous Driving with Instance-based Transfer Imitation Learning

arXiv

引用

arXiv 2024年

作者： Lin, Fangze He, Ying Yu, Fei College of Computer Science and Software Engineering Shenzhen University China Carleton University Canada

Personalized motion planning holds significant importance within urban automated driving, catering to the unique requirements of individual users. Nevertheless, prior endeavors have frequently encountered difficulties in simultaneously addressing two crucial aspects: personalized planning within intricate urban settings and enhancing planning performance through data utilization. The challenge arises from the expensive and limited nature of user data, coupled with the scene state space tending towards infinity. These factors contribute to overfitting and poor generalization problems during model training. Henceforth, we propose an instance-based transfer imitation learning approach. This method facilitates knowledge transfer from extensive expert domain data to the user domain, presenting a resolution to these issues. We initially train a pre-trained model using large-scale expert data. Subsequently, during the fine-tuning phase, we feed the batch data, which comprises expert and user data. Employing the inverse reinforcement learning technique, we extract the style feature distribution from user demonstrations, constructing the regularization term for the approximation of user style. In our experiments, we conducted extensive evaluations of the proposed method. Compared to the baseline methods, our approach mitigates the overfitting issue caused by sparse user data. Furthermore, we discovered that integrating the driving model with a differentiable nonlinear optimizer as a safety protection layer for end-to-end personalized fine-tuning results in superior planning performance. The code will be available at https://***/LinFunster/PP-TIL. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Idea23D: Collaborative LMM Agents Enable 3D Model Generation from Interleaved Multimodal Inputs 31

Idea23D: Collaborative LMM Agents Enable 3D Model Generation...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Chen, Junhao Li, Xiang Ye, Xiaojun Li, Chao Fan, Zhaoxin Zhao, Hao Tsinghua University China Tsinghua Shenzhen International Graduate School Tsinghua University China School of Software and Microelectronics Peking University China College of Computer Science Zhejiang University China College of Computer Science and Technology Harbin Engineering University China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing School of Artificial Intelligence Beihang University China

ISBN: (纸本)9798891761964

With the success of 2D diffusion models, 2D AIGC content has already transformed our lives. Recently, this success has been extended to 3D AIGC, with state-of-the-art methods generating textured 3D models from single images or text. However, we argue that current 3D AIGC methods still don't fully unleash human creativity. We often imagine 3D content made from multimodal inputs, such as what it would look like if my pet bunny were eating a doughnut on the table. In this paper, we explore a novel 3D AIGC approach: generating 3D content from IDEAs. An IDEA is a multimodal input composed of text, image, and 3D models. To our knowledge, this challenging and exciting 3D AIGC setting has not been studied before. We propose the new framework Idea23D, which combines three agents based on large multimodal models (LMMs) and existing algorithmic tools. These three LMM-based agents are tasked with prompt generation, model selection, and feedback reflection. They collaborate and critique each other in a fully automated loop, without human intervention. The framework then generates a text prompt to create 3D models that align closely with the input IDEAs. We demonstrate impressive 3D AIGC results that surpass previous methods. To comprehensively assess the 3D AIGC capabilities of Idea23D, we introduce the Eval3DAIGC-198 dataset, containing 198 multimodal inputs for 3D generation tasks. This dataset evaluates the alignment between generated 3D content and input IDEAs. Our user study and quantitative results show that Idea23D significantly improves the success rate and accuracy of 3D generation, with excellent compatibility across various LMM, Text-to-Image, and Image-to-3D models. Code and dataset are available at https://***/. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

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：