检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Khalid, Umar Iqbal, Hasan Karim, Nazmul Hua, Jing Chen, Chen Tayyab, Muhammad Center for Research in Computer Vision University of Central Florida OrlandoFL United States Department of Computer Science Wayne State University DetroitMI United States

While neural fields have made significant strides in view synthesis and scene reconstruction, editing them poses a formidable challenge due to their implicit encoding of geometry and texture information from multi-view inputs. In this paper, we introduce LatentEditor, an innovative framework designed to empower users with the ability to perform precise and locally controlled editing of neural fields using text prompts. Leveraging denoising diffusion models, we successfully embed real-world scenes into the latent space, resulting in a faster and more adaptable NeRF backbone for editing compared to traditional methods. To enhance editing precision, we introduce a delta score to calculate the 2D mask in the latent space that serves as a guide for local modifications while preserving irrelevant regions. Our novel pixel-level scoring approach harnesses the power of InstructPix2Pix (IP2P) to discern the disparity between IP2P conditional and unconditional noise predictions in the latent space. The edited latents conditioned on the 2D masks are then iteratively updated in the training set to achieve 3D local editing. Our approach achieves faster editing speeds and superior output quality compared to existing 3D editing models, bridging the gap between textual instructions and high-quality 3D scene editing in latent space. We show the superiority of our approach on four benchmark 3D datasets, LLFF [26], IN2N [8], NeRFStudio [44] and NeRF-Art [47]. Project Page: https://***/ Copyright © 2023, The Authors. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Skeletonmae: Spatial-Temporal Masked Autoencoders for Self-Supervised Skeleton Action Recognition

Skeletonmae: Spatial-Temporal Masked Autoencoders for Self-S...

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Wenhan Wu Yilei Hua Ce Zheng Shiqian Wu Chen Chen Aidong Lu Department of Computer Science University of North Carolina at Charlotte USA School of Information Science and Engineering Wuhan University of Science and Technology China Center for Research in Computer Vision University of Central Florida USA

Self-supervised skeleton-based action recognition has attracted more attention in recent years. By utilizing the unlabeled data, more generalizable features can be learned to alleviate the overfitting problem and reduce the demand for massive labeled training data. Inspired by the MAE [1], we propose a spatial-temporal masked autoencoder framework for self-supervised 3D skeleton-based action recognition (SkeletonMAE). Following MAE's masking and reconstruction pipeline, we utilize a skeleton-based encoder-decoder transformer architecture to reconstruct the masked skeleton sequences. A novel masking strategy, named Spatial-Temporal Masking, is introduced in terms of both joint-level and frame-level for the skeleton sequence. This pre-training strategy makes the encoder output generalizable skeleton features with spatial and temporal dependencies. Given the unmasked skeleton sequence, the encoder is fine-tuned for the action recognition task. Extensive experiments show that our SkeletonMAE achieves remarkable performance and outperforms the state-of-the-art methods on both NTU RGB+D 60 and NTU RGB+D 120 datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cyberbullying Classification Using a Natural Language Processing and Machine Learning Techniques

Cyberbullying Classification Using a Natural Language Proces...

引用

2024 International Conference on Advances in Computing research on science Engineering and Technology, ACROSET 2024

作者： Mankar, Nikhilesh Pramod Mahure, Tushar Joshi, Anushka A. Pande, Sagar Dhanraj Khamparia, Aditya Nathe, Ankita Shrikrushna Turjman, Fadi Al Pune India Independent Researcher Amravati India Babasaheb Bhimrao Ambedkar University Department of Computer Science Amethi India Kavikulguru Institute of Technology and Science Department of Information Technology Nagpur India Ai and Robotics Institute Near East University Artificial Intelligence Software Information Systems Engineering Departments Nicosia Cyprus University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Turkey

ISBN: (纸本)9798350388800

The usage of online entertainment has increased dramatically after some time with the enhancement of the Internet and has turned into the most compelling systems administration stage in this century. Notwithstanding, the upgrade of a social network regularly makes adverse consequences on society that add to two or three terrible peculiarities, for example, online maltreatment, badgering cyberbullying, cybercrime, and internet savaging. Cyberbullying habitually prompts genuine mental and actual misery, especially for ladies and kids, and even occasionally make them to use self-destruction methods. Multiple number of episodes have as of late happened worldwide because of online badgering, like sharing private talks, bits of hearsay, and sexual comments. In this way, the distinguishing proof of harassing messages or messages via online entertainment has gained a significant measure for development for consideration with in scientists. The ground or motive for this exploration is to create a full-fledged way or a method to differentiate online harmful and tormenting drafts by combining various methods and techniques in the domain of natural language processing and AI © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Prior Knowledge-Driven Hybrid Prompter Learning for RGB-Event Tracking

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Mianzhao Shi, Fan Cheng, Xu Chen, Shengyong Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System School of Computer Science and Engineering Tianjin300384 China Technical University of Denmark Department of Technology Management and Economics Kongens Lyngby Denmark

Event data can asynchronously capture variations in light intensity, thereby implicitly providing valuable complementary cues for RGB-Event tracking. Existing methods typically employ a direct interaction mechanism to fuse RGB and event data. However, due to differences in imaging mechanisms, the representational disparity between these two data types is not fixed, which can lead to tracking failures in certain challenging scenarios. To address this issue, we propose a novel prior knowledge-driven hybrid prompter learning framework for RGB-Event tracking. Specifically, we develop a frame-event hybrid prompter that leverages prior tracking knowledge from the foundation model as intermediate modal support to mitigate the heterogeneity between RGB and event data. By leveraging its rich prior tracking knowledge, the intermediate modal reduces the gap between the dense RGB and sparse event data interactions, effectively guiding complementary learning between modalities. Meanwhile, to mitigate the internal learning disparities between the lightweight hybrid prompter and the deep transformer model, we introduce a pseudo-prompt learning strategy that lies between full fine-tuning and partial fine-tuning. This strategy adopts a divide-and-conquer approach to assign different learning rates to modules with distinct functions, effectively reducing the dominant influence of RGB information in complex scenarios. Extensive experiments conducted on two public RGB-Event tracking datasets show that the proposed HPL outperforms state-of-the-art tracking methods, achieving exceptional performance. © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

The Main Threat to computer Network Security in Smart Cities 3

The Main Threat to Computer Network Security in Smart Cities

引用

3rd International Conference on Advancement in Electronics and Communication Engineering, AECE 2023

作者： Salama, Ramiz Al-Turjman, Sinem Altrjman, Chadi Al-Turjman, Fadi Vikash, Om Yadav, Satya Prakash Vats, Satvik Ai and Robotics Institute Research Center for Ai and IoT Near East University Department of Computer Engineering Near East Boulevard TRNC Mersin 10 Nicosia99138 Turkey Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept Mersin10 Nicosia Turkey Waterloo University Department of Chemical Engineering ONN2L 3G1 Canada Friedrich- Alexander University Clean Energy Processing Department Chemical and Biological Engineerin Erlangen Germany Department of Computer Science and Engineering Greater Noida201306 India Graphic Era Hill University Dehradun Department of Computer Science and Engineering India

ISBN: (纸本)9798350330724

As the concept of smart cities continues to gain momentum, the integration of various technologies has become essential for creating sustainable and efficient urban environments. However, with the proliferation of interconnected devices and systems, the risk of network security threats has increased significantly. This research article aims to identify and analyze the main threats to network security in smart cities. By exploring the potential vulnerabilities and challenges posed by the interconnected infrastructure, this study provides insights into the key areas that require attention to ensure the resilience and protection of smart cities. The findings of this research emphasize the need for robust security measures and proactive strategies to mitigate the identified threats. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

The ways in which Artificial Intelligence improves several facets of Cyber Security-A survey 1

The ways in which Artificial Intelligence improves several f...

引用

1st International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023

作者： Salama, Ramiz Al-Turjman, Fadi Altrjman, Chadi Bordoloi, Dibyahash Ai and Robotics Institute Research Center for Ai and IoT Near East University Nicosia Department of Computer Engineering Mersin10 Turkey Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept. Mersin Nicosia10 Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Mersin10 Turkey Waterloo University Canada Graphic Era Hill University Dehradun Rs Cse Graphuc Era University Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350338027

With the increase in computer use for the last 10 years, it increases the size of cyber-attacks as well. Since most computers are connected to the network, they may suffer cyber-attacks. Because of these cyber threats, Cyber Security is becoming a really important area in the information technology area. Cyber Security is an area which is mainly responsible for dealing with cyber-attacks by hackers. The improvements and advancements in the information technology area allow cyber criminals to do really complicated and dangerous cyber-attacks. Cyber-attack methods that are being used today are much more effective than the ones in the past. Because of that, there is always a war between cyber security specialists and cyber attackers or hackers. Cyber security analysts, on the other hand, try to come up with new solutions to the methods developed by cyber criminals or hackers. The competition between them continuously advances and improves cyber security technologies every day. The improvements can be either in cyber security or cybercrime side. These days, traditional cyber security solutions are enough to fight against cyber-attacks, but can these solutions be further developed? This is the question everyone in the cyber security area is trying to answer. Of course, yes. Thanks to AI, which is one of the most popular technologies in the information technology area, it is used in many areas ranging from e-commerce, advertising, human resource & recruiting, video games, transportation, surveillance systems etc. AI has been used in cyber security over the last years. Although it also has negative effects, we are going to mostly talk about its positive sides in this article. We are going to go deep into how and why AI is used in cyber security, how AI improves and enhances the current traditional cyber security methods. Then, we will also talk about which AI techniques play an important role in the cyber security area. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

The use of machine learning (ML) in sustainable systems-An Overview 1

The use of machine learning (ML) in sustainable systems-An O...

引用

1st International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023

作者： Salama, Ramiz Al-Turjman, Fadi Altrjman, Chadi Bordoloi, Dibyahash Ai and Robotics Institute Research Center for Ai and IoT Near East University Nicosia Department of Computer Engineering Mersin10 Turkey Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept. Mersin Nicosia10 Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Mersin10 Turkey Waterloo University Canada Graphic Era Hill University Dehradun Rs Cse Graphic Era University Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350338027

Machine learning has the ability to dramatically improve sustainable systems by anticipating needs, maximizing resource use, raising output, and lowering waste. An overview of earlier studies on the incorporation of machine learning into sustainable systems is presented together with a case study of how machine learning was used to lower energy use in a residential structure. The results show that machine learning may be used to increase energy efficiency and save a lot of money. Wearable technology has added a whole new dimension to the already vast field of personal electronics. The mobile phone gave devices their true individuality. Because so many services are designed around mobile phones, the market has opened up for a brand-new personalized experience utilizing wearable technologies. Fabric sensors may now be combined with wearable microcontrollers like the flora and lily pad to monitor stretch, pressure, bend, and even the direction that the body is being braced. The connections between them are based on conductive threads that follow the curve of the fabric. We'll examine how different teams used their in-depth understanding of wearable technologies to accomplish their goals in this study. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

DUAL STUDENT NETWORKS FOR DATA-FREE MODEL STEALING

arXiv

引用

arXiv 2023年

作者： Beetham, James Kardan, Navid Mian, Ajmal Shah, Mubarak Center for Research in Computer Vision University of Central Florida OrlandoFL32816 United States Department of Computer Science University of Western Australia CrawleyWA6009 Australia

Data-free model stealing aims to replicate a target model without direct access to either the training data or the target model. To accomplish this, existing methods use a generator to produce samples in order to train a student model to match the target model outputs. To this end, the two main challenges are estimating gradients of the target model without access to its parameters, and generating a diverse set of training samples that thoroughly explores the input space. We propose a Dual Student method where two students are symmetrically trained in order to provide the generator a criterion to generate samples that the two students disagree on. On one hand, disagreement on a sample implies at least one student has classified the sample incorrectly when compared to the target model. This incentive towards disagreement implicitly encourages the generator to explore more diverse regions of the input space. On the other hand, our method utilizes gradients of student models to indirectly estimate gradients of the target model. We show that this novel training objective for the generator network is equivalent to optimizing a lower bound on the generator’s loss if we had access to the target model gradients. In other words, our method alters the standard data-free model stealing paradigm by substituting the target model with a separate student model, thereby creating a lower bound which can be directly optimized without additional target model queries or separate synthetic datasets. We show that our new optimization framework provides more accurate gradient estimation of the target model and better accuracies on benchmark classification datasets. Additionally, our approach balances improved query efficiency with training computation cost. Finally, we demonstrate that our method serves as a better proxy model for transfer-based adversarial attacks than existing data-free model stealing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

CoBaIR: A Python Library for Context-Based Intention Recognition in Human-Robot-Interaction

arXiv

引用

arXiv 2023年

作者： Lubitz, Adrian Gutzeit, Lisa Kirchner, Frank Robotics Research Group Department of Computer Science University of Bremen Bremen28359 Germany German Research Center for Artificial Intelligence Bremen28359 Germany

Human-Robot Interaction (HRI) becomes more and more important in a world where robots integrate fast in all aspects of our lives but HRI applications depend massively on the utilized robotic system as well as the deployment environment and cultural differences. Because of these variable dependencies it is often not feasible to use a data-driven approach to train a model for human intent recognition. Expert systems have been proven to close this gap very efficiently. Furthermore, it is important to support understandability in HRI systems to establish trust in the system. To address the above-mentioned challenges in HRI we present an adaptable python library in which current state-of-the-art Models for context recognition can be integrated. For Context-Based Intention Recognition a two-layer Bayesian Network (BN) is used. The bayesian approach offers explainability and clarity in the creation of scenarios and is easily extendable with more modalities. Additionally, it can be used as an expert system if no data is available but can as well be fine-tuned when data becomes available. © 2023, CC BY.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

Authentication using Biometric Data from Mobile Cloud Computing in Smart Cities 3

Authentication using Biometric Data from Mobile Cloud Comput...

引用

3rd International Conference on Advancement in Electronics and Communication Engineering, AECE 2023

作者： Salama, Ramiz Al-Turjman, Sinem Altrjman, Chadi Al-Turjman, Fadi Prakash, R.Om Yadav, Satya Prakash Vats, Satvik Ai and Robotics Institute Research Center for Ai and IoT Department of Computer Engineering Near East University Near East Boulevard TRNC Mersin 10 Nicosia99138 Turkey Ai and Robotics Institute Near Artificial Intelligence Engineering Dept Near East University Mersin10 Nicosia Turkey Waterloo University Department of Chemical Engineering ONN2L 3G1 Canada Noida Instue Engineering and Technology U.P Greator Noida201306 India Department of Computer Science and Engineering Greater Noida201306 India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350330724

Smart cities are cities that are designed to be more efficient, sustainable, and connected. As our cities grow and become more complex, it's important to find new ways to address the challenges that arise, such as security, privacy, and mobility. This is where mobile cloud computing and biometric authentication come in. Mobile cloud computing is a way to provide cloud computing services to mobile devices, which means people can access services and data from anywhere and at any time. Biometric authentication is a method of identifying people based on their unique physical or behavioral characteristics, like fingerprints, facial recognition, or voice recognition. These two technologies can be combined to create a secure and personalized environment for residents and visitors in smart cities. By using mobile devices, IoT devices, wireless sensor networks, and edge computing, we can collect real-time data that can be used for big data analytics and machine learning. This means we can optimize city services, like traffic management, waste management, or energy consumption, and enhance the quality of life for people living in smart cities. However, the use of these technologies also poses significant security and privacy risks, so it's important to design systems that are secure and privacy-preserving. This requires interdisciplinary research and collaboration between experts in different fields. In summary, mobile cloud computing and biometric authentication have the potential to transform smart cities by creating a more secure and personalized environment for residents and visitors. But we must also be mindful of the potential risks and work together to address them. © 2023 IEEE.

关键词： Mobile cloud computing

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：