检索结果-内蒙古大学图书馆

VideoDreamer: Customized Multi-Subject Text-to-Video Generation With Disen-Mix Finetuning on Language-Video Foundation Models

引用

IEEE Transactions on Multimedia 2025年 27卷 2875-2885页

作者： Chen, Hong Wang, Xin Zeng, Guanning Zhang, Yipeng Zhou, Yuwei Han, Feilin Wu, Yaofei Zhu, Wenwu Tsinghua University Department of Computer Science and Technology Beijing100084 China Beijing National Research Center for Information Science and Technology Beijing100084 China Beijing Film Academy Department of Film and TV Technology Beijing100088 China Beijing University of Technology Beijing100124 China

Customized text-to-video generation aims to generate text-guided videos with user-given subjects, which has gained increasing attention. However, existing works are primarily limited to single-subject oriented text-to-video generation, leaving the more challenging problem of customized multi-subject generation unexplored. In this paper, we fill this gap and propose a novel VideoDreamer framework, which can generate temporally consistent text-guided videos that faithfully preserve the visual features of the given multiple subjects. Specifically, VideoDreamer adopts the pretrained Stable Diffusion with temporal modules as its base video generator, taking the power of the text-to-image model to generate diversified content. The video generator is further customized for multi-subjects, which leverages the proposed Disen-Mix Finetuning and Human-in-the-Loop Re-finetuning strategy, to tackle the attribute binding problem of multi-subject generation. Additionally, we present a disentangled motion customization strategy to finetune the temporal modules so that we can generate videos with both customized subjects and motions. To evaluate the performance of customized multi-subject text-to-video generation, we introduce the MultiStudioBench benchmark. Extensive experiments demonstrate the remarkable ability of VideoDreamer to generate videos with new content such as new events and backgrounds, tailored to the customized multiple subjects. © 1999-2012 IEEE.

关键词： Text to video Dogs Codes Visualization Generators Text to image Diffusion models Hands Training Noise measurement

来源：评论

学校读者我要写书评

暂无评论

AAMA-Sim – A Gazebo and ROS2-Based Simulation Tool for Agent-Based Modelling of Cyber-Physical Systems 22nd

AAMA-Sim – A Gazebo and ROS2-Based Simulation Tool for Ag...

引用

22nd International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2024

作者： Altay, Dogukan Karaduman, Burak Challenger, Moharram Department of Computer Science University of Antwerp Antwerp Belgium AnSyMo/Cosys Core-lab Flanders Make Strategic Research Center Antwerp Belgium

ISBN: (纸本)9783031704147

The development of complex Multi-Agent Systems (MAS) represents a formidable challenge. Within this process, researchers and developers are tasked with designing, testing, and validating many agent behaviours applicable across various facets of the application. Yet, the implementation phase of these agents presents significant difficulties, notably due to the challenges and high costs associated with testing behaviours in physical systems. Although numerous simulation tools exist designed to offer a virtual testing environment for engineers to validate their designs, a prevalent observation is that most of these tools primarily focus on the semantics of the modelled environment, often neglecting the intricacies of real-world physical conditions. To bridge this gap, we introduce a new simulation testbench where engineers can adjust the simulation parameters to meet specific needs, thereby reducing the disparity between simulated environments and real-world constraints. This paper elucidates how a multi-agent system can leverage this advanced simulation environment to evaluate its agents’ behaviours within a context that closely mimics real-world conditions. Moreover, we explore the capabilities of the simulation environment’s sandbox features, which allow engineers to customize the environment in alignment with their unique use cases, thereby enhancing the utility and applicability of the simulation for comprehensive behavioural testing and validation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Integration in O- RAN: A Concise Review 33

Federated Learning Integration in O- RAN: A Concise Review

引用

33rd International Telecommunication Networks and Applications Conference, ITNAC 2023

作者： Islam, Noureen Monir, Fahad Mahbubul Syeed, M.M. Hasan, Mahady Uddin, Mohammad Faisal Independent University Department of Computer Science & Engineering Bangladesh Independent University RIoT Research Center Bangladesh

ISBN: (纸本)9798350317138

The rapid growth of the telecommunication industry presents a global challenge in maintaining data security and privacy amid increasing data traffic and diverse applications. Applying Federated Learning (FL) to the upcoming Next Generation Wireless Networks (NextG) or Open Radio Access Network (O-RAN) holds great potential as a solution for addressing these challenges. With this in consideration, our paper explores a secure and privacy-conscious solution, focusing on the potential of FL in upcoming wireless networks or O-RAN. FL's cooperative learning approach ensures data confidentiality, offering significant advancements in security issues associated with growing user numbers, and supports the migration to the NextG. In this paper, the concise review provides valuable insights into O-RAN, FL, and related works, with an emphasis on security and privacy. Additionally, it explores framework utilization and outlines future research directions for integrating FL within O-RAN. This approach aims to offer the readers a quick and clear understanding of FL integration within O-RAN, avoiding the need to navigate through extensive survey papers. © 2023 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Interval Pade Approximation for the Construction of an Approximate D-SDRE Controller 16

Interval Pade Approximation for the Construction of an Appro...

引用

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Danik, Yulia Dmitriev, Mikhail Federal Research Center 'Computer Science and Control' of Russian Academy of Sciences Department 71 Moscow Russia

ISBN: (纸本)9798350337907

In this paper a parametric family of stabilizing controllers for a nonlinear discrete control system is obtained for different values of a parameter at the system matrix. An algorithm for constructing a stabilizing controller based on the D-SDRE approach, asymptotic methods and Padé approximations is proposed which uses asymptotic expansions in the neighborhood of the boundary and interior points of the given parameter variation interval which break it on several subintervals. © 2023 IEEE.

关键词： Discrete time control systems

来源：评论

学校读者我要写书评

暂无评论

Breakthrough in breast tumor detection and diagnosis: a noise-resilient, rotation-invariant framework

引用

Multimedia Tools and Applications 2025年 1-27页

作者： Nosheen, Fariha Khan, Salabat Sharif, Muhammad Kim, Do Hyeun Alkanhel, Reem AbdelSamee, Nagwan Department of Computer Science COMSATS University Islamabad Attock Campus Attock43600 Pakistan Department of Computer Engineering Jeju National University Jeju Special Self-Governing Province Jeju-Si63243 Korea Republic of Big Data Research Center Jeju National University Jeju63243 Korea Republic of Department of Information Technology College of Computer and Information Sciences Princess Nourahbint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

The fact that early-stage breast cancer typically presents no signs, poses a global risk to the lives of women. Digital mammography is just one method among many that can detect breast cancer in its early stages. Despite extensive research, most methods for detecting breast cancers still produce a large number of false positives. The difficulty in improving detection accuracy is in reducing false positives by differentiating masses from normal tissues. Using the textural properties of the masses, this study aims to develop a computer-aided diagnosis system that reduces the number of false positive and negative mammography results. The suggested method initially partitions regions of interest (ROI) into small patches to extract an abnormality region and micro-pattern, which permits the extraction of specific information about the image's content in targeted areas. Reducing the computational complexity of an image analysis operation is accomplished by partitioning a ROI into smaller patches rather than processing the complete image at once. Due to the significant impact the noise has on detection accuracy in mammograms, a textural descriptor that is insensitive to noise is introduced to describe image features such as lines, spots, flat areas, and edges. By expanding the rotation-invariant and noise-tolerant descriptor histograms, we generate an improved histogram that preserves the original regional patterns and spatial relationships between masses. To distinguish between "normal" and "mass" and "benign" and "malignant", Support Vector Machines (SVM) is employed with grid search based hyperparameter optimization. Our proposed approach was evaluated using the Digital Database for Screening Mammography (DDSM), which contains over 1024 ROI cases. This database is a well-established benchmark for testing new mammography analysis methods. Each case in the DDSM database has been analyzed and interpreted by qualified radiologists, with comprehensive information provided thr

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Teaching Agent-Based Modeling for Simulating Social Systems – A research-Based Learning Approach 25th

Teaching Agent-Based Modeling for Simulating Social Systems ...

引用

25th International Workshop on Multi-Agent-Based Simulation, MABS 2024

作者： Lorig, Fabian Belfrage, Michael Johansson, Emil Department of Computer Science and Media Technology Malmö University Malmö Sweden Internet of Things and People Research Center Malmö University Malmö Sweden

ISBN: (纸本)9783031880162

Existing courses on agent-based modeling and simulating (ABMS) are mainly aimed at doctoral students and many modelers have acquired their ABMS skills by teaching themselves. This paper reports and reflects on the development of an undergraduate course on ABMS of social systems. It presents a problem-based approach to teaching ABMS of social systems, the Integrated Learning Outcomes (ILOs), and the course structure. This paper discusses the constructive alignment of the syllabus, presents the results from the course evaluation, and draws conclusions for further editions of the course. Rather than proposing how such courses should be structured, we discuss the feasibility of the pursued research-based learning approach. Our goal is to inspire other researchers and teachers to develop similar courses, to encourage the establishment of a general curriculum, and to promote ABMS in undergraduate education. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Double Mixed Compressed Images Based on Quaternion Convolutional Neural Network

引用

Chinese Journal of Electronics 2024年第3期33卷 657-671页

作者： Hao WANG Jinwei WANG Xuelong HU Bingtao HU Qilin YIN Xiangyang LUO Bin MA Jinsheng SUN Department of Automation Nanjing University of Science and Technology Engineering Research Center of Digital Forensics Ministry of Education Department of Computer and Software Nanjing University of Information Science and Technology School of Management Nanjing University of Posts and Telecommunications Department of Computer Science and Engineering Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University State Key Laboratory of Mathematical Engineering and Advanced Computing Qilu University of Technology

Detection of color images that have undergone double compression is a critical aspect of digital image *** the existence of various methods capable of detecting double Joint Photographic Experts Group(JPEG) compression,they are unable to address the issue of mixed double compression resulting from the use of different compression *** particular,the implementation of Joint Photographic Experts Group 2000(JPEG2000)as the secondary compression standard can result in a decline or complete loss of performance in existing *** tackle this challenge of JPEG+JPEG2000 compression,a detection method based on quaternion convolutional neural networks(QCNN) is *** QCNN processes the data as a quaternion,transforming the components of a traditional convolutional neural network(CNN) into a quaternion *** relationships between the color channels of the image are preserved,and the utilization of color information is ***,the method includes a feature conversion module that converts the extracted features into quaternion statistical features,thereby amplifying the evidence of double *** results indicate that the proposed QCNN-based method improves,on average,by 27% compared to existing methods in the detection of JPEG+JPEG2000 compression.

关键词： Color image forensics JPEG JPEG2000 Mixed double compression Quaternion convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Digital Twin, Metaverse and Smart Cities in a Race to the Future 24

Digital Twin, Metaverse and Smart Cities in a Race to the Fu...

引用

24th International Arab Conference on Information Technology, ACIT 2023

作者： Zainab, Hijab E Bawanay, Narmeen Zakaria Jinnah University for Women Center for Computing Research Department of Computer Science and Software Engineering Karachi Pakistan

ISBN: (纸本)9798350384307

In the dynamic landscape of urban development, the synergy of the Metaverse, Digital Twins, and Smart Cities emerges as a potent catalyst for transformation. The Metaverse, a vibrant virtual space, collaborates with cutting-edge technologies, including Virtual Reality (VR), Augmented Reality (AR), the Internet of Things (IoT), and Artificial Intelligence (AI), crafting immersive experiences. Simultaneously, Digital Twins, serving as virtual replicas of physical entities, instigating an industrial revolution, while Smart Cities harness advanced technologies for sustainable urban living. This paper explores the applications of converging these technologies across diverse industries, showcasing how Digital Twins reshape conventional practices and amplify the concept of smart cities through the immersive realm of the Metaverse. However, the exploration unveils challenges, particularly in data privacy, interoperability, and ethical considerations. The study advocates for a balanced and informed approach, emphasizing that the symbiotic relationship between Digital Twins and the Metaverse should steer the evolution of Smart Cities toward security, innovation, and interconnected urban spaces. © 2023 IEEE.

关键词： Digital Twins Immersive Experiences Metaverse Smart Cities Sustainable Urban Living Urban Development

来源：评论

学校读者我要写书评

暂无评论

A Survey on Image Semantic Segmentation Using Deep Learning Techniques

引用

computers, Materials & Continua 2023年第1期74卷 1941-1957页

作者： Jieren Cheng Hua Li Dengbo Li Shuai Hua Victor S.Sheng School of Computer Science and Technology Hainan UniversityHaikou570228China School of Cyberspace Security(School of Cryptology) Hainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research Center Hainan UniversityHaikou570228China Department of Computer Science Texas Tech University TX 79409USA

Image semantic segmentation is an important branch of computer vision of a wide variety of practical applications such as medical image analysis,autonomous driving,virtual or augmented reality,*** recent years,due to the remarkable performance of transformer and multilayer perceptron(MLP)in computer vision,which is equivalent to convolutional neural network(CNN),there has been a substantial amount of image semantic segmentation works aimed at developing different types of deep learning *** survey aims to provide a comprehensive overview of deep learning methods in the field of general image semantic ***,the commonly used image segmentation datasets are ***,extensive pioneering works are deeply studied from multiple perspectives(e.g.,network structures,feature fusion methods,attention mechanisms),and are divided into four categories according to different network architectures:CNN-based architectures,transformer-based architectures,MLP-based architectures,and ***,this paper presents some common evaluation metrics and compares the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value on the most widely used ***,possible future research directions and challenges are discussed for the reference of other researchers.

关键词： Deep learning semantic segmentation CNN MLP transformer

来源：评论

学校读者我要写书评

暂无评论

A Blockchain based Framework for Verifying Drug Authenticity 24

A Blockchain based Framework for Verifying Drug Authenticity

引用

24th International Arab Conference on Information Technology, ACIT 2023

作者： Hamid, Soomaiya Bawany, Narmeen Zakaria Fatima, Kiran Jinnah University for Women Center for Computing Research Department of Computer Science and Software Engineering Karachi Pakistan

ISBN: (纸本)9798350384307

Counterfeit drugs are fake medicines that are potentially harmful for health. Safeguarding the integrity of pharmaceutical distribution plays a crucial role in preventing the circulation of counterfeit drugs. Traditional drug supply chain systems have no effective mechanism to ensure the traceability and integrity of the drug supply chain process. Various ICT-based solutions have been adopted previously and numerous regulations were passed by drug regulatory authorities to ensure interoperable and traceable drug distribution process. However, these solutions could not guarantee a tamper-proof history of supply chain process. Blockchain technology has gained traction in many diverse fields including real-estate, identity management, digital voting, healthcare, etc. Therefore, we have proposed a decentralized framework to insure the authenticity and traceability of the drugs. Moreover, this study presents an overview of how blockchain technology can be employed to counter the fake medicines circulation by embedding the traceability in drug supply chain process. Comparison of various blockchain-based solutions and open research challenges in this regard are also presented. © 2023 IEEE.

关键词： Blockchain Technology Counterfeit Drugs decentralized framework Drug Supply Chain Traceability of Drugs Traditional Pharmaceutical Supply Chain

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：