检索结果-内蒙古大学图书馆

UniTrans:Unified Parameter-Efficient Transfer Learning and Multimodal Alignment for Large Multimodal Foundation Model

引用

computers, Materials & Continua 2025年第4期83卷 219-238页

作者： Jiakang Sun Ke Chen Xinyang He Xu Liu Ke Li Cheng Peng Chengdu Institute of Computer Application Chinese Academy of SciencesChengdu610213China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing101499China

With the advancements in parameter-efficient transfer learning techniques,it has become feasible to leverage large pre-trained language models for downstream tasks under low-cost and low-resource ***,applying this technique to multimodal knowledge transfer introduces a significant challenge:ensuring alignment across modalities while minimizing the number of additional parameters required for downstream task *** paper introduces UniTrans,a framework aimed at facilitating efficient knowledge transfer across multiple *** leverages Vector-based Cross-modal Random Matrix Adaptation to enable fine-tuning with minimal parameter *** further enhance modality alignment,we introduce two key components:the Multimodal Consistency Alignment Module and the Query-Augmentation Side Network,specifically optimized for scenarios with extremely limited trainable *** evaluations on various cross-modal downstream tasks demonstrate that our approach surpasses state-of-the-art methods while using just 5%of their trainable ***,it achieves superior performance compared to fully fine-tuned models on certain benchmarks.

关键词： Parameter-efficient transfer learning multimodal alignment image captioning image-text retrieval visual question answering

来源：评论

学校读者我要写书评

暂无评论

An Interactive Framework for Personalized Navigation Based on Metacosmic Cultural Tourism and Large Model Fine-tuning

引用

IEEE Access 2025年 13卷 81450-81461页

作者： Guo, Hang Liu, Zhiqiang Tang, Chuanqian Zhang, Xiaodan Qinghai University School of Computer Technology and Application Xining China Qinghai University Qinghai Provincial Intelligent Computing and Application Laboratory Xining China

With the wide application of Large Language models (LLMs) and the rapid growth of metaverse tourism demand, the digital tour and personalized interaction of historical sites have become the key to improving users’ digital travel experience. Creating an environment where users can access rich cultural information and enjoy personalized, immersive experiences is a crucial issue in the field of digital cultural travel. To this end, we propose a tourism information multimodal generation personalized question-answering interactive framework TIGMI based on LLM fine-tuning, which aims to provide a richer and more in-depth experience for virtual Tours of historical monuments. Taking Qutan Temple as an example, the framework combines LLM, retrieval augmented generation (RAG), and auto-prompting engineering techniques to retrieve accurate information related to the historical monument from external knowledge bases and seamlessly integrates it into the generated content. This integration mechanism ensures the accuracy and relevance of the generated answers. Through TIGMI’s LLM-driven command interaction mechanism in the 3D digital scene of Qutan Temple, users are able to interact with the building and scene environment in a personalized and real-time manner, successfully integrating historical and cultural information with modern digital technology. This integration significantly enhances the naturalness of interaction and personalizes the user experience, thereby improving user immersion and information acquisition efficiency. Evaluation results show that TIGMI excels in question-answering and multimodal interactions, significantly enhancing the depth and breadth of services provided by the personalized virtual tour. We conclude by addressing the limitations of TIGMI and briefly discuss how future research will focus on further improving the accuracy and user satisfaction of the generated content to adapt to the dynamically changing tourism environment. © 2013 IEEE.

关键词： Leisure

来源：评论

学校读者我要写书评

暂无评论

Ensemble Knowledge Distillation for Federated Semi-Supervised Image Classification

引用

Tsinghua Science and technology 2025年第1期30卷 112-123页

作者： Ertong Shang Hui Liu Jingyang Zhang Runqi Zhao Junzhao Du School of Computer Science and Technology Xidian UniversityXi’an 710126China Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of EducationXi’an 710126China Key Laboratory of Smart Human-Computer Interaction and Wearable Technology of Shaanxi Province Xi’an 710126China

Federated learning is an emerging privacy-preserving distributed learning paradigm,in which many clients collaboratively train a shared global model under the orchestration of a remote *** current works on federated learning have focused on fully supervised learning settings,assuming that all the data are annotated with ground-truth ***,this work considers a more realistic and challenging setting,Federated Semi-Supervised Learning(FSSL),where clients have a large amount of unlabeled data and only the server hosts a small number of labeled *** to reasonably utilize the server-side labeled data and the client-side unlabeled data is the core challenge in this *** this paper,we propose a new FSSL algorithm for image classification based on consistency regularization and ensemble knowledge distillation,called *** algorithm uses the global model as the teacher in consistency regularization methods to enhance both the accuracy and stability of client-side unsupervised learning on unlabeled ***,we introduce an additional ensemble knowledge distillation loss to mitigate model overfitting during server-side retraining on labeled *** experiments on several image classification datasets show that our EKDFSSL outperforms current baseline methods.

关键词： federated learning semi-supervised learning federated semi-supervised learning knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Optimal Production Capacity Matching for Blockchain-Enabled Manufacturing Collaboration With the Iterative Double Auction Method

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 550-562页

作者： Ying Chen Feilong Lin Zhongyu Chen Changbing Tang Cailian Chen the Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University the School of Computer Science and Technology Zhejiang Normal University IEEE the College of Physics and Electronic Information Engineering Zhejiang Normal University the Department of Automation Shanghai Jiao Tong University

The increased demand for personalized customization calls for new production modes to enhance collaborations among a wide range of manufacturing practitioners who unnecessarily trust each other. In this article, a blockchain-enabled manufacturing collaboration framework is proposed, with a focus on the production capacity matching problem for blockchainbased peer-to-peer(P2P) collaboration. First, a digital model of production capacity description is built for trustworthy and transparent sharing over the blockchain. Second, an optimization problem is formulated for P2P production capacity matching with objectives to maximize both social welfare and individual benefits of all participants. Third, a feasible solution based on an iterative double auction mechanism is designed to determine the optimal price and quantity for production capacity matching with a lack of personal information. It facilitates automation of the matching process while protecting users' privacy via blockchainbased smart contracts. Finally, simulation results from the Hyperledger Fabric-based prototype show that the proposed approach increases social welfare by 1.4% compared to the Bayesian game-based approach, makes all participants profitable,and achieves 90% fairness of enterprises.

关键词： Blockchain iterative double auction manufacturing collaboration production capacity matching

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security in Distributed Drone-Based Litchi Fruit Recognition and Localization Systems

引用

computers, Materials & Continua 2025年第2期82卷 1985-1999页

作者： Liang Mao Yue Li Linlin Wang Jie Li Jiajun Tan Yang Meng Cheng Xiong Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence Application Technology Research Institute Shenzhen Polytechnic UniversityShenzhen518055China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China

This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations. Our method incorporates depth information to ensure precise localization and utilizes a streamlined detection network centered on the RepVGG module. This module replaces the traditional C2f module, enhancing detection performance while maintaining speed. To bolster the detection of small, distant fruits in complex settings, we integrate Selective Kernel Attention (SKAttention) and a specialized small-target detection layer. This adaptation allows the system to manage difficult conditions, such as variable lighting and obstructive foliage. To reinforce security, the tasks of recognition and localization are distributed among multiple drones, enhancing resilience against tampering and data manipulation. This distribution also optimizes resource allocation through collaborative processing. The model remains lightweight and is optimized for rapid and accurate detection, which is essential for real-time applications. Our proposed system, validated with a D435 depth camera, achieves a mean Average Precision (mAP) of 0.943 and a frame rate of 169 FPS, which represents a significant improvement over the baseline by 0.039 percentage points and 25 FPS, respectively. Additionally, the average localization error is reduced to 0.82 cm, highlighting the model’s high precision. These enhancements render our system highly effective for secure, autonomous fruit-picking operations, effectively addressing significant performance and cybersecurity challenges in agriculture. This approach establishes a foundation for reliable, efficient, and secure distributed fruit-picking applications, facilitating the advancement of autonomous systems in contemporary agricultural practices.

关键词： Objective detection deep learning machine learning

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-Object Tracking Using Vision Sensor with Fine-Grained Cues in Occluded and Dynamic Scenes

引用

IEEE Sensors Journal 2025年第11期25卷 20547-20560页

作者： Hu, Yaoqi Sun, Jinqiu Jin, Hao Niu, Axi Yan, Qingsen Zhu, Yu Zhang, Yanning School of Computer Science China School of Astronautics China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Dongxiang Road Shaanxi Xi'an710129 China

Multi-object tracking (MOT) using vision sensors remains a challenging problem, particularly in dynamic backgrounds and severe occlusions. Existing methods, relying on holistic appearance or spatial cues, fail to capture detailed information within object regions and the background, resulting in inaccurate and inconsistent tracking. To address these issues, we propose a novel Detail-Driven Multi-Object Tracking (DD-MOT) method that revisits and leverages fine-grained cues to discover the dynamics of both object regions and the background, facilitating the recovery and association of trajectories. Specifically, the proposed method consists of three key modules: (i) Points Trajectories Generator, (ii) Camera Motion and Occlusion Compensation, and (iii) Fine- and Coarsegrained Association. The Points Trajectories Generator is responsible for generating fine-grained cues by sampling an initial set of points, generating point trajectories, and refining the initial set of points. The Camera Motion and Occlusion Compensation module utilizes the background and object point trajectories to correct background motion and recover occluded object bounding boxes. Finally, the Fine- and Coarse-grained Association module leverages point trajectory cues to assist in establishing a more effective association strategy, combining both fine-grained and coarse-grained spatial cues from the object bounding boxes. We evaluate our DD-MOT method on several benchmark datasets, including MOT17, MOT20, demonstrating that it consistently outperforms state-of-the-art (SOTA) methods in key metrics such as HOTA (64.2, 62.6), MOTA (80.8, 78.1), and IDF1 (78.8, 77.1). © 2025 IEEE.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Fall Detection and Alerts in Hearing Aids for Deaf using Generative AI 2

Fall Detection and Alerts in Hearing Aids for Deaf using Gen...

引用

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

作者： Tripathi, Bharat Lal Saini, Madan Jain, Manish Saxena, Apoorva Pal, Narendra Department of Computer Application Allenhouse Institute of Technology Kanpur India Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab India Department of Computer Application Allenhouse Business School Kanpur India Department of Computer Science & Engineering Axis Institute of Technology & Management Kanpur India Department of Computer Science & Engineering Invertis University Bareilly India

ISBN: (纸本)9798331530389

Individuals with sensorineural hearing loss often experience difficulty comprehending speech when background noise is present. This paper investigates the extent of this problem in various listening scenarios and with different types of background sounds. Additionally, the section explores the contributing factors to this challenge such as reduced audibility, reduced frequency selectivity, loudness recruitment, and dead regions in the cochlea where there are no surviving inner hair cells and or neurons. The sections evaluate different techniques for compensating for the effects of these factors. While signal-processing methods using the output of a single microphone to compensate for reduced frequency selectivity have had limited success, techniques utilizing multiple microphones have proven effective. Amplitude compression has also been effective in compensating for the effects of loudness recruitment, enabling individuals to understand speech across a wide range of sound levels. Next, the paper delves into the technical aspects of implementing fall detection systems in hearing aids, learning algorithms are also investigated for their potential in enhancing fall detection accuracy and minimizing false alarms. Furthermore, the importance of user-friendly interfaces and customization features in ensuring the effectiveness and acceptance of fall detection alerts is also highlighted. The paper also addresses the ethical and privacy considerations associated with fall detection in hearing aids. It emphasizes the need for transparent data handling practices and user consent, while also addressing potential concerns related to user autonomy and intrusion. © 2025 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Data Processing Support Model of Government Information System Based on Deep Learning

Research on Intelligent Data Processing Support Model of Gov...

引用

2025 Asia-Europe Conference on Cybersecurity, Internet of Things and Soft Computing, CITSC 2025

作者： Lu, Dapeng Liu, Haojie Zhuhai College of Science and Technology School of Tourism and Public Administration Guangdong Zhuhai519000 China Henan University of Technology Computer Application Technology Zhengzhou450001 China

ISBN: (纸本)9798331504205

This study constructs a data processing model that supports government information system. By designing a deep learning algorithm suitable for government scenarios, intelligent processing functions such as text analysis and image recognition are integrated into the system, aiming to achieve accurate processing of multi-source government data. The model design includes data preprocessing, feature extraction, algorithm optimization and adaptive learning modules to improve the recognition and analysis capabilities of complex government data. Through system simulation, this paper verifies the effectiveness of the proposed model. The simulation data shows that the model is significantly superior to traditional methods in data processing speed, accuracy and resource utilization. Precise experimental results show that the accuracy of the model in text data classification, image data recognition and other aspects reaches more than 96%. At the same time, it can effectively shorten the processing time in large-scale data processing tasks, providing technical support for the practical application of intelligent government information system. This study provides an efficient and scalable solution for intelligent data processing in government information system. © 2025 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Efficient and fine-grained access control with fully-hidden policies for cloud-enabled IoT

引用

Digital Communications and Networks 2025年第2期11卷 473-481页

作者： Qi Li Gaozhan Liu Qianqian Zhang Lidong Han Wei Chen Rui Li Jinbo Xiong School of Computer Science Nanjing University of Posts and Telecommunications Key Laboratory of Cryptography of Zhejiang Province Hangzhou Normal University Tongda College of Nanjing University of Posts and Telecommunications Henan Key Laboratory of Network Cryptography Technology School of Computer Science and Technology Xidian University State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Normal University Faculty of Software Fujian Normal University

Ciphertext-Policy Attribute-Based Encryption(CP-ABE) enables fine-grained access control on ciphertexts, making it a promising approach for managing data stored in the cloud-enabled Internet of Things. But existing schemes often suffer from privacy breaches due to explicit attachment of access policies or partial hiding of critical attribute content. Additionally, resource-constrained IoT devices, especially those adopting wireless communication, frequently encounter affordability issues regarding decryption costs. In this paper, we propose an efficient and fine-grained access control scheme with fully hidden policies(named FHAC). FHAC conceals all attributes in the policy and utilizes bloom filters to efficiently locate them. A test phase before decryption is applied to assist authorized users in finding matches between their attributes and the access policy. Dictionary attacks are thwarted by providing unauthorized users with invalid values. The heavy computational overhead of both the test phase and most of the decryption phase is outsourced to two cloud servers. Additionally, users can verify the correctness of multiple outsourced decryption results simultaneously. Security analysis and performance comparisons demonstrate FHAC's effectiveness in protecting policy privacy and achieving efficient decryption.

关键词： Access control Policy hiding Verifiable outsourced computation Cloud IoT

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Operation and Maintenance Management System for Teaching Building Based on IoT+WebGIS 3D Visualization 24

Design and Implementation of Operation and Maintenance Manag...

引用

8th International Conference on Electronic Information technology and computer Engineering, EITCE 2024

作者： Zhao, Yongheng Seng, Bingfeng Liu, Xiaojing Wang, Shuhong School of Computer Technology and Application Qinghai University Qinghai Xining China Qinghai Provincial Key Laboratory of Media Integration Technology and Communication Qinghai Xining China

ISBN: (纸本)9798400710094

Building an operation and maintenance system for teaching buildings that integrates"three-dimensional visualization" and"digital informatization" is essential for realizing a smart campus. To address the limitations of current systems in real-time monitoring and visualization, this study integrates Internet of Things (IoT) technology with WebGIS three-dimensional visualization techniques to develop an operation and maintenance management system, taking the teaching building of the school of computer Science at Qinghai University as a case study. The system achieves real-time data collection and dynamic monitoring through IoT devices, and integrates multiple functions, including live three-dimensional model display, indoor and outdoor environmental monitoring, fire alarm and early warning, classroom and equipment management, security monitoring, and energy consumption analysis. This system not only facilitates the transformation of traditional teaching buildings into smart and information-based infrastructure, but also provides operational staff with efficient and intelligent management tools. © 2024 Copyright held by the owner/author(s).

关键词： Fire alarm systems

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：