检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Fan, Yunfeng Xu, Wenchao Wang, Haozhao Liu, Junhong Guo, Song Department of Computing The Hong Kong Polytechnic University Hong Kong Hong Kong School of Computer Science and Technology Huazhong University of Science and Technology Hubei China School of Software Beihang University Beijing China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong

ISBN: (纸本)9798400706868

Recently, Multimodal Learning (MML) has gained significant interest as it compensates for single-modality limitations through comprehensive complementary information within multimodal data. However, traditional MML methods generally use the joint learning framework with a uniform learning objective that can lead to the modality competition issue, where feedback predominantly comes from certain modalities, limiting the full potential of others. In response to this challenge, this paper introduces DI-MML, a novel detached MML framework designed to learn complementary information across modalities under the premise of avoiding modality competition. Specifically, DI-MML addresses competition by separately training each modality encoder with isolated learning objectives. It further encourages cross-modal interaction via a shared classifier that defines a common feature space and employing a dimension-decoupled unidirectional contrastive (DUC) loss to facilitate modality-level knowledge transfer. Additionally, to account for varying reliability in sample pairs, we devise a certainty-aware logit weighting strategy to effectively leverage complementary information at the instance level during inference. Extensive experiments conducted on audio-visual, flow-image, and front-rear view datasets show the superior performance of our proposed method. The code is released at https://***/fanyunfeng-bit/DI-MML. © 2024 Owner/Author.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Efficient Large-Scale Constraint Optimization Problem Solving by Integrating Machine Learning and Automated Reasoning 2

Advancing Efficient Large-Scale Constraint Optimization Prob...

引用

2nd International Workshop on Spatio-Temporal Reasoning and Learning, STRL 2023

作者： Kong, Shufeng School of Software Engineering Sun Yat-sen University Guangzhou China Department of Computer Science Cornell University Ithaca United States

来源：评论

学校读者我要写书评

暂无评论

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge Computing Environment

引用

China Communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

来源：评论

学校读者我要写书评

暂无评论

Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification 24

Category-Prompt Refined Feature Learning for Long-Tailed Mul...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yan, Jiexuan Huang, Sheng Mu, Nankun Huangfu, Luwen Liu, Bo School of Big Data & Software Engineering Chongqing University Chongqing China College of Computer Science Chongqing University Chongqing China Fowler College of Business San Diego State University San DiegoCA United States School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9798400706868

Real-world data consistently exhibits a long-tailed distribution, often spanning multiple categories. This complexity underscores the challenge of content comprehension, particularly in scenarios requiring Long-Tailed Multi-Label image Classification (LTMLC). In such contexts, imbalanced data distribution and multi-object recognition pose significant hurdles. To address this issue, we propose a novel and effective approach for LTMLC, termed Category-Prompt Refined Feature Learning (CPRFL), utilizing semantic correlations between different categories and decoupling category-specific visual representations for each category. Specifically, CPRFL initializes category-prompts from the pretrained CLIP's embeddings and decouples category-specific visual representations through interaction with visual features, thereby facilitating the establishment of semantic correlations between the head and tail classes. To mitigate the visual-semantic domain bias, we design a progressive Dual-Path Back-Propagation mechanism to refine the prompts by progressively incorporating context-related visual information into prompts. Simultaneously, the refinement process facilitates the progressive purification of the category-specific visual representations under the guidance of the refined prompts. Furthermore, taking into account the negative-positive sample imbalance, we adopt the Asymmetric Loss as our optimization objective to suppress negative samples across all classes and potentially enhance the head-to-tail recognition performance. We validate the effectiveness of our method on two LTMLC benchmarks and extensive experiments demonstrate the superiority of our work over *** code is available at https://***/jiexuanyan/CPRFL. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semi-Discrete Optimal Transport for Long-Tailed Classification

引用

计算机科学技术学报（英文版） 2025年第1期40卷 252-266页

作者：金连宝雷娜罗钟铉吴瑾艾超顾险峰 1School of Mathematical Sciences Dalian University of Technology Dalian 116024 China 2International School of Information Science and Engineering Dalian University of Technology Dalian 116024 China 3School of Software Technology Dalian University of Technology Dalian 116024 China 4Huawei Technologies Co. Ltd Shenzhen 518100 China 5Department of Computer Science Stony Brook University New York 11794-2424 U.S.A.

The long-tailed data distribution poses an enormous challenge for training neural networks in classification.A classification network can be decoupled into a feature extractor and a *** paper takes a semi-discrete opti-mal transport(OT)perspective to analyze the long-tailed classification problem,where the feature space is viewed as a continuous source domain,and the classifier weights are viewed as a discrete target *** classifier is indeed to find a cell decomposition of the feature space with each cell corresponding to one *** imbalanced training set causes the more frequent classes to have larger volume cells,which means that the classifier's decision boundary is biased towards less frequent classes,resulting in reduced classification performance in the inference ***,we propose a novel OT-dynamic softmax loss,which dynamically adjusts the decision boundary in the training phase to avoid overfitting in the tail *** addition,our method incorporates the supervised contrastive loss so that the feature space can satisfy the uniform distribution *** and comprehensive experiments demonstrate that our method achieves state-of-the-art performance on multiple long-tailed recognition benchmarks,including CIFAR-LT,ImageNet-LT,iNaturalist 2018,and Places-LT.

关键词： semi-discrete optimal transport long-tailed classification decision boundary supervised contrastive loss

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent access control technology of face recognition model based on parameter sharing and dense connection

引用

International Journal of Computational Intelligence Studies 2023年第3-4期12卷 255-270页

作者： Xu, Yonghua School of Computer Engineering Jinling Institute of Technology Jiangsu Nanjing211169 China Jiangsu Key Laboratory of Data Science and Smart Software Jinling Institute of Technology Nanjing211169 China

This study proposes a laboratory intelligent facial recognition system based on improved CNN, which significantly improves the accuracy of facial recognition by optimising the portrait recognition algorithm, improving CNN calculation and large parameter scale, and utilising perspective projection to improve portrait effect and sample utilisation. The experimental results show that the recognition rate has been improved by 10%, the CPU usage rate is less than 100%, and the model parameters have been reduced by more than 95%. This system can effectively and accurately recognise faces, making it suitable for embedded facial recognition devices. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Enrich Code Search Query Semantics with Raw Descriptions 19th

Enrich Code Search Query Semantics with Raw Descriptions

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Liu, Xiangzheng Liu, Jianxun Hu, Haize Liu, Yi School of Computer Science and Engineering Hunan University of Science and Technology Hunan Xiangtan China Hunan Provincial Key Laboratory for Services Computing and Novel Software Technology Hunan University of Science and Technology Hunan Xiangtan China

ISBN: (纸本)9783031545207

Code search can recommend relevant source code according to the development intention (query statement) of the demander, thereby improving the efficiency of software development. In the research of deep code search model, code description is used to replace query sentences for training. However, the heterogeneity existing between the query statement and the code description will seriously affect the accuracy of the code search model. In order to make up for the shortcomings of code search, this paper proposes a sentence-integrated query expansion method—SIQE. Unlike previous query expansion methods that focus on word-level expansion, SIQE uses the entire code description fragment as the source of query expansion. And by learning the mapping relationship between the query statement and the code description, the heterogeneity problem between them is compensated. In order to verify the effect of the proposed model in code search tasks, the article conducts code search experiments and analyzes on two languages: python and java. Experimental results show that, compared with the baseline model, SIQE has higher code search results. Therefore, the SIQE model can effectively improve the search effect of query statements, improve the accuracy of code search, and further improve the development of software engineering. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Blockchain System Based on Differential Privacy

Intelligent Blockchain System Based on Differential Privacy

引用

2021 International Conference on Intelligent Power and Systems, ICIPS 2021

作者： Wu, Z.J. Dai, H. Yuan, Y.K. Meng, D. School of Computer and Software Engineering University of Science and Technology Liaoning Anshan114051 China

Due to the advantages of decentralization, traceability and non deletion, blockchain technology can be well combined with differential privacy algorithm to protect data privacy. Therefore, it effectively ensures the privacy security of data stored in the system in terms of technical structure and algorithm. This paper proposes a micro service system architecture based on super ledger fabric, which carries out data privacy noise processing combined with smart contract, and carries out different noise processing according to the security level recognized by the system at the time of user registration. The implementation and test results of the system show that the system architecture has good scalability, traceability and security, can meet the query control of users for data privacy, and effectively prevent the tampering and destruction of data by malicious attackers. © Published under licence by IOP Publishing Ltd.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Accurate Reliability Analysis Methods for Approximate Computing Circuits

引用

Tsinghua science and Technology 2022年第4期27卷 729-740页

作者： Zhen Wang Guofa Zhang Jing Ye Jianhui Jiang Fengyong Li Yong Wang School of the Computer Science and Technology Shanghai University of Electric PowerShanghai 200090China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China School of Software Engineering Tongji UniversityShanghai 200092China

In recent years,Approximate Computing Circuits(ACCs)have been widely used in applications with intrinsic tolerance to *** the increased availability of approximate computing circuit approaches,reliability analysis methods for assessing their fault vulnerability have become highly *** this study,two accurate reliability evaluation methods for approximate computing circuits are *** reliability of approximate computing circuits is calculated on the basis of the iterative Probabilistic Transfer Matrix(PTM)*** the calculation,the correlation coefficients are derived and combined to deal with the correlation problem caused by fanout *** accuracy and scalability of the two methods are verified using three sets of approximate computing circuit instances and more circuits in Evo Approx8 b,which is an approximate computing circuit open source *** results show that relative to the Monte Carlo simulation,the two methods achieve average error rates of 0.46%and 1.29%and time overheads of 0.002%and 0.1%.Different from the existing approaches to reliability estimation for approximate computing circuits based on the original PTM model,the proposed methods reduce the space overheads by nearly 50%and achieve time overheads of 1.78%and 2.19%.

关键词： Approximate Computing Circuit(ACC) correlation coefficient iterative Probabilistic Transfer Matrix(PTM) reliability

来源：评论

学校读者我要写书评

暂无评论

EvdCLIP: Improving Vision-Language Retrieval with Entity Visual Descriptions from Large Language Models 39

EvdCLIP: Improving Vision-Language Retrieval with Entity Vis...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Meng, GuangHao He, Sunan Wang, Jinpeng Dai, Tao Zhang, Letian Zhu, Jieming Li, Qing Wang, Gang Zhang, Rui Jiang, Yong Tsinghua Shenzhen International Graduate School Tsinghua University China Peng Cheng Laboratory China School of Computer Science & Tech Huazhong University of Science and Technology China College of Computer Science and Software Engineering Shenzhen University China Huawei Noah’s Ark Lab Canada Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)157735897X

Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images (or text). However, existing methods often neglect the rich visual semantics knowledge of entities, thus leading to incorrect retrieval results. To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries. Specifically, since humans recognize entities through visual cues, we employ a large language model (LLM) to generate Entity Visual Descriptions (EVDs) as alignment cues to complement textual data. These EVDs are then integrated into raw queries to create visually-rich, EVD-enhanced queries. Furthermore, recognizing that EVD-enhanced queries may introduce noise or low-quality expansions, we develop a novel, trainable EVD-aware Rewriter (EaRW) for vision-language retrieval tasks. EaRW utilizes EVD knowledge and the generative capabilities of the language model to effectively rewrite queries. With our specialized training strategy, EaRW can generate high-quality and low-noise EVD-enhanced queries. Extensive quantitative and qualitative experiments on image-text retrieval benchmarks validate the superiority of EvdCLIP on vision-language retrieval tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Visual languages

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：