检索结果-内蒙古大学图书馆

Communications technology and computer Science (ACCTCS), Asia-Pacific Conference on

作者： Jianpeng Zou Kaoru Uchida Wenxin Yao Kashing Yuen Graduate School of Computer and Information Sciences Hosei University Tokyo Japan School of Software Engineering University of Science and Technology of China Hefei China

This study presents a novel text-driven method for the editing of portraits with robustness in a sparse latent space. Due to the development of GAN and the proposal of many excellent models like StyleGAN, text-driven image editing and image generation have made great progress in recent years, but the task of generating facial images under the guidance of text is still lacking in some special situations. Our model combines and makes good use of two pre-training models, CLIP2Latent and StyleGAN2, to conduct a preliminary exploration of the above task. The latent code of the input portrait is driven to be edited and manipulated in the StyleGAN latent space via a CLIP-based text-driven generation module. Finally, some promising results have been obtained, especially in the sparse region of the generator latent space and when simultaneously changing numerous attributes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion

arXiv

引用

arXiv 2025年

作者： Liu, Jinyuan Zhang, Bowei Mei, Qingyun Li, Xingyuan Zou, Yang Jiang, Zhiying Ma, Long Liu, Risheng Fan, Xin School of Mechanical Engineering Dalian University of Technology China School of Software Technology DUT-RU International School of ISE Dalian University of Technology China School of Computer Science Northwestern Polytechnical University China College of Information Science and Technology Dalian Maritime University China

Infrared and visible image fusion integrates information from distinct spectral bands to enhance image quality by leveraging the strengths and mitigating the limitations of each modality. Existing approaches typically treat image fusion and subsequent high-level tasks as separate processes, resulting in fused images that offer only marginal gains in task performance and fail to provide constructive feedback for optimizing the fusion process. To overcome these limitations, we propose a Discriminative Cross-Dimension Evolutionary Learning Framework, termed DCEvo, which simultaneously enhances visual quality and perception accuracy. Leveraging the robust search capabilities of Evolutionary Learning, our approach formulates the optimization of dual tasks as a multi-objective problem by employing an Evolutionary Algorithm (EA) to dynamically balance loss function parameters. Inspired by visual neuroscience, we integrate a Discriminative Enhancer (DE) within both the encoder and decoder, enabling the effective learning of complementary features from different modalities. Additionally, our Cross-Dimensional Embedding (CDE) block facilitates mutual enhancement between high-dimensional task features and low-dimensional fusion features, ensuring a cohesive and efficient feature integration process. Experimental results on three benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches, achieving an average improvement of 9.32% in visual quality while also enhancing subsequent high-level tasks. The code is available at https://***/ Beate-Suy-Zhang/*** Codes 68T45 Copyright © 2025, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Online Neural Fiber Classification Method based on Lightweight Neural Network 7

Online Neural Fiber Classification Method based on Lightweig...

引用

7th International Conference on Image, Vision and Computing, ICIVC 2022

作者： Xu, Baolei Li, Xiaojie Shi, Canghong Sichuan University of Arts and Sciences Key Laboratory of Exploitation and Study of Distinctive Plants in Education Department of Sichuan Province Dazhou China Chengdu University of Information Technology School of Computer Science Chengdu China Xihua University School of Computer Science and Software Engineering Chengdu China

ISBN: (数字)9781665467346

ISBN: (纸本)9781665467346

Traditional neural fiber classification methods are generally difficult to balance classification accuracy and algorithm complexity, and there is a problem of relying on manual intervention, mainly including manual drawing of region of interest (ROI) and manual screening of target fiber bundles, resulting in uncertainty of classification results and large data error. To reduce manual intervention, balance accuracy and algorithm complexity, a simple and effective BP neural network model combined with fast image processing algorithm is proposed. Based on the neural fiber map information, this method uses the fiber coordinate information to train the classification network structure and realize the online fiber classification. While improving the classification accuracy, it also reduces the complexity of the algorithm and does not need to know the distribution of fibers in advance. Compared with several typical classification algorithms, BP neural network model has strong robustness and can effectively prevent over-fitting. The experimental results show that the method performs well in several classifiers, and the classification accuracy is optimal. The experimental training accuracy is 0.9824, and the test accuracy is 0.9774. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Based Intelligent Indoor Smoke and Fire Detection System for Smart Buildings

Federated Learning-Based Intelligent Indoor Smoke and Fire D...

引用

2024 International Conference on Telecommunications and Intelligent Systems, ICTIS 2024

作者： Aymene Berkani, Mohamed Rafik Chouchane, Ammar Himeur, Yassine Abdennebi, Anes Sagiroglu, Seref Amira, Abbes Medea Algeria University Biskra University Center of Barika Laboratory of LI3C Amdoukal Road Barika05001 Algeria University of Dubai College of Engineering and Information Technology Dubai United Arab Emirates École de Technologie Supérieure Software and Information Technology Engineering Montréal Canada Analytics Security R&D Center Gazi University Artificial Intelligence and Big Data Ankara Turkey University of Sharjah Department of Computer Science Sharjah United Arab Emirates

ISBN: (纸本)9798331527396

Ensuring safety in smart buildings is crucial due to the increasing prevalence of smoke and fire hazards in modern environments. This paper introduces a novel privacy-preserving FL approach based on a CNN1D for smoke and fire detection in smart buildings. Our system integrates data from wearable environmental sensors to train a lightweight, edge-deployable DL-CNN1D model, ensuring data privacy while enabling collaborative learning across distributed clients using Federated Averaging (FedAvg) aggregation. Experiments conducted on a comprehensive air measurement dataset for smoke and fire detection demonstrate exceptional performance, with the global model achieving 99.97% accuracy, 99.96% precision, in smoke and fire recognition. Our model demonstrates a low communication cost of 0.4 MB, underscoring its efficiency for real-time applications. Our FL-based approach represents a significant step towards balancing the need for robust safety systems with growing privacy concerns in smart building environments. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Separate and Integrate Different Level Reasoning for Event Causality Identification

Separate and Integrate Different Level Reasoning for Event C...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yuchang Deng Wenti Huang Tingxuan Chen Jun Long School of Software Xinjiang University Urumqi China School of Computer Science and Engineering Hunan University of Science and Technology Changsha China School of Computer Science and Engineering Central South University Changsha China Big Data Institute Central South University Changsha China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Document-level event causality identification (DECI) aims to discern the causal relationship between two event mentions within a document, which is a more challenging task compared to sentence-level event causality identification. However, the conventional DECI model applies the same method to all pairs of events without considering the distinctions and connections between intra-sentence and inter-sentence event pairs. This paper introduces a novel Separate and Integrate Different Level reasoning model (SIDL) to extract and fuse text features of events. Specifically, we separately encode intra-sentence and inter-sentence event pairs and leverage attention from pre-trained language models to identify the relevant context for aiding in the determination of causality. Additionally, we propose a causal reasoning strategy that leverages intra-sentence causal relationships to assist in the inference of inter-sentence causal relationships. We combine different features of event pairs by discriminating the characters and effects of intra-sentence and inter-sentence reasoning. Experimental results show that our approach achieves superior performance compared to previous models in two benchmarks EventStoryLine and CausalTimeBank.

关键词： Knowledge engineering Correlation Fuses Neural networks Cause effect analysis Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MLFuse: Multi-Scenario Feature Joint Learning for Multi-Modality Image Fusion

引用

IEEE Transactions on Multimedia 2025年

作者： Lei, Jia Li, Jiawei Liu, Jinyuan Wang, Bin Zhou, Shihua Zhang, Qiang Wei, Xiaopeng Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1010 New Zealand Ulster University Intelligent Systems Research Center LondonderryBT52 1SA United Kingdom

Multi-modality image fusion (MMIF) entails synthesizing images with detailed textures and prominent objects. Existing methods tend to use general feature extraction to handle different fusion tasks. However, these methods have difficulty breaking fusion barriers across various modalities owing to the lack of targeted learning routes. In this work, we propose a multi-scenario feature joint learning architecture, MLFuse, that employs the commonalities of multi-modality images to deconstruct the fusion progress. Specifically, we construct a cross-modal knowledge reinforcing network that adopts a multipath calibration strategy to promote information communication between different images. In addition, two professional networks are developed to maintain the salient and textural information of fusion results. The spatial-spectral domain optimizing network can learn the vital relationship of the source image context with the help of spatial attention and spectral attention. The edge-guided learning network utilizes the convolution operations of various receptive fields to capture image texture information. The desired fusion results are obtained by aggregating the outputs from the three networks. Extensive experiments demonstrate the superiority of MLFuse for infrared-visible image fusion and medical image fusion. The excellent results of downstream tasks (i.e., object detection and semantic segmentation) further verify the high-quality fusion performance of our method. The code is publicly available at https://***/jialei-sc/MLFuse. © 1999-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Empowering Adaptive Endogenous Security Trend Prediction Detection for IoT Sensor Nodes

Empowering Adaptive Endogenous Security Trend Prediction Det...

引用

Advances in Electrical, Electronics and Computing technology (EECT), International Conference on

作者： Lihu Zhou Xiuying Dong Enli Zhang Ting Wang Xiao Zhang Chong Zhang School of Computer Science and Software Engineering Southwest Petroleum University Chengdu China Exploration and Development Research Institute of PetroChina Southwest Oil & Gasfield Company Chengdu China School of Computer Science Chengdu University of Information Technology Chengdu China

ISBN: (数字)9798331541545

ISBN: (纸本)9798331541552

Massively deployed IoT devices require a lightweight design to reduce costs. However, this architecture inherently limits their security, increasing the risk of data breaches and tampering on a large scale. In this paper, we propose CGAD, a model that leverages one-dimensional convolution (Conv1D), gated recurrent units (GRU), and the attention mechanism to analyze multi-sensor time series data at the data gateway from sensing terminals. To achieve this, we generate time series predictions and detect anomalies by comparing predicted values with real data using a threshold-based approach, thereby enhancing data security. To address the labeling problem of massive data, we employ unsupervised learning and design a dynamic sliding window threshold to improve the judgment of time series with varying characteristics. We also used a number of datasets, such as the KW51 railroad bridge dataset and the self-picked temperature and humidity dataset, to evaluate our system. The results demonstrate that our CGAD model achieves recall rates of 98 % and 99 % for anomaly detection on the two datasets, respectively. Additionally, the precision and F1 scores surpass other methods, ensuring cost-effectiveness for massive terminals and addressing the security issues of sensitive data. These advantages contribute to realizing the Internet of Everything.

关键词： Adaptation models Data security Time series analysis Humidity Predictive models Logic gates Data models Sensors Internet of Things Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Three-Stage Cutting Simulation System Based on Mass-Spring Model

引用

computer Modeling in engineering & Sciences 2021年第4期127卷 117-133页

作者： Xiaorui Zhang Jiali Duan Wei Sun Tong Xu Sunil Kumar Jha Jiangsu Engineering Center of Network Monitoring Engineering Research Center of Digital ForensicsMinistry of EducationSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China Faculty of Information Technology University of Information Technology and ManagementRzeszow35-225Poland

The cutting simulation of soft tissue is important in virtual *** includes three major challenges in computation:Soft tissue simulation,collision detection,and handling,as well as soft tissue *** order to address the earlier challenges,we propose a virtual cutting system based on the mass-spring *** this system,MSM is utilized to simulate the soft tissue *** stress is introduced to the model for simulating the shrinking effect of soft tissue in ***,a cylinder-based collision detection method is used to supervise the collision between surgical tools and soft ***,we simulate the cutting operation with a three-stage cutting method with swept volume,B´ezier curve,and an algorithm named shortest distance nodes matching *** order to verify the system performance,we carry out three validation experiments on the proposed system:Cutting accuracy experiment,collision detection validation,and practical cutting *** indicate that our system can well perform the shrinking effect of soft tissue in *** system has fast and accurate collision ***,the system can reconstruct smooth incisions vividly.

关键词： Mass-spring model collision algorithm virtual surgery soft tissue simulation

来源：评论

学校读者我要写书评

暂无评论

Continuous contrastive learning for long-tailed semi-supervised recognition 24

Continuous contrastive learning for long-tailed semi-supervi...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zi-Hao Zhou Siyuan Fang Zi-Jing Zhou Tong Wei Yuanyu Wan Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

ISBN: (纸本)9798331314385

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PATCH: Empowering Large Language Model with Programmer-Intent Guidance and Collaborative-Behavior Simulation for Automatic Bug Fixing

arXiv

引用

arXiv 2025年

作者： Zhang, Yuwei Jin, Zhi Xing, Ying Li, Ge Liu, Fang Zhu, Jiaxin Dou, Wensheng Wei, Jun Affiliated with Nanjing Institute of Software Technology University of Chinese Academy of Sciences Nanjing China Key Laboratory of System Software Chinese Academy of Sciences Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Key Laboratory of High Confidence Software Technologies Peking University Ministry of Education School of Computer Science Peking University Beijing China School of Computer Science Wuhan University Wuhan China School of Intelligent Engineering and Automation Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Beihang University Beijing China

Bug fixing holds significant importance in software development and maintenance. Recent research has made substantial strides in exploring the potential of large language models (LLMs) for automatically resolving software bugs. However, a noticeable gap in existing approaches lies in the oversight of collaborative facets intrinsic to bug resolution, treating the process as a single-stage endeavor. Moreover, most approaches solely take the buggy code snippet as input for LLMs during the patch generation stage. To mitigate the aforementioned limitations, we introduce a novel stage-wise framework named PATCH. Specifically, we first augment the buggy code snippet with corresponding dependence context and intent information to better guide LLMs in generating the correct candidate patches. Additionally, by taking inspiration from bug management practices, we decompose the bug-fixing task into four distinct stages: bug reporting, bug diagnosis, patch generation, and patch verification. These stages are performed interactively by LLMs, aiming to simulate the collaborative behavior of programmers during the resolution of software bugs. By harnessing these collective contributions, PATCH effectively enhances the bug-fixing capability of LLMs. We implement PATCH by employing the powerful dialogue-based LLM ChatGPT. Our evaluation on the widely used bug-fixing benchmark BFP demonstrates that PATCH has achieved better performance than state-of-the-art LLMs. Copyright © 2025, The Authors. All rights reserved.

关键词： computer software maintenance

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：