检索结果-内蒙古大学图书馆

A Method for Fast Feature Selection Utilizing Cross-Similarity within the Context of Fuzzy Relations

Computers, Materials & Continua 2025年第4期83卷 1195-1218页

作者： Wenchang Yu Xiaoqin Ma Zheqing Zhang Qinli Zhang School of Big Data and Artificial Intelligence Chizhou UniversityChizhou247000China Anhui Education Big Data Intelligent Perception and Application Engineering Research Center Anhui Provincial Joint Construction Key Laboratory of Intelligent Education Equipment and TechnologyChizhou247000China

Feature selection methods rooted in rough sets confront two notable limitations:their high computa-tional complexity and sensitivity to noise,rendering them impractical for managing large-scale and noisy *** primary issue stems from these methods’undue reliance on all *** overcome these challenges,we introduce the concept of cross-similarity grounded in a robust fuzzy relation and design a rapid and robust feature selection ***,we construct a robust fuzzy relation by introducing a truncation ***,based on this fuzzy relation,we propose the concept of cross-similarity,which emphasizes the sample-to-sample similarity relations that uniquely determine feature importance,rather than considering all such relations *** studying the manifestations and properties of cross-similarity across different fuzzy granularities,we propose a forward greedy feature selection algorithm that leverages cross-similarity as the foundation for information *** algorithm significantly reduces the time complexity from O(m2n2)to O(mn2).Experimental findings reveal that the average runtime of five state-of-the-art comparison algorithms is roughly 3.7 times longer than our algorithm,while our algorithm achieves an average accuracy that surpasses those of the five comparison algorithms by approximately 3.52%.This underscores the effectiveness of our *** paper paves the way for applying feature selection algorithms grounded in fuzzy rough sets to large-scale gene datasets.

关键词： Fuzzy rough sets feature selection cross-similarity fuzzy relations

来源：评论

学校读者我要写书评

暂无评论

ControlVideo: conditional control for one-shot text-driven video editing and beyond

引用

Science China(Information Sciences) 2025年第3期68卷 150-162页

作者： Min ZHAO Rongzhen WANG Fan BAO Chongxuan LI Jun ZHU Department of Computer Science and Technology Institute for AI Tsinghua-Bosch Joint ML CenterTsinghua Laboratory of Brain and Intelligence Lab Tsinghua University ShengShu Technology Gaoling School of Artificial Intelligence Renmin University of China Beijing Key Laboratory of Big Data Management and Analysis Methods Pazhou Laboratory (Huangpu)

This paper presents ControlVideo for text-driven video editing — generating a video that aligns with a given text while preserving the structure of the source video. Building on a pre-trained text-to-image diffusion model, ControlVideo enhances the fidelity and temporal consistency by incorporating additional conditions(such as edge maps), and fine-tuning the key-frame and temporal attention on the source video-text pair via an in-depth exploration of the design space. Extensive experimental results demonstrate that ControlVideo outperforms various competitive baselines by delivering videos that exhibit high fidelity w.r.t. the source content, and temporal consistency, all while aligning with the text. By incorporating low-rank adaptation layers into the model before training, ControlVideo is further empowered to generate videos that align seamlessly with reference images. More importantly, ControlVideo can be readily extended to the more challenging task of long video editing(e.g., with hundreds of frames), where maintaining long-range temporal consistency is crucial. To achieve this, we propose to construct a fused ControlVideo by applying basic ControlVideo to overlapping short video segments and key frame videos and then merging them by pre-defined weight functions. Empirical results validate its capability to create videos across 140 frames, which is approximately 5.83 to 17.5 times more than what previous studies achieved. The code is available at https://***/thu-ml/controlvideo.

关键词： diffusion models controllable generation text-driven editing video editing long video editing

来源：评论

学校读者我要写书评

暂无评论

VIDF-SR: A Multispectral Super-resolution Method Based on Visible-infrared Difference Feature Maps 10

VIDF-SR: A Multispectral Super-resolution Method Based on Vi...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Wang, Yuanzhe Jin, Yi Wang, Xu Zeng, Yuqiao Li, Yidong Beijing Jiaotong University Beijing China Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education The State Key Laboratory of Advanced Rail Autonomous Operation China

ISBN: (纸本)9798331520861

Multispectral super-resolution aims to recover a high-resolution image from low-resolution images of two modalities. The primary challenges are the poor quality of visible light images under low-light conditions and the inherently low resolution and insufficient structural information in infrared images. There are relatively few approaches dedicated to multispectral super-resolution so far as most methods focus on single-image super-resolution. The existing methods on multispectral super-resolution typically rely on simple convolution and upsampling techniques, resulting in suboptimal performance. To address these issues, we propose a multispectral super-resolution method based on visible-infrared difference feature maps (VIDF-SR) in this study. Specifically, to effectively utilize the superior structural information from the visible light modality and the clearer texture and edge information from the infrared modality during the reconstruction process, we introduce the Modal Information Complementary Module (MICM), which generates fused features based on the difference feature maps between the two modalities, retaining key information from both. Furthermore, to produce clearer multispectral super-resolution images, we design the Feature Map Super-Resolution Module (FMSR), incorporating a diffusion model into our framework to achieve superior performance. Experiments on the M3FD dataset show that our method surpasses current approaches, with ablation studies providing additional confirmation of the effectiveness of each component. © 2024 IEEE.

关键词： Light modulation

来源：评论

学校读者我要写书评

暂无评论

Orangutan: A Compression Algorithm for Precision-Redundant Floating-Point Time Series 3

Orangutan: A Compression Algorithm for Precision-Redundant F...

引用

3rd International Conference on High Performance Computing and Communication Engineering, HPCCE 2023

作者： Zhao, Zhenshan Qu, Youli Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University No. 3 Shangyuan Village Haidian District Beijing100044 China

ISBN: (数字)9781510674653

ISBN: (纸本)9781510674646

IoT devices and various sensors generate a large amount of time-series data every moment, and the cost of transmitting and storing this data is high. Compact, efficient, and lossless compression of time series is a common solution. Current state-of-the-art lossless compression algorithms for time series are based on XOR operations but do not take advantage of the fact that most floating-point sequences in real life have precision redundancy. In this paper, we propose a unique trailing bit zeroing scheme called Orangutan, which can zero as many trailing bits as possible in O(1) time without incurring any additional space overhead, resulting in a higher compression ratio. In addition, we also designed the compression and decompression methods specifically for the case of more zeroes in the tail bits and can obtain good compression results. Comparing Orangutan with 9 current state-of-the-art compression algorithms on 19 datasets shows that Orangutan is more space-efficient than the best compression algorithms currently used for time series, and the compression speed is at the same level as them. © 2024 SPIE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

SINN: A structural information-based neural network for traffic flow forecasting in large-scale road networks 4

SINN: A structural information-based neural network for traf...

引用

4th International Conference on Internet of Things and Smart City, IoTSC 2024

作者： Zhu, Weiguo Liu, Caiyuan Zhang, Xingyu Sun, Yongqi Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9781510681767

Current traffic flow forecasting is a crucial component within intelligent transportation systems (ITSs). However, most existing studies still cannot be employed on large-scale data flow forecasting in real-world scenarios. In this paper, we design a spatiotemporal neural network called SINN for large-scale traffic flow forecasting tasks in real-world scenarios. First, we propose a transformer-based neural network to integrate the historical traffic flow into further traffic flow. Second, we propose a structural information-based hierarchical graph neural network module suitable for large-scale network structures, which can capture relevant node features within large-scale road networks for forecasting future traffic flow. Finally, we collect a large-scale traffic flow dataset and execute evaluation experiments. The experimental results indicate that SINN is capable of processing datasets with thousands of nodes. Compared with the methods that can execute the same scale datasets, SINN can make significant improvements by 44.29%, 26.54%, and 25.23% in the metrics of MAE, RMSE, and MAPE. © 2024 SPIE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Few-shot 3D Point Cloud Segmentation via Relation Consistency-guided Heterogeneous Prototypes

引用

IEEE Transactions on Multimedia 2025年 27卷 3158-3170页

作者： Wei, Lili Lang, Congyan Xu, Zheming Liang, Liqian Liu, Jun Ministry of Education Key Laboratory of Big Data & Artificial Intelligence in Transportation China Beijing Jiaotong University School of Computer Science & Technology Beijing100044 China Lancaster University LA1 4YW Lancaster United Kingdom

Few-shot 3D point cloud semantic segmentation is a challenging task due to the lack of labeled point clouds (support set). To segment unlabeled query point clouds, existing prototype-based methods learn 3D prototypes from point features of the support set and then measure their distances to the query points. However, such homogeneous 3D prototypes are often of low quality because they overlook the valuable heterogeneous information buried in the support set, such as semantic labels and projected 2D depth maps. To address this issue, in this paper, we propose a novel Relation Consistency-guided Heterogeneous Prototype learning framework (RCHP), which improves prototype quality by integrating heterogeneous information using large multi-modal models (e.g. CLIP). RCHP achieves this through two core components: Heterogeneous Prototype Generation module which collaborates with 3D networks and CLIP to generate heterogeneous prototypes, and Heterogeneous Prototype Fusion module which effectively fuses heterogeneous prototypes to obtain high-quality prototypes. Furthermore, to bridge the gap between heterogeneous prototypes, we introduce a Heterogeneous Relation Consistency loss, which transfers more reliable inter-class relations (i.e., inter-prototype relations) from refined prototypes to heterogeneous ones. Extensive experiments conducted on five point cloud segmentation datasets, including four indoor datasets (S3DIS, ScanNet, SceneNN, NYU Depth V2) and one outdoor dataset (Semantic3D), demonstrate the superiority and generalization capability of our method, outperforming state-of-the-art approaches across all datasets. The code will be released as soon as the paper is accepted. © 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

引用

High-Speed Railway 2024年第2期2卷 101-109页

作者： Jiaxu Guo Ding Ding Peihan Yang Qi Zou Yaping Huang School of Computer Science and Technology Beijing Jiaotong UniversityBeijing 100044China Key Laboratory of Big Data&Artificial Intelligence in Transportation Ministry of EducationBeijing 100044China

It is of great significance to improve the efficiency of railway production and operation by realizing the fault knowledge association through the efficient data mining ***,high utility quantitative frequent pattern mining algorithms in the field of data mining still suffer from the problems of low time-memory performance and are not easy to scale *** the context of such needs,we propose a related degree-based frequent pattern mining algorithm,named Related High Utility Quantitative Item set Mining(RHUQI-Miner),to enable the effective mining of railway fault *** algorithm constructs the item-related degree structure of fault data and gives a pruning optimization strategy to find frequent patterns with higher related degrees,reducing redundancy and invalid frequent ***,it uses the fixed pattern length strategy to modify the utility information of the item in the mining process so that the algorithm can control the length of the output frequent pattern according to the actual data situation and further improve the performance and practicability of the *** experimental results on the real fault dataset show that RHUQI-Miner can effectively reduce the time and memory consumption in the mining process,thus providing data support for differentiated and precise maintenance strategies.

关键词： High utility Quantitative Frequent pattern mining Related degree pruning Fixed pattern length

来源：评论

学校读者我要写书评

暂无评论

Graph distillation with network symmetry

引用

Chinese Physics B 2025年第4期34卷 262-271页

作者： Feng Lin Jia-Lin He China West Normal University Nanchong 637000China The Internet of Things Perception and Big Data Analysis Key Laboratory of Nanchong City Nanchong 637000China Institute of Artificial Intelligence China West Normal UniversityNanchong 637000China

Graph neural networks(GNNs)have demonstrated excellent performance in graph representation ***,as the volume of graph data grows,issues related to cost and efficiency become increasingly *** distillation methods address this challenge by extracting a smaller,reduced graph,ensuring that GNNs trained on both the original and reduced graphs show similar *** methods,however,primarily optimize the feature matrix of the reduced graph and rely on correlation information from GNNs,while neglecting the original graph’s structure and redundant *** often results in a loss of critical information within the reduced *** overcome this limitation,we propose a graph distillation method guided by network ***,we identify symmetric nodes with equivalent neighborhood structures and merge them into“super nodes”,thereby simplifying the network structure,reducing redundant parameter optimization and enhancing training *** the same time,instead of relying on the original node features,we employ gradient descent to match optimal features that align with the original features,thus improving downstream task ***,our method guarantees that the reduced graph retains the key information present in the original *** experiments demonstrate that our approach achieves significant improvements in graph distillation,exhibiting strong generalization capability and outperforming existing graph reduction methods.

关键词： graph neural networks graph distillation network symmetry super nodes feature optimization

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Feature Selection With Multi-Scale Fuzzy Information Fusion: From Both Global and Local Perspectives

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1825-1839页

作者： Zhou, Nan Liao, Shujiao Chen, Hongmei Ding, Weiping Lu, Yaqian Minnan Normal University School of Mathematics and Statistics Fujian Key Laboratory of Granular Computing and Applications Zhangzhou363000 China Southwest Jiaotong University School of Computing and Artificial Intelligence National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

In reality, the laborious nature of label annotation leads to the widespread existence of limited labeled data. Moreover, multi-scale data have received widespread attention due to its rich knowledge representation. However, current research on multi-scale data primarily focuses on supervised learning environments, while semi-supervised feature selection for multi-scale data with limited labels remains inadequately explored. Meanwhile, existing studies on multi-scale data often emphasize selecting optimal scales and further conducting feature selection, but this strategy may result in losing potentially valuable information from other scales. To overcome these limitations, by adopting a multi-scale fuzzy information fusion mechanism, this article proposes two new semi-supervised feature selection approaches for multi-scale data with limited labels from both global and local perspectives. Initially, by fusing fuzzy information at various scales, a label learning method is proposed to convert the decision of missing labels into a fuzzy decision of label distribution. Subsequently, label-distributed multi-scale fuzzy global and local rough sets are constructed from global and local perspectives, respectively. Based on the two models, two semi-supervised feature selection algorithms are developed based on global and local multi-scale fuzzy information fusion. Experimental results demonstrate that, compared to other advanced feature selection algorithms, the two proposed algorithms can effectively handle multi-scale data with limited labels and exhibit superior classification performance, computational efficiency and robustness. © 1993-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Adversarial Example Transferability via Regularized Constrained Feature Layer

引用

Computers, Materials & Continua 2025年第4期83卷 157-175页

作者： Xiaoyin Yi Long Chen Jiacheng Huang Ning Yu Qian Huang School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Chongqing Key Laboratory of Public Big Data Security Technology Chongqing401420China School of Cyber Security and Information Law Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of EducationChongqing400065China Artificial Intelligence and Big Data College Chongqing Polytechnic University of Electronic TechnologyChongqing401331China

Transfer-based Adversarial Attacks(TAAs)can deceive a victim model even without prior *** is achieved by leveraging the property of adversarial *** is,when generated from a surrogate model,they retain their features if applied to other models due to their good ***,adversarial examples often exhibit overfitting,as they are tailored to exploit the particular architecture and feature representation of source ***,when attempting black-box transfer attacks on different target models,their effectiveness is *** solve this problem,this study proposes an approach based on a Regularized Constrained Feature Layer(RCFL).The proposed method first uses regularization constraints to attenuate the initial examples of low-frequency *** are then added to a pre-specified layer of the source model using the back-propagation technique,in order to modify the original adversarial ***,a regularized loss function is used to enhance the black-box transferability between different target *** proposed method is finally tested on the ImageNet,CIFAR-100,and Stanford Car datasets with various target models,The obtained results demonstrate that it achieves a significantly higher transfer-based adversarial attack success rate compared with baseline techniques.

关键词： Adversarial examples black-box transferability regularized constrained transfer-based adversarial attacks

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：