检索结果-内蒙古大学图书馆

Probe Machine Based Computing Model for Maximum Clique Problem

Chinese Journal of Electronics 2022年第2期31卷 304-312页

作者： CUI Jianzhong YIN Zhixiang TANG Zhen YANG Jing Department of Computer Huainan Union University School of Electronic and Information Engineering Anhui University of Science & Technology School of Mathematics Physics and Statistics Shanghai University of Engineering Science School of Mathematics and Big Data Anhui University of Science & Technology

Probe machine(PM) is a recently reported mathematic model with massive parallelism. Herein,we presented searching the maximum clique of an undirected graph with six vertices. We constructed data library containing n sublibraries, each sublibrary corresponded to a vertex in the given graph. Then, probe library according to the induced subgraph was designed in order to search and generate all maximal cliques. Subsequently,we performed probe operation, and all maximal cliques were generated in parallel. The advantages of the proposed model lie in two aspects. On one hand, solution to NP-complete problem is generated in just one step of probe operation rather than found in vast solution *** the other hand, the proposed model is highly *** work demonstrates that PM is superior to TM in terms of searching capacity when tackling NP-complete problem.

关键词： maximal cliques maximum clique problem searching capacity data library NP-complete problem computational complexity model lie induced subgraph probe operation undirected graph mathematic model graph theory parallel algorithms optimisation parallelism computing model vertex probe library probe machine

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

DEEP ORTHOGONAL HYPERSPHERE COMPRESSION FOR ANOMALY DETECTION 12

DEEP ORTHOGONAL HYPERSPHERE COMPRESSION FOR ANOMALY DETECTIO...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Zhang, Yunhe Sun, Yan Cai, Jinyu Fan, Jicong School of Data Science The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Many well-known and effective anomaly detection methods assume that a reasonable decision boundary has a hypersphere shape, which however is difficult to obtain in practice and is not sufficiently compact, especially when the data are in high-dimensional spaces. In this paper, we first propose a novel deep anomaly detection model that improves the original hypersphere learning through an orthogonal projection layer, which ensures that the training data distribution is consistent with the hypersphere hypothesis, thereby increasing the true positive rate and decreasing the false negative rate. Moreover, we propose a bi-hypersphere compression method to obtain a hyperspherical shell that yields a more compact decision region than a hyperball, which is demonstrated theoretically and numerically. The proposed methods are not confined to common datasets such as image and tabular data, but are also extended to a more challenging but promising scenario, graph-level anomaly detection, which learns graph representation with maximum mutual information between the substructure and global structure features while exploring orthogonal single- or bi-hypersphere anomaly decision boundaries. The numerical and visualization results on benchmark datasets demonstrate the superiority of our methods in comparison to many baselines and state-of-the-art methods. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

science China(Information sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Autonomous Recommendation of Fault Detection Algorithms for Spacecraft

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 273-275页

作者： Wenbo Li Baoling Ning the National Key Laboratory of Science and Technology on Space Intelligent Control Beijing Institute of Control EngineeringBeijing 100094China the School of Data Science and Technology Heilongjiang UniversityHarbin 150001China

Dear Editor, This letter deals with the problem of algorithm recommendation for online fault detection of spacecraft. By transforming the time series data into distributions and introducing a distribution-aware measure, a principal method is designed for quantifying the detectabilities of fault detection algorithms over special datasets.

关键词： fault introducing letter

来源：评论

学校读者我要写书评

暂无评论

Federated learning privacy incentives:Reverse auctions and negotiations

引用

CAAI Transactions on Intelligence technology 2023年第4期8卷 1538-1557页

作者： Hongqin Lyu Yongxiong Zhang Chao Wang Shigong Long Shengnan Guo Guizhou Provincial Key Laboratory of Public Big Data Guizhou UniversityGuiyangChina College of Computer Science and Technology Guizhou UniversityGuiyangChina

The incentive mechanism of federated learning has been a hot topic,but little research has been done on the compensation of privacy *** this end,this study uses the Local SGD federal learning framework and gives a theoretical analysis under the use of differential privacy *** on the analysis,a multi‐attribute reverse auction model is proposed to be used for user selection as well as payment calculation for participation in federal *** model uses a mixture of economic and non‐economic attributes in making choices for users and is transformed into an optimisation equation to solve the user choice *** addition,a post‐auction negotiation model that uses the Rubinstein bargaining model as well as optimisation equations to describe the negotiation process and theoretically demonstrate the improvement of social welfare is *** the experimental part,the authors find that their algorithm improves both the model accuracy and the F1‐score values relative to the comparison algorithms to varying degrees.

关键词： artificial intelligence data privacy decision making internet of things

来源：评论

学校读者我要写书评

暂无评论

MTSC-Net:A Semi-Supervised Counting Network for Estimating the Number of Slash pine New Shoots

引用

植物表型组学（英文） 2024年第4期6卷 953-966页

作者： Zhaoxu Zhang Yanjie Li Yue Cao Yu Wang Xuchao Guo Xia Hao College of Information Science and Engineering Shandong Agricultural UniversityTaian271018Shandong ProvinceChina Research Institute of Subtropical Forestry Chinese Academy of ForestryHangzhou 311400Zhejiang ProvinceChina School of Big Data Taishan College of Science and TechnologyTaian271034Shandong ProvinceChina

The new shoot density of slash pine serves as a vital indicator for assessing its growth and photosynthetic capacity,while the number of new shoots offers an intuitive reflection of this *** deep learning methods becoming increasingly popular,automated counting of new shoots has greatly improved in recent years but is still limited by tedious and expensive data collection and *** resolve these issues,this paper proposes a semi-supervised counting network(MTSC-Net)for estimating the number of slash pine new ***,based on the mean-teacher framework,we introduce the improved VGG19 to extract multiscale new shoot ***,to connect local new shoot feature information with global channel features,attention feature fusion module is introduced to achieve effective feature ***,the new shoot density map and density probability distribution are processed in a fine-grained manner through multiscale dilated convolution of the regression head and classification *** addition,a masked image modeling strategy is introduced to encourage the contextual understanding of global new shoot features and improve the counting *** experimental results show that MTSC-Net outperforms other semi-supervised counting models with labeled percentages ranging from 5％to 50％.When the labeled percentage is 5％,the mean absolute error and root mean square error are 17.71 and 25.49,*** findings demonstrate that our work can be used as an efficient semi-supervised counting method to provide automated support for tree breeding and genetic utilization.

关键词： network counting estimating mtsc-net number pine semi-supervised shoots slash

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-assisted Multi-objective Grey Wolf Optimizer for Empty-heavy Train Allocation Considering Coordinated Line Utilization Balance

引用

Journal of Bionic Engineering 2025年第1期22卷 383-397页

作者： Zhigang Du Shaoquan Ni Jeng-Shyang Pan Shuchuan Chu School of Transportation and Logistics Southwest Jiaotong UniversityChengdu610031China School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China National and Local Joint Engineering Lab for Integrated Transportation Intelligence Chengdu610031China National Engineering Lab of Comprehensive Transportation Big Data Application Technology Chengdu610031China

This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer(SMOGWO)as a novel methodology for addressing the complex problem of empty-heavy train allocation,with a focus on line utilization *** integrating surrogate models to approximate the objective functions,SMOGWO significantly improves the efficiency and accuracy of the optimization *** effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite,where SMOGWO achieves a superiority rate of 76.67%compared to other leading multi-objective ***,the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation,which validates its ability to balance line capacity,minimize transportation costs,and optimize the technical combination of heavy *** research highlights SMOGWO's potential as a robust solution for optimization challenges in railway transportation,offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.

关键词： Surrogate-assisted model Grey wolf optimizer Multi-objective optimization Empty-heavy train allocation

来源：评论

学校读者我要写书评

暂无评论

FCIGAN: A Three-dimensional Ink Rendering Brushwork Based on Generative Adversarial Network

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1348-1358页

作者： Wang, Qinghua Lin, Wenru Lan, Wei Huang, Jingwei Chen, Yang Long, Xinling Zheng, Lujia Huang, Huilong Zhang, Fuquan School of Computer and Data Science Minjiang University Fuzhou University Town No.200 Xiyuangong Road Fuzhou350108 China Fujian Province University Fuzhou350300 China College of Computer and Big Data Fuzhou University Fuzhou China

Three-dimensional ink rendering is a NPR (Non-Photorealistic rendering) art style, widely used in a range of fields, including gaming and ***, CycleGAN is a standard image transformation model, however, it prefers Western painting methods, resulting in less-than-ideal ink rendering effects. As a result, this investigation focuses on the characteristics of ink painting by merging attention processes with three-dimensional depth information. It emphasizes differences in ink color depth to depict the relationship between distance and three-dimensional perception of things in the picture. It also makes use of methods like line thickness and curves to show the contours and textures of things. Additionally, to make the picture as close to the real traditional Chinese ink painting as possible, we use the thickness and bending of lines to show the outline and texture of objects, and highlight the key points or depict some details in the picture by leaving blank. This method is named FCIGAN (Freehand Chinese Ink Generative Adversarial Network). We have also gathered and created a matching dataset called FCI Images to aid in the experiment’s smooth progression. In conclusion, the experimental results show that, the FCIGAN approach suggested in this research has much better performance when compared to conventional techniques and may be used more effectively in the 3D rendering field. © 2024, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

TriNet: A Synergistic Hybrid Approach for Network Traffic Anomaly Detection

TriNet: A Synergistic Hybrid Approach for Network Traffic An...

引用

2024 International Conference on Electronics and Devices, Computational science, ICEDCS 2024

作者： Chen, Zirui Zhuhai College of Science and Technology School of Data Science Zhuhai China

ISBN: (纸本)9798331527624

Network traffic anomaly detection is essential for securing digital infrastructures, yet traditional methods often fail to handle the complexity and dynamics of network data effectively. Additionally, this paper presents a hybrid model called TriNet, which consists of convolutional neural networks (CNNNs), long short-term memory (Bi-LSTM) networks, and attention mechanisms integrated into one cohesive system. This allows intricate spatiotemporal patterns in network traffic to be captured in a synergistic way. Our model employs CNNs for extracting spatial features, Bi-LSTMs for modeling temporal sequences, and Attention mechanisms for focusing on critical features, augmented by residual connections to enhance training dynamics. Based on experimental findings conducted on the KDD Cup 1999 dataset, the TriNet model has shown significant improvements in terms of accuracy, precision, recall, as well as the F1 score versus traditional machine learning models. TriNet's innovative architecture and robust performance underscore its potential as a powerful tool for network traffic anomaly detection, offering substantial improvements in network security. © 2024 IEEE.

关键词： Convolutional neural networks

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：