检索结果-内蒙古大学图书馆

IEEE Workshop on Multimedia Signal Processing

作者： Yizhao Wang Jiaqi Zhang Songlin Sun School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education China Engineering Research Center of Blockchain and Network Convergence Technology Ministry of Education China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China

In this paper, we propose a simplified cubic polynomial R-D model with corresponding rate control methods for Versatile Video Coding (VVC) intra frame coding. First, we explore the rate-distortion (R-D) characteristics of VVC intra coding. By comparing several potential R-D modeling approaches, a new intra coding R-D model has been proposed based on the simplified cubic polynomial function. Subsequently, we derive the corresponding $R-\lambda$ model and introduce a complexity measurement to improve the performance of intra frame rate control. Furthermore, we propose a Coding Tree Unit (CTU)-level rate control method based on the newly proposed R-D model and further develop a pre-compression-based approach on this basis. Experimental results show that the proposed method can achieve 1.87% and 0.55% bit rate reduction for All-Intra (AI) and Random-Access (RA) configurations over the original rate control in VVC Test Model (VTM), while the computational complexity increment is negligible. Meanwhile, the enhanced bit rate accuracy from rate control has been observed in the proposed methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UCL-AST: Active Self-Training with Uncertainty-Aware Clouded Logits for Few-Shot Text Classification

UCL-AST: Active Self-Training with Uncertainty-Aware Clouded...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Yi Xu Jie Hu Zhiqiao Gao Jinpeng Chen School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China China Telecom Corporation Limited Research Institute Beijing China

Although the recent advances in pre-training language models have achieved great success and migrated annotation bottleneck for many tasks, the task-specific fine-tuning for text classification still requires thousands of labeled samples or even more. When few human annotations are available, active self-training is one of the efficient approaches for reducing human annotation costs which integrates pseudo labels of self-training into the procedure of active learning. The traditional active self-training approaches mix manual labels and pseudo labels indistinguishably without considering the impact of active learning and self-training on each other. There are two problems for active self-training in few-shot text classification: (1) The noise in a large number of pseudo-labels may mislead the model training. (2) The confusing samples in overlap boundaries between classes are especially difficult to identify correctly with a few labels. To solve these problems, we propose UCL-AST, an active self-training framework that boosts the performance of the active teacher model to provide superior pseudo labels for the self-training student model and facilitates the active teacher model to learn more clear class boundaries with uncertainty-aware clouded logits in few-shot. The extensive experiments and visualization analysis have demonstrated the effectiveness of the proposed framework on four datasets compared with state-of-the-art methods.

关键词： Training Visualization Uncertainty Costs Annotations Text categorization Measurement uncertainty

来源：评论

学校读者我要写书评

暂无评论

From Passive to Active: Near-optimal DNS-based Data Exfiltration Defense Method Based on Sticky Mechanism

From Passive to Active: Near-optimal DNS-based Data Exfiltra...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Jiawen Diao Binxing Fang Xiang Cui Zhongru Wang Tian Wang Shouyou Song Key Laboratory of Trustworthy Distributed Computing and Service (Beijing University of Posts and Telecommunications) Ministry of Education Beijing China Zhongguancun Laboratory Beijing China Chinese Academy of Cyberspace Studies Beijing China Beijing DigApis Technology Co. Ltd Beijing China

DNS-based data exfiltration has become increasingly popular among advanced persistent threat (APT) attackers owing to the ubiquity and penetrability of the DNS protocol. AI-powered methods solve the defect that attackers can easily bypass because of the fixed threshold and weight in rule matching while still suffer from several issues. Such as the lack of malware samples for training, the amplified impact of even low FPR present enormous obstacles to applying the model in real-world *** present a method to generate malicious traffic covering an extensive sample space based on Tactics, Techniques, and Procedures (TTPs). We then propose a sticky mechanism, which transforms certain decision-making into dynamic human-computer interaction decision-making, to verify the suspicious hosts recognized by the AI model. The experimental results demonstrate the superiority of our model by identifying eight kinds of real attacks precisely. The good performance on real-world traffic shows our method is a solid foothold for applying AI-powered detection to practical applications.

关键词： Training Human computer interaction Data privacy Protocols Decision making Transforms Solids

来源：评论

学校读者我要写书评

暂无评论

Transformer-F: A Transformer network with effective methods for learning universal sentence representation

arXiv

引用

arXiv 2021年

作者： Shi, Yu School of Software Engineering Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China

The Transformer model is widely used in natural language processing for sentence representation. However, the previous Transformer-based models focus on function words that have limited meaning in most cases and could merely extract high-level semantic abstraction features. In this paper, two approaches are introduced to improve the performance of Transformers. We calculated the attention score by multiplying the part-of-speech weight vector with the correlation coefficient, which helps extract the words with more practical meaning. The weight vector is obtained by the input text sequence based on the importance of the part-of-speech. Furthermore, we fuse the features of each layer to make the sentence representation results more comprehensive and accurate. In experiments, we demonstrate the effectiveness of our model Transformer-F on three standard text classification datasets. Experimental results show that our proposed model significantly boosts the performance of text classification as compared to the baseline model. Specifically, we obtain a 5.28% relative improvement over the vanilla Transformer on the simple tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

A microservice based generic consensus engine for BaaS

A microservice based generic consensus engine for BaaS

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Huiyang Li Xu Zhang Jing Li Dongbin Wang Beijing University of Posts and Telecommunications Beijing China School of Cyber Security National Engineering Laboratory for Mobile Network Security Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing Tongbang Zhuoyi Technology Co. Ltd

ISBN: (纸本)9781728119496

Blockchain-as-a-service (BaaS) has gradually serve as an infrastructure, providing underlying blockchain services for the rapid deployment and transaction on-chain of large-scale enterprise application scenarios. By hosting different blockchains in its underlying structure layers, BaaS platform satisfies the requirements of consensus algorithms in different scenarios, and still uses its own consensus algorithms in different blockchains, which has limited scalability and is difficult to satisfy the requirements of future applications. To deal with such problems, MGCE, a microservice based generic consensus engine for BaaS is proposed in this paper. It is a functional framework based on microservices architecture which can load the appropriate consensus algorithm and perform the consensus process of transactions for blockchain nodes according the different scenarios. The engine is composed of Consensus Node Group, Consensus Management and four functional modules, namely Consensus Network, Transactions Pool, Consensus Protocol and Consensus Outcome. For microservice purpose, each functional module is deployed into a independently project, running in its own process, which is easy to modify and test, and interacts with other modules through the http APIs to complete the consensus process together. To test the function and performance of this engine, three common consensus algorithms have been implemented including Raft, BFT-SMART and PoW. Through experiments, it is proved that this engine could realize the loading and use of different consensus algorithms. Through the performance comparison between using the engine and with the direct use of each consensus algorithm, the results show that the overhead introducing the engine is acceptable. Through the operation result of three algorithms in different projects, the design of engine architecture could satisfy the microservice objective.

关键词： Costs Scalability Loading Microservice architectures Consensus algorithm Consensus protocol Engines

来源：评论

学校读者我要写书评

暂无评论

Uplink channel estimation and signal extraction under malicious attack in massive MIMO system

arXiv

引用

arXiv 2020年

作者： Zheng, Xiaofeng Cao, Ruohan Lu, Yueming Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing100876 China

This paper investigates correlative attack for the massive MIMO uplink. Malicious users (MUs) send jamming data sequences that are correlative to the data sequences of legitimate users (LUs) to a base station (BS). We consider the problem of channel estimation and signal extraction in the presence of correlative attacks. The right singular matrix of received signal at the BS is a function of the correlation between the legitimate and jamming data in large-scale antenna regime. As a result, correlative attacks degrade the performance of traditional channel estimation methods that base on eigenvalue decomposition (EVD) of the received signals. Then, we propose a signal extraction and channel estimation method to combat against correlative attacks. More precisely, geometric arguments, such as convex hull of extracted signals, are utilized for providing signal extraction and channel estimation criteria. For the optimization of these criteria, we develop an extractor which is able to capture convex hull of desired signals from noisy signals. Based on the proposed extractor, we formulate two optimization problems, whose global minima are solved to perform signal extraction and channel estimation. Experimental results show that when correlation coefficient is 0.6, the proposed method outperforms the EVD-based method more than 5 dB in the sense of normalized mean square error (NMSE). Copyright © 2020, The Authors. All rights reserved.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Mandari: Multi-Modal Temporal Knowledge Graph-aware Sub-graph Embedding for Next-POI Recommendation

Mandari: Multi-Modal Temporal Knowledge Graph-aware Sub-grap...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoqian Liu Xiuyun Li Yuan Cao Fan Zhang Xiongnan Jin Jinpeng Chen School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China The Technology Innovation Center of Cultural Tourism Big Data of Hebei Province Chengde China Hebei Normal University for Nationalities Chengde China Knowledge Discovery and Data Mining Research Center Zhejiang Lab Hangzhou China

Next-POI recommendation aims to explore from user check-in sequence to predict the next possible location to be visited. Existing methods are often difficult to model the implicit association of multi-modal data with user choices. Moreover, traditional methods struggle to fully explore the variation of user preferences at variable time intervals. To tackle these limitations, we propose a Multi-Modal Temporal Knowledge Graph-aware Sub-graph Embedding approach (Mandari). We first construct a novel Multi-Modal Temporal Knowledge Graph. Based on the proposed knowledge graph, we integrate multi-modal information and leverage the graph attention network to calculate sub-graph prediction probability. Next, we implement a temporal knowledge mining method to model the segmentation and periodicity of user check-in and obtain temporal prediction probability. Finally, we fuse temporal prediction probability with the previous sub-graph prediction probability to obtain the final result. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved CTU-level Rate Control Algorithm Based on Temporal Domain Motion Intensity

An Improved CTU-level Rate Control Algorithm Based on Tempor...

引用

International Symposium on Communications and Information Technologies (ISCIT)

作者： Shaokang Wang Songlin Sun Jiaqi Zou Ruotong Wu Zhilei Ling Xingtong Liu School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education China Engineering Research Center of Blockchain and Network Convergence Technology Ministry of Education China Department of Electronics and Electrical Engineering University College London London UK Business School Beijing Normal University Beijing China

Rate control (RC) plays a vital role in Versatile Video Coding (VVC) and video transmission. However, the RC algorithm in VVC remains the problem that the process of updating model parameters only considers the impact of the current encoding block content, without considering the similarity and reference value between different Coding Tree Units (CTUs) in the temporal domain. As a result, the coding performance is not optimal. To address this problem and further optimize the RC of VVC, this paper proposes an improved CTU-level rate control model parameter updating algorithm based on temporal domain motion intensity and we integrate this algorithm into VTM 1S.0. Experiments show that the proposed algorithm achieves better coding performance than anchor with 0.74% and 1.03% BD-rate saving under the Low Delay B (LDB) and Random Access (RA) configurations, respectively, while obtaining smaller bitrate error under common test conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity

arXiv

引用

arXiv 2022年

作者： Li, Jiahao Wang, Quan Mao, Zhendong Guo, Junbo Yang, Yanyan Zhang, Yongdong University of Science and Technology of China Hefei China MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China People's Daily Online Co. Beijing China People's Public Security University of China Beijing China

Chinese spelling check (CSC) is a fundamental NLP task that detects and corrects spelling errors in Chinese texts. As most of these spelling errors are caused by phonetic similarity, effectively modeling the pronunciation of Chinese characters is a key factor for CSC. In this paper, we consider introducing an auxiliary task of Chinese pronunciation prediction (CPP) to improve CSC, and, for the first time, systematically discuss the adaptivity and granularity of this auxiliary task. We propose SCOPE which builds on top of a shared encoder two parallel decoders, one for the primary CSC task and the other for a fine-grained auxiliary CPP task, with a novel adaptive weighting scheme to balance the two tasks. In addition, we design a delicate iterative correction strategy for further improvements during inference. Empirical evaluation shows that SCOPE achieves new state-of-the-art on three CSC benchmarks, demonstrating the effectiveness and superiority of the auxiliary CPP task. Comprehensive ablation studies further verify the positive effects of adaptivity and granularity of the task. Code and data used in this paper are publicly available at https://***/jiahaozhenbang/SCOPE. Copyright © 2022, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A High-performance Web Attack Detection Method based on CNN-GRU Model

A High-performance Web Attack Detection Method based on CNN-...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Qiangqiang Niu Xiaoyong Li Ministry of Education Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Beijing China

ISBN: (数字)9781728143903

ISBN: (纸本)9781728143910

WEB attack detection is an important part of WEB security. This paper proposes a web attack detection method based on Convolutional Neural Network (CNN) combined with Gated Recurrent Unit (GRU). In order to improve the detection performance, we extract eight statistical features with good classification effect to augment the original data. In addition, we also pre-trained the word embedding matrix using the word2Vec model, then obtained the input of the CNN-GRU model and classified the final results. The experimental results show that the accuracy of the method in the HTTP CSIC 2010 dataset is 99.00%, the recall rate is 97.74%, the F1 value is 98.77% and the precision is 99.82%. Compared with traditional machine learning methods, this method proposed in this paper has better performance.

关键词：

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：