检索结果-南通市图书馆

Computational Visual Media 2021年第2期7卷 217-227页

作者： Peng Liu Huiyuan Fu Huadong Ma Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and TelecommunicationsBeijing 100876China

Deep convolutional neural networks(DCNNs)have been widely deployed in real-world scenarios.However,DCNNs are easily tricked by adversarial examples,which present challenges for critical applications,such as vehicle classification.To address this problem,we propose a novel end-to-end convolutional network for joint detection and removal of adversarial perturbations by denoising(DDAP).It gets rid of adversarial perturbations using the DDAP denoiser based on adversarial examples discovered by the DDAP detector.The proposed method can be regarded as a pre-processing step—it does not require modifying the structure of the vehicle classification model and hardly affects the classification results on clean images.We consider four kinds of adversarial attack(FGSM,BIM,DeepFool,PGD)to verify DDAP’s capabilities when trained on BIT-Vehicle and other public datasets.It provides better defense than other state-of-the-art defensive methods.

关键词： adversarial defense adversarial detection vehicle classification deep learning

维普期刊数据库

Few-shot node classification via local adaptive discriminant structure learning

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第2期17卷 135-143页

作者： Zhe XUE Junping DU Xin XU Xiangbin LIU Junfu WANG Feifei KOU beijing key laboratory of intelligent Telecommunication software and multimedia School of Computer ScienceBeijing University of Posts and TelecommunicationsBeijing 100876China

Node classification has a wide range of application scenarios such as citation analysis and social network analysis.In many real-world attributed networks,a large portion of classes only contain limited labeled nodes.Most of the existing node classification methods cannot be used for few-shot node classification.To train the model effectively and improve the robustness and reliability of the model with scarce labeled samples,in this paper,we propose a local adaptive discriminant structure learning(LADSL)method for few-shot node classification.LADSL aims to properly represent the nodes in the attributed graphs and learn a metric space with a strong discriminating power by reducing the intra-class variations and enlargingginter-classdifferences.Extensiveexperiments conducted on various attributed networks datasets demonstrate that LADSL is superior to the other methods on few-shot node classification task.

关键词： few-shot learning node classification graph neural network adaptive structure learning attention strategy

Graph-ranking collective Chinese entity linking algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2020年第2期14卷 291-303页

作者： Tao XIE Bin WU Bingjing JIA Bai WANG Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and TelecommunicationsBeijing 100876China

Entity linking(EL)systems aim to link entity mentions in the document to their corresponding entity records in a reference knowledge base.Existing EL approaches usually ignore the semantic correlation between the mentions in the text,and are limited to the scale of the local knowledge base.In this paper,we propose a novel graphranking collective Chinese entity linking(GRCCEL)algorithm,which can take advantage of both the structured relationship between entities in the local knowledge base and the additional background information offered by external knowledge sources.By improved weighted word2vec textual similarity and improved PageRank algorithm,more semantic information and structural information can be captured in the document.With an incremental evidence mining process,more powerful discrimination capability for similar entities can be obtained.We evaluate the performance of our algorithm on some open domain corpus.Experimental results show the effectiveness of our method in Chinese entity linking task and demonstrate the superiority of our method over state-of-the-art methods.

关键词： collective entity linking knowledge mapping word embedding entity correlation graph PageRank

A Cluster-Based Opportunistic Multicast in Multi-hop Wireless Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2015年第1期24卷 170-175页

作者： ZHANG Haiyang Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications

Multicast has become increasingly important in multi-hop wireless networks for such applications which deliver shared media and data to multiple receivers.However, the existing multicast protocols for wireless network have large control overhead, and cannot adequately take the advantage of broadcast communication mode in multicast structure for sharing the forwarding path. This paper proposes a Cluster-based opportunistic multicast(COM) algorithm, which constructs multicast tree structure based on clusters by utilizing a stability greedy algorithm to achieve the minimum total Cluster-based expected transmission count(CETX). In this multicast tree structure, the edge is created between the kernel sets respectively belonging to two clusters for improving the forwarding efficiency and the stability of this structure. In the process of data distribution, our multi-layer solution combines multicast and opportunistic routing to improve the efficiency of transmission. Simulation results show that COM scheme can achieve the less total number of sending packets, and higher stability than other topology-based solutions and opportunistic multicast.

关键词： Multi-hop wireless network Multicast Opportunistic routing Cluster.

Multimodal Interactive Network for Sequential Recommendation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2023年第4期38卷 911-926页

作者：韩滕跃王鹏飞牛少彰 beijing key laboratory of intelligent Telecommunication software and multimedia Beijing University of Posts and TelecommunicationsBeijing 100876China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China

Building an effective sequential recommendation system is still a challenging task due to limited interactions among users and items.Recent work has shown the effectiveness of incorporating textual or visual information into sequential recommendation to alleviate the data sparse problem.The data sparse problem now is attracting a lot of attention in both industry and academic community.However,considering interactions among modalities on a sequential scenario is an interesting yet challenging task because of multimodal heterogeneity.In this paper,we introduce a novel recommendation approach of considering both textual and visual information,namely Multimodal Interactive Network(MIN).The advantage of MIN lies in designing a learning framework to leverage the interactions among modalities from both the item level and the sequence level for building an efficient system.Firstly,an item-wise interactive layer based on the encoder-decoder mechanism is utilized to model the item-level interactions among modalities to select the informative information.Secondly,a sequence interactive layer based on the attention strategy is designed to capture the sequence-level preference of each modality.MIN seamlessly incorporates interactions among modalities from both the item level and the sequence level for sequential recommendation.It is the first time that interactions in each modality have been explicitly discussed and utilized in sequential recommenders.Experimental results on four real-world datasets show that our approach can significantly outperform all the baselines in sequential recommendation task.

关键词： multi-modality interactive network sequential recommendation

Hybrid Semantic Concept Temporal Pooling for Large-Scale Video Event Analysis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2017年第6期26卷 1125-1131页

作者： LIU Wu MA Huadong beijing key laboratory of intelligent Telecommunication software and multimedia Beijing University of Posts and Telecommunications

To solve the task of detecting and recounting events in videos with limited training examples, we propose a novel two-stage hybrid concept temporal pooling approach that is aware of potential concept drift in the video stream. We initially partition videos into temporal pyramids consisting of keyframes. Semantic concepts in keyframes is detected, which enables us to derive aggregated detection scores for each temporal pyramid using average-pooling and ultimately for the entire video via max-pooling. Owing to this refined hybrid pooling, our method yields more discriminative semantic representations with respect to the event query. We also develop an effective filtering strategy to cope with noisy concept detectors to robustify the textual description generation in recounting. Experiments on the large scale TRECVID MEDTest dataset demonstrate our method improves the accuracies over state-of-the-art methods, both for event detection and recounting.

关键词： Event detection Event recounting Semantic representation Hybrid temporal pooling Concept filtering

Minimizing Resource Cost for Camera Stream Scheduling in Video Data Center

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2017年第3期32卷 555-570页

作者： Yi-Hong Gao Hua-Dong Ma Wu Liu Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing 100876 China

Video surveillance service, which receives live streams from IP cameras and forwards the streams to end users, has become one of the most popular services of video data center. The video data center focuses on minimizing the resource cost during resource provisioning for the service. However, little of the previous work comprehensively considers the bandwidth cost optimization of both upload and forwarding streams, and the capacity of the media server. In this paper, we propose an efficient resource scheduling approach for online multi-camera video forwarding, which tries to optimize the resource sharing of media servers and the networks together. Firstly, we not only provide a fine-grained resource usage model for media servers, but also evaluate the bandwidth cost of both upload and forwarding streams. Without loss of generality, we utilize two resource pricing models with different resource cost functions to evaluate the resource cost： the linear cost function and the non-linear cost functions. Then, we formulate the cost minimization problem as a constrained integer programming problem. For the linear resource cost function, the drift-plus-penalty optimization method is exploited in our approach. For non-linear resource cost functions, the approach employs a heuristic method to reduce both media server cost and bandwidth cost. The experimental results demonstrate that our approach obviously reduces the total resource costs on both media servers and networks simultaneously.

关键词： video data center resource scheduling video surveillance as a service multi-camera networking

Robust load-balanced backbone-based multicast routing in mobile opportunistic networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第4期17卷 109-125页

作者： Di ZHANG Dong ZHAO uadong MA Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and TelecommunicationsBeijing 100876China

Mobile opportunistic network(MON)is an efficient way of communication when there is no persistent connection between nodes.Multicast in MONs can be used to efficiently deliver messages to multiple destination nodes.However,because multiple destination nodes are involved,multicast routing is more complex than unicast and brings a higher communication cost.Backbone-based routing can effectively reduce the network overhead and the complexity of routing scheme.However,the load of backbone nodes is larger than that of regular nodes.If the backbone node’s buffer is exhausted,it will have a significant impact on the performance of the routing scheme.Load balancing can improve the ability of backbone to deal with the change of network load,and backbone maintenance algorithm can provide backbone robustness.In this paper,we propose a robust load-balanced backbone-based multicast routing scheme in MONs.In the backbone construction algorithm,we transform the problem of backbone construction into a multi-objective optimization problem,and propose a multi-objective evolutionary algorithmbased backbone construction algorithm,namely LBMBCMOEA algorithm.In addition,in order to increase the robustness of the backbone-based routing scheme,we propose a localized multicast backbone maintenance algorithm(MBMA)to deal with the buffer exhaustion of backbone nodes.When a backbone node’s residual buffer is insufficient,MBMA algorithm selects other nodes to replace the backbone node.The results on extensive simulations show that when considering the node buffer size constraints,compared with previous backbone-based multicast routing schemes,our proposed algorithm has better performance,and when the node’s residual buffer is insufficient,MBMA algorithm can significantly improve the performance of the backbone-based multicast routing scheme.

关键词： mobile opportunistic network multicast multiobjective optimization backbone construction backbone maintenance

An Adaptive User Preferences Elicitation Scheme for Location Recommendation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2016年第5期25卷 943-949页

作者： WANG Fan MENG Xiangwu ZHANG Yujie Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia School of Computer Science Beijing University of Posts and Telecommunications

User preferences elicitation is a key issue of location recommendation. This paper proposes an adaptive user preferences elicitation scheme based on Collaborative filtering(CF) algorithm for location recommendation. In this scheme, user preferences are divided into user static preferences and user dynamic preferences. The former is estimated based on location category information and historical ratings. Meanwhile, the latter is evaluated based on geographical information and two-dimensional cloud model. The advantage of this method is that it not only considers the diversity of user preferences, but also can alleviate the data sparsity problem. In order to predict user preferences of new locations more precisely, the scheme integrates the similarity of user static preferences, user dynamic preferences and social ties into CF algorithm. Furthermore, the scheme is parallelized on the Hadoop platform for significant improvement in efficiency. Experimental results on Yelp dataset demonstrate the performance gains of the scheme.

关键词： Location recommendation Adaptive User static preferences User dynamic preferences

A Novel Hotfix Scheme for System Vulnerability Based on the Android Application Layer

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2019年第2期28卷 408-415页

作者： ZHANG Wen SU Ningning NIU Shaozhang LI Hui HUANG Ruqiang beijing key laboratory of intelligent Telecommunication software and multimedia Beijing University of Posts and Telecommunications School of Cyberspace Security Beijing University of Posts and Telecommunications

At present, fixing Android system vulnerabilities relies on official Android support and various equipment manufacturers, and it is mainly implemented by system upgrades. This situation causes many problems, such as high costs and delayed fixing of vulnerabilities. This study is performed to design a novel fixing policy construction model targeting Android system vulnerabilities, which can be used for vulnerability feature quantification and fixing policy customization. On this basis, a novel security vulnerability solution called DroidHFix is proposed and implemented. This solution constructs security policies and loads security policy files during the risky application startup. The system helps to fix Android system vulnerabilities dynamically and defend against attacks on the risky application depending on system vulnerability exploitation. Experimental results show that DroidHFix fixes the Android system vulnerabilities effectively, with good performance and compatibility.

关键词： Hotfix Vulnerability fixing Construction model