检索结果-内蒙古大学图书馆

Instance Retrieval Using Region of Interest Based CNN Features

Journal of New Media 2019年第2期1卷 87-99页

作者： Jingcheng Chen Zhili Zhou Zhaoqing Pan Ching-nung Yang Jiangsu Engineering Center of Network Monitoring&Department of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Department of Electrical and computer Engineer University of WinsorN9B3P4WinsorONCanada Department of Computer Science and Information Engineering National Dong Hwa University ShoufengHualien 974Taiwan

Recently, image representations derived by convolutional neural networks(CNN) have achieved promising performance for instance retrieval, and they outperformthe traditional hand-crafted image features. However, most of existing CNN-based featuresare proposed to describe the entire images, and thus they are less robust to backgroundclutter. This paper proposes a region of interest (RoI)-based deep convolutionalrepresentation for instance retrieval. It first detects the region of interests (RoIs) from animage, and then extracts a set of RoI-based CNN features from the fully-connected layerof CNN. The proposed RoI-based CNN feature describes the patterns of the detected RoIs,so that the visual matching can be implemented at image region-level to effectively identifytarget objects from cluttered backgrounds. Moreover, we test the performance of theproposed RoI-based CNN feature, when it is extracted from different convolutional layersor fully-connected layers. Also, we compare the performance of RoI-based CNN featurewith those of the state-of-the-art CNN features on two instance retrieval *** results show that the proposed RoI-based CNN feature provides superiorperformance than the state-of-the-art CNN features for in-stance retrieval.

关键词： Image retrieval instance retrieval RoI CNN convolutional layer,convolutional feature maps

来源：评论

学校读者我要写书评

暂无评论

Coverless Information Hiding Based on the Molecular Structure Images of Material

引用

computers, Materials & Continua 2018年第2期54卷 197-207页

作者： Yi Cao Zhili Zhou Xingming Sun Chongzhi Gao School of Computer and Software Nanjing University of Information Science and TechnologyNing Liu RoadNO.219Nanjing210044China Jiangsu Engineering Centre of Network Monitoring Ning Liu RoadNo.219Nanjing210044China Department of Electrical and computer Engineering University of Windsor401 Sunset AvenueWindsorONCanada N9B 3P4 School of Computer Science Guangzhou UniversityWaihuanxi RoadNo.230Guangzhou510006China

The traditional information hiding methods embed the secret information by modifying the carrier,which will inevitably leave traces of modification on the *** this way,it is hard to resist the detection of steganalysis *** address this problem,the concept of coverless information hiding was *** information hiding can effectively resist steganalysis algorithm,since it uses unmodified natural stego-carriers to represent and convey confidential ***,the state-of-the-arts method has a low hidden capacity,which makes it less *** the pixel values of different regions of the molecular structure images of material(MSIM)are usually different,this paper proposes a novel coverless information hiding method based on MSIM,which utilizes the average value of sub-image’s pixels to represent the secret information,according to the mapping between pixel value intervals and secret *** addition,we employ a pseudo-random label sequence that is used to determine the position of sub-images to improve the security of the *** the histogram of the Bag of words model(BOW)is used to determine the number of subimages in the image that convey secret ***,to improve the retrieval efficiency,we built a multi-level inverted index ***,the proposed method can also be used for other natural *** with the state-of-the-arts,experimental results and analysis manifest that our method has better performance in anti-steganalysis,security and capacity.

关键词： Coverless information hiding molecular structure images of material pixel value inverted index image retrieval bag of words model

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Trusted Electronic Records Preservation in Cloud Storage

引用

computers, Materials & Continua 2019年第1期58卷 135-151页

作者： Zhiliang Deng Yongjun Ren Yepeng Liu Xiang Yin Zixuan Shen Hye-Jin Kim School of Information and Control Nanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing210044China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science&TechnologyNanjing210044China School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China College of Information Engineering Yangzhou UniversityYangzhou225127China Business Administration Research Institute Sungshin W.UniversitySeoulKorea

Cloud storage represents the trend of intensive,scale and specialization of information technology,which has changed the technical architecture and implementation method of electronic records ***,it will provide a convenient way to generate more advanced and efficient management of the electronic data ***,in cloud storage environment,it is difficult to guarantee the trustworthiness of electronic records,which results in a series of severe challenges to electronic records *** from the definition and specification of electronic records,this paper firstly analyzes the requirements of the trustworthiness in cloud storage during their long-term preservation according to the information security theory and subdivides the trustworthiness into the authenticity,integrity,usability,and reliability of electronic records in cloud ***,this paper proposes the technology framework of preservation for trusted electronic ***,the technology of blockchain,proofs of retrievability,the open archival information system model and erasure code are adopted to protect these four security attributes,to guarantee the credibility of the electronic record.

关键词： Trusted electronic record blockchain cloud storage

来源：评论

学校读者我要写书评

暂无评论

Image Emotion Classification network Based on Multilayer Attentional Interaction,Adaptive Feature Aggregation

引用

computers, Materials & Continua 2023年第5期75卷 4273-4291页

作者： Xiaorui Zhang Chunlin Yuan Wei Sun Sunil Kumar Jha Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China Adani University AhmedabadGujaratIndia

The image emotion classification task aims to use the model to automatically predict the emotional response of people when they see the *** have shown that certain local regions are more likely to inspire an emotional response than the whole ***,existing methods perform poorly in predicting the details of emotional regions and are prone to overfitting during training due to the small size of the ***,this study proposes an image emotion classification network based on multilayer attentional interaction and adaptive feature *** perform more accurate emotional region prediction,this study designs a multilayer attentional interaction *** module calculates spatial attention maps for higher-layer semantic features and fusion features through amultilayer shuffle attention *** layer-by-layer up-sampling and gating operations,the higher-layer features guide the lower-layer features to learn,eventually achieving sentiment region prediction at the optimal *** complement the important information lost by layer-by-layer fusion,this study not only adds an intra-layer fusion to the multilayer attention interaction module but also designs an adaptive feature aggregation *** module uses global average pooling to compress spatial information and connect channel information from all ***,the module adaptively generates a set of aggregated weights through two fully connected layers to augment the original features of each ***,the semantics and details of the different layers are aggregated through gating operations and residual connectivity to complement the lost *** reduce overfitting on small datasets,the network is pre-trained on the FI dataset,and further weight fine-tuning is performed on the small *** experimental results on the FI,Twitter I and Emotion ROI(Region of Interest)datasets show that the proposed network exceeds existing image emotion classification methods

关键词： Attentionmechanism emotional region prediction image emotion classification transfer learning

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Throughput Maximization in Cognitive Radio network with NOMA

引用

computers, Materials & Continua 2022年第1期70卷 195-212页

作者： Xiaoli He Yu Song Yu Xue Muhammad Owais Weijian Yang Xinwen Cheng School of Computer Science Sichuan University of Science and EngineeringZigong643000China Department of Network Information Management Center Sichuan University of Science and EngineeringZigong643000China School of Information Engineering South West University of Science and TechnologyMianyang621010China School of Computer and Software Nanjing University of Information Science and TechnologyJiangsu210044China Alhamd Islamic University Airport Road Quetta BalochistanPakistan

Spectrum resources are the precious and limited natural *** order to improve the utilization of spectrum resources and maximize the network throughput,this paper studies the resource allocation of the downlink cognitive radio network with non-orthogonalmultiple access(CRN-NOMA).NOMA,as the key technology of the fifth-generation communication(5G),can effectively increase the capacity of 5G *** optimization problem proposed in this paper aims to maximize the number of secondary users(SUs)accessing the system and the total throughput in the *** the constraints of total power,minimum rate,interference and SINR,CRN-NOMA throughput is maximized by allocating optimal transmission ***,for the situation of multiple sub-users,an adaptive optimization method is proposed to reduce the complexity of the optimization ***,for the optimization problem of nonlinear programming,a maximization throughput optimization algorithm based on Chebyshev and convex(MTCC)for CRN-NOMA is proposed,which converts multi-objective optimization problem into single-objective optimization problem to *** the same time,the convergence and time complexity of the algorithm are *** analysis and simulation results show that the algorithm can effectively improve the system *** terms of interference and throughput,the performance of the sub-optimal solution is better than that of orthogonal-frequency-division-multiple-access(OFDMA).This paper provides important insights for the research and application of NOMA in future communications.

关键词： Resource allocation non-orthogonal multiple access cognitive radio network throughput maximization Chebyshev convex

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Content-aware Search over Encrypted Outsourced Data in Cloud

Towards Efficient Content-aware Search over Encrypted Outsou...

引用

Annual IEEE International Conference on computer Communications

作者： Zhangjie Fu Xingming Sun Sai Ji Guowu Xie College of Computer and Software Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Department of Computer Science and Engineering University of California Riverside

ISBN: (纸本)9781467399548

With the increasing adoption of cloud computing, a growing number of users outsource their datasets into cloud. The datasets usually are encrypted before outsourcing to preserve the privacy. However, the common practice of encryption makes the effective utilization difficult, for example, search the given keywords in the encrypted datasets. Many schemes are proposed to make encrypted data searchable based on keywords. However, keyword-based search schemes ignore the semantic representation information of users retrieval, and cannot completely meet with users search intention. Therefore, how to design a content-based search scheme and make semantic search more effective and context-aware is a difficult challenge. In this paper, we proposed an innovative semantic search scheme based on the concept hierarchy and the semantic relationship between concepts in the encrypted datasets. More specifically, our scheme first indexes the documents and builds trapdoor based on the concept hierarchy. To further improve the search efficiency, we utilize a tree-based index structure to organize all the document index vectors. Our experiment results based on the real world datasets show the scheme is more efficient than previous scheme. We also study the threat model of our approach and prove it does not introduce any security risk.

关键词： Dataset outsourcing Scheme Consumers CLOUDS Clouds Semantics Context awareness Searches

来源：评论

学校读者我要写书评

暂无评论

Order tracking based on Gabor and Viterbi algorithm

Order tracking based on Gabor and Viterbi algorithm

引用

2011 International Conference on Mechatronic Science, Electric engineering and computer, MEC 2011

作者： Zhao, Xiaoping Zhao, Xiuli Wang, Yan Zheng, Yuhui Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing 210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China Hebei Software Institute Baoding 071000 China School of Electrical Engineering and Information Anhui University of Technology Maanshan China

ISBN: (纸本)9781612847221

The study proposes an improved Gabor order tracking technique based on Viterbi algorithm (V-GOT) to cope with close orders and crossing orders that cannot be effectively separated by using the original Gabor order tracking scheme. The dual function of the Gabor elementary function can effect the precision of tracked orders. In the paper, its influence on the computed Gabor expansion coefficients is investigated. For applying V-GOT in practical works, the separation and extraction of close orders components of vibration signals measured from an aircraft engine test is illustrated. © 2011 IEEE.

关键词： Viterbi algorithm

来源：评论

学校读者我要写书评

暂无评论

Kernel-based motion-blurred target tracking

Kernel-based motion-blurred target tracking

引用

7th International Symposium on Visual Computing, ISVC 2011

作者： Wu, Yi Hu, Jing Li, Feng Cheng, Erkang Yu, Jingyi Ling, Haibin Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing 210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China Center for Information Science and Technology Computer and Information Science Department Temple University Philadelphia PA United States Department of Computer and Information Sciences University of Delaware Newark DE 19716 United States Network Center Nanjing University of Information Science and Technology Nanjing 210044 China

Motion blurs are pervasive in real captured video data, especially for hand-held cameras and smartphone cameras because of their low frame rate and material quality. This paper presents a novel Kernel-based motion-Blurred target Tracking (KBT) approach to accurately locate objects in motion blurred video sequence, without explicitly performing deblurring. To model the underlying motion blurs, we first augment the target model by synthesizing a set of blurred templates from the target with different blur directions and strengths. These templates are then represented by color histograms regularized by an isotropic kernel. To locate the optimal position for each template, we choose to use the mean shift method for iterative optimization. Finally, the optimal region with maximum similarity to its corresponding template is considered as the target. To demonstrate the effectiveness and efficiency of our method, we collect several video sequences with severe motion blurs and compare KBT with other traditional trackers. Experimental results show that our KBT method can robustly and reliably track strong motion blurred targets. © 2011 Springer-Verlag.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A blockchain-based computation offloading method for edge computing in 5G networks

A blockchain-based computation offloading method for edge co...

引用

作者： Xu, Xiaolong Chen, Yi Zhang, Xuyun Liu, Qingxiang Liu, Xihua Qi, Lianyong School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Electrical and Computer Engineering University of Auckland Auckland New Zealand School of Information Science and Engineering Qufu Normal University Qufu China

Edge computing (EC) emerges as a novel computing paradigm to offload computing tasks from user equipments (UEs) to edge notes (ENs) in fifth-generation networks, which definitely breaks the resource limitation of UEs to a certain degree. However, it is troublesome to guarantee the overall operating performance of ENs due to the uneven distributed resource demands of UEs, the resulting transmission delay and the data loss for computation offloading between the covered EN and the deployed destination EN. In view of this challenge, a blockchain-based computation offloading method, named BCO, is proposed in this paper. Technically, since blockchain is a promising technique for the decentralized system, a blockchain-based EC framework is designed to degrade the data loss possibility by integrating blockchain and EC. Then, the nondominated sorting genetic algorithm, the third version (NSGA-III), is leveraged to acquire the balanced offloading strategies. Furthermore, by taking advantage of Simple Additive Weighting and Multiple Criteria Decision Making, the optimal offloading strategy is identified. Finally, systematic experiments and analyses on the comparative experiment are conducted to verify the efficiency of our proposed method BCO. © 2019 John Wiley & Sons, Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A RFID data-cleaning algorithm based on communication information among RFID readers

引用

International Journal of u- and e- Service, Science and Technology 2015年第1期8卷 155-164页

作者： Gu, Yunhua Gao, Bao Wang, Jin Yin, Mingshu Zhang, Junyong Jiangsu Engineering Center of Network Monitoring School of Computer and Software Nanjing University of Information Science and Technology Nanjing China

For the insufficient of existing algorithms of redundant-reader elimination, the paper proposes a data-cleaning algorithm based on communication information among readers. This algorithm is no longer dependent on the tag to send information between the RFID readers, but to transmit information directly through communication information among the readers to determine which reader the tag belongs to and whether the reader is redundant or not. This paper does a lot of experiments to verify the effectiveness of the algorithm. © 2015 SERSC.

关键词： Cleaning

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：