检索结果-内蒙古大学图书馆

DSD-MatchingNet:Deformable sparse-to-dense feature matching for learning accurate correspondences

Virtual Reality & Intelligent Hardware 2022年第5期4卷 432-443页

作者： Yicheng ZHAO Han ZHANG Ping LU Ping LI Enhua WU Bin SHENG Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China ZTE Corporation Shenzhen 518057China State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen 518057China Department of Computing The Hong Kong Polytechnic UniversityHong Kong 999077China School of Design The Hong Kong Polytechnic UniversityHong Kong 999077China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China Faculty of Science and Technology University of MacaoMacao 999078China

Background Exploring correspondences across multiview images is the basis of various computer vision ***,most existing methods have limited accuracy under challenging *** To learn more robust and accurate correspondences,we propose DSD-MatchingNet for local feature matching in this ***,we develop a deformable feature extraction module to obtain multilevel feature maps,which harvest contextual information from dynamic receptive *** dynamic receptive fields provided by the deformable convolution network ensure that our method obtains dense and robust ***,we utilize sparse-to-dense matching with symmetry of correspondence to implement accurate pixel-level matching,which enables our method to produce more accurate *** Experiments show that our proposed DSD-MatchingNet achieves a better performance on the image matching benchmark,as well as on the visual localization ***,our method achieved 91.3%mean matching accuracy on the HPatches dataset and 99.3%visual localization recalls on the Aachen Day-Night dataset.

关键词： Image matching Deformable convolution network Sparse-to-dense matching

来源：评论

学校读者我要写书评

暂无评论

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

Generalizable Decision Boundaries: Dualistic Meta-Learning f...

引用

International Conference on computer Vision (ICCV)

作者： Xiran Wang Jian Zhang Lei Qi Yinghuan Shi Nanjing University State Key Laboratory for Novel Software Technology and National Institute of Healthcare Data Science Nanjing University China Southeast University School of Computer Science and Engineering Southeast University China

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario where the source and target domains have different classes. To overcome this deficiency, open set domain generalization (OSDG) then emerges as a more practical setting to recognize unseen classes in unseen domains. An intuitive approach is to use multiple one-vs-all classifiers to define decision boundaries for each class and reject the outliers as unknown. However, the significant class imbalance between positive and negative samples often causes the boundaries biased towards positive ones, resulting in misclassification for known samples in the unseen target domain. In this paper, we propose a novel meta-learning-based framework called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers gradient matching towards inter-domain and inter-class splits simultaneously to find a generalizable boundary balanced for all tasks. Experimental results demonstrate that MEDIC not only outperforms previous methods in open set scenarios, but also maintains competitive close set generalization ability at the same time. Our code is available at https://***/zzwdx/MEDIC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method of Multidimensional software Aging Prediction Based on Ensemble Learning: A Case of Android Os

SSRN

引用

SSRN 2023年

作者： Nie, Yuge Chen, Yulei Jiang, Yujia Wu, Huayao Yin, Beibei Cai, Kai-Yuan Beihang University School of Automation Science and Electrical Engineering Beijing100083 China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing210023 China

Context: software aging refers to the phenomenon of performance degradation, increasing failure rate, or system crash due to resource consumption and error accumulation in software systems running for a long time. Precisely predicting software aging is crucial for enabling proactive measures before the situation substantially deteriorates. Previous machine learning (ML) methods for predicting aging predominantly rely on a single ML modeland a single labeling metric to attain their objectives. Furthermore, a common limitation shared by these methods is that training and prediction data stem from identical operational profiles. This could pose challenges for these models in delivering the desired performance when confronted with diverse user scenarios. Objective: In this paper, we aim to find a method that can both consistently and precisely predict aging trends across a wide range of application scenarios. Method: We propose a method of multidimensional software aging prediction based on ensemble learning called MSAP. Unlike the previous full-process single-threaded approaches, in the framework of MSAP, five dimensions including datasets, labeling metrics, labeling thresholds, algorithms, and model decisions are extracted and diversified to protest against diverse user scenarios and aging situations. Results: When subjected to identical workloads, MSAP demonstrates comparable performance to the majority of unidimensional models, albeit without significant prominence. Under different workloads, MSAP consistently outperforms unidimensional models whose performance drops dramatically in terms of precision, maintaining a notable lead while exhibiting minimal fluctuations. Conclusion: MSAP exhibits exceptional stability while concurrently upholding outstanding prediction precision across a spectrum of user scenarios. Therefore, it has better generalization characteristics and application prospects. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Semantic Conflict Prevention in Real-Time Collaborative Programming 17th

Hybrid Semantic Conflict Prevention in Real-Time Collaborati...

引用

17th EAI International Conference on Collaborative Computing: Networking, Applications, and Worksharing, CollaborateCom 2021

作者： Xu, Wenhua Zhang, Yiteng Chiu, Brian Chen, Dong Jiang, Jinfeng Du, Bowen Fan, Hongfei School of Software Engineering Tongji University Shanghai China SAP Labs China Shanghai China Department of Computer Science University of Warwick Coventry United Kingdom

ISBN: (纸本)9783030926373

Real-time collaborative programming allows a group of programmers to edit the same source code at the same time. To support semantic conflict prevention in real-time collaboration, a dependency-based automatic locking (DAL) approach was proposed in prior work. The DAL mechanism automatically detects programming elements with dependency relationships, and prohibits concurrent editing on the inter-dependent source code regions by locking. However, the prior DAL scheme is too restrictive, which leads to an unnecessarily large locking scope and seriously impacts the concurrent work. To address this issue, we propose a novel hybrid semantic conflict prevention (HSCP) scheme, to achieve a better balance between conflict prevention and concurrent work. The scheme enforces locking on the working and strongly-depended regions, while applies awareness highlight on weakly-depended regions. The depth of locking scope can be customized by each programmer in a fine-grained manner. A three-level awareness mechanism has been designed for programmers to intuitively distinguish working, strongly-depended and weakly-depended regions. In supporting the scheme, we have devised techniques and solutions, and implemented a prototype that supports programmers to enjoy hybrid semantic conflict prevention in real-time collaborative programming over Eclipse and IntelliJ IDEA platforms. Experimental evaluations have confirmed the satisfactory performance of the scheme in complex real-world scenarios. © 2021, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A-REA: Relation-Aware Graph Convolutional Network Entity Alignment Via a Differential Adjacency Matrix

A-REA: Relation-Aware Graph Convolutional Network Entity Ali...

引用

Image Processing, Electronics and computers (IPEC), Asia-Pacific Conference on

作者： Yuemei Dang Chen Qiu Feng Gao Jinguang Gu Lihua Zhang Ghazaleh Arman School of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Software College East China Jiaotong University Nanchang Jiangxi China Faculty of Information Technology and Computer Engineering Urmia University of Technology Urmia Iran

Entity Alignment is the task of seeking entities with the same semantics from distinct knowledge graphs (KGs). Researchers have recently proposed Graph Convolutional Network (GCN) based approaches to achieve this task. Most existing GCN-based methods embed all the relations into an identical value, making the underlying loss on the diversity of the relationship. Relation semantics of entities and relation structure have benefitted the entity alignment task in the monolingual scenarios. This paper proposes a Relation-Aware Graph Convolutional Network with a Differential Adjacency Matrix (A-REA), which exploits the relation-specific semantics and structural information of entities in the KGs to promote the entity representations. The experiments on DBP-15K and DWY-100K datasets, including three cross-lingual subsets and two cross-knowledge graph sub-datasets, reveal that our approach leads to advance in entity alignment task in both the cross-lingual and cross-knowledge KGs. Discriminating the relation shows the effective signal for entity alignment, especially for the schema heterogeneity of different KGs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Detection Approach of Content Aware Image Resizing

引用

computers, Materials & Continua 2020年第8期64卷 887-907页

作者： Ming Lu Shaozhang Niu Zhenguang Gao Beijing Key Lab of Intelligent Telecommunication Software and Multimedia Beijing University of Posts and TelecommunicationsBeijing100876China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China Department of Computer Science Framingham State UniversityMassachusettsMA 01772USA

Content aware image resizing(CAIR)is an excellent technology used widely for image *** can also be used to tamper with images and bring the trust crisis of image content to the *** an image is processed by CAIR,the correlation of local neighborhood pixels will be *** local binary patterns(LBP)can effectively describe the local texture,it however cannot describe the magnitude information of local neighborhood pixels and is also vulnerable to ***,to deal with the detection of CAIR,a novel forensic method based on improved local ternary patterns(ILTP)feature and gradient energy feature(GEF)is proposed in this ***,the adaptive threshold of the original local ternary patterns(LTP)operator is improved,and the ILTP operator is used to describe the change of correlation among local neighborhood pixels caused by ***,the histogram features of ILTP and the gradient energy features are extracted from the candidate image for CAIR forgery ***,the ILTP features and the gradient energy features are concatenated into the combined features,and the combined features are used to train *** support vector machine(SVM)is exploited as a classifier to be trained and tested by the above features in order to distinguish whether an image is subjected to CAIR or *** candidate images are extracted from uncompressed color image database(UCID),then the training and testing sets are *** experimental results with many test images show that the proposed method can detect CAIR tampering effectively,and that its performance is improved compared with other *** can achieve a better performance than the state-of-the-art approaches.

关键词： Digital image forensics content aware image resizing local ternary patterns gradient energy feature

来源：评论

学校读者我要写书评

暂无评论

CMG-Net: An End-to-End Contact-based Multi-Finger Dexterous Grasping Network

CMG-Net: An End-to-End Contact-based Multi-Finger Dexterous ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Mingze Wei Yaomin Huang Zhiyuan Xu Ning Liu Zhengping Che Xinyu Zhang Chaomin Shen Feifei Feng Chun Shan Jian Tang School of Software Engineering East China Normal University China School of Computer Science East China Normal University China Midea Group China School of Electronics and Information Guangdong Polytechnic Normal University China

In this paper, we propose a novel representation for grasping using contacts between multi-finger robotic hands and objects to be manipulated. This representation significantly reduces the prediction dimensions and accelerates the learning process. We present an effective end-to-end network, CMG-Net, for grasping unknown objects in a cluttered environment by efficiently predicting multi-finger grasp poses and hand configurations from a single-shot point cloud. Moreover, we create a synthetic grasp dataset that consists of five thousand cluttered scenes, 80 object categories, and 20 million annotations. We perform a comprehensive empirical study and demonstrate the effectiveness of our grasping representation and CMG-Net. Our work significantly outperforms the state-of-the-art for three-finger robotic hands. We also demonstrate that the model trained using synthetic data perform very well for real robots.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time monocular depth estimation with adaptive receptive fields

Real-time monocular depth estimation with adaptive receptive...

引用

作者： Ji, Zhenyan Song, Xiaojun Guo, Xiaoxuan Wang, Fangshi Armendáriz-Iñigo, José Enrique School of Software Engineering Beijing Jiaotong University Beijing100044 China Department of Statistics Computer Science and Mathematics Public University of Navarre Pamplona31006 Spain

Monocular depth estimation is a popular research topic in the field of autonomous driving. Nowadays many models are leading in accuracy but performing poorly in a real-time scenario. To effectively increase the depth estimation efficiency, we propose a novel model combining a multi-scale pyramid architecture for depth estimation together with adaptive receptive fields. The pyramid architecture reduces the trainable parameters from dozens of mega to less than 10 mega. Adaptive receptive fields are more sensitive to objects at different depth/distances in images, leading to better accuracy. We have adopted stacked convolution kernels instead of raw kernels to compress the model. Thus, the model that we proposed performs well in both real-time performance and estimation accuracy. We provide a set of experiments where our model performs better in terms of Eigen split than other previously known models. Furthermore, we show that our model is also better in runtime performance in regard to the depth estimation to the rest of models but the Pyd-Net model. Finally, our model is a lightweight depth estimation model with state-of-the-art accuracy. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-media Scientific Research Achievements Query based on Ranking Learning

arXiv

引用

arXiv 2022年

作者： Wang, Benzhi Liang, Meiyu Li, Ang School of Computer Science National Pilot School of Software Engineering Beijing University of Posts and Telecommunications Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia Beijing100876 China

With the advent of the information age, the scale of data on the Internet is getting larger and larger, and it is full of text, images, videos, and other information. Different from social media data and news data, scientific research achievements information has the characteristics of many proper nouns and strong ambiguity. The traditional single-mode query method based on keywords can no longer meet the needs of scientific researchers and managers of the Ministry of science and Technology. Scientific research project information and scientific research scholar information contain a large amount of valuable scientific research achievement information. Evaluating the output capability of scientific research projects and scientific research teams can effectively assist managers in decision-making. In view of the above background, this paper expounds on the research status from four aspects: characteristic learning of scientific research results, cross-media research results query, ranking learning of scientific research results, and cross-media scientific research achievement query system. Copyright © 2022, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Robust Anonymous Authentication Scheme for Securing IoT-Enabled Healthcare Services

A Robust Anonymous Authentication Scheme for Securing IoT-En...

引用

Cyber Security in Networking Conference (CSNet)

作者： Sana Ullah Shanshan Tu Akhtar Badshah Muhammad Waqas Department of Enterprise and Technology Atlantic Technological University Galway Ireland College of Computer Science Beijing University of Technology Beijing China Department of Software Engineering Faculty of Engineering University of Malakand Dir Lower Pakistan Faculty of Engineering and Science School of Computing and Mathematical Sciences University of Greenwich U.K. School of Engineering Edith Cowan University Perth WA Australia

ISBN: (数字)9798331534103

ISBN: (纸本)9798331534110

Smart wearables and body implanted IoT devices continuously track and transmit health metrics wirelessly to a central controller, such as a personal server, enabling real-time monitoring, proactive treatment and timely assistance. However, the security of IoT-enabled healthcare systems remains a concern, particularly regarding the protection of sensitive patient data. To address the aforementioned issue and enhance security in IoT-enabled healthcare services, we propose a robust anonymous authentication scheme in this work. By leveraging lightweight cryptographic primitives including hash functions and XOR operations coupled with physical unclonable functions (PUFs) and fuzzy extractors, the proposed scheme introduces a novel authentication and key agreement mechanism for secure communication in IoT-enabled healthcare systems. The integration of PUF technology ensure the physical security of resource constrained implantable medical devices (IMDs) against various attacks including device physical capture and impersonation attacks that compromise the IoT-enabled healthcare operations. A thorough security analysis demonstrated the robustness and resilience of the proposed scheme against various active and pas-sive security attacks, thus ensure the integrity and confidentiality of sensitive healthcare data. Finally, comparative analysis of the proposed scheme with other state-of-the-art highlighted that our scheme outperformed other approaches in terms of providing security and additional features, positioning it as a comprehensive solution for authentication in IoT-enabled healthcare services.

关键词： Hash functions Medical devices Authentication Medical services Physical unclonable function Security Internet of Things Servers Wearable devices Resilience

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：