检索结果-内蒙古大学图书馆

International Conference on software engineering (ICSE)

作者： Jiwei Yan Miaomiao Wang Yepang Liu Jun Yan Long Zhang Technology Center of Software Engineering Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

Nowadays, many applications do not exist independently but rely on various frameworks or libraries. The frequent evolution and the complex implementation of framework APIs induce lots of unexpected post-release crashes. Starting from the crash stack traces, existing approaches either perform application-level call graph (CG) tracing or construct datasets with similar crash-fixing records to locate buggy methods. However, these approaches are limited by the completeness of CG or dependent on historical fixing records, and some of them only focus on specific manually modeled exception types. To achieve effective debugging on complex framework-specific crashes, we propose a code-separation-based locating approach that weakly relies on CG tracing and does not require any prior knowledge. Our key insight is that one crash trace with the description message can be mapped to a definite exception-thrown point in the framework, the semantics analysis of which can help to figure out the root causes of the crash-triggering procedure. Thus, we can pre-construct reusable summaries for all the framework-specific exceptions to support fault localization in application code. Based on that idea, we design the exception-thrown summary (ETS) that describes both the key variables and key APIs related to the exception triggering. Then, we perform static analysis to automatically compute such summaries and make a data-tracking of key variables and APIs in the application code to get the ranked buggy candidates. In the scenario of locating Android framework-specific crashing faults, our tool CrashTracker exhibited an overall MRR value of 0.91 and outperforms the state-of-the-art tool Anchor with higher precision. It only provides a compact candidate set and gives user-friendly reports with explainable reasons for each candidate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rsta: A Reversible Signal Transmission Architecture for Breaking the Limitation of Unidirectional Transmission

SSRN

引用

SSRN 2025年

作者： Liu, Xin Cui, Shuang Zhang, Xun Zhou, Fuxing Sheng, Kaikai Wang, Bin Zhang, Qiang School of Computer Science and Technology Dalian University of Technology Dalian116024 China Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian116622 China

Molecular circuits are essential tools for biosensing and molecular information processing. However, the long-distance and reversible transmission of orthogonal signals remains a significant challenge in molecular circuits, preventing molecular signals from achieving reversible transmission similar to that of electrical signals in wires. To overcome the limitations of unidirectional signal transmission and facilitate the integration of antagonistic circuits. We propose a reversible signal transmission architecture (RSTA) with wire-like characteristics to achieve reversible signal transmission based on fundamental molecular devices known as reversible signal fan-out devices (RSFDs). The polarity of the input signal dictates the transmission direction, establishing the initial condition for the output signals. Cascaded RSFDs within RSTA offer two key advantages. First, the temporal response to signals. Second, the reversible transformation of opposite circuit types without structural modification. We experimentally validated the principles and functionality of RSTA using temporal logic device and integrated molecular circuits. This work advances the field of reversible molecular signal transmission, enabling the rational design of complex molecular circuits and molecular information processing systems. We envision applications of this technology in nanomachines, molecular computing, and biosensing. © 2025, The Authors. All rights reserved.

关键词： Temporal logic

来源：评论

学校读者我要写书评

暂无评论

Visual Style Prompt Learning Using Diffusion Models for Blind Face Restoration

arXiv

引用

arXiv 2024年

作者： Lu, Wanglong Wang, Jikai Wang, Tao Zhang, Kaihao Jiang, Xianta Zhao, Hanli Key Laboratory of Intelligent Informatics for Safety and Emergency of Zhejiang Province Wenzhou University China Department of Computer Science Memorial University of Newfoundland St. John’s Canada State Key Laboratory for Novel Software Technology Nanjing University China College of Engineering and Computer Science Australian National University Australia

Blind face restoration aims to recover high-quality facial images from various unidentified sources of degradation, posing significant challenges due to the minimal information retrievable from the degraded images. Prior knowledge-based methods, leveraging geometric priors and facial features, have led to advancements in face restoration but often fall short of capturing fine details. To address this, we introduce a visual style prompt learning framework that utilizes diffusion probabilistic models to explicitly generate visual prompts within the latent space of pre-trained generative models. These prompts are designed to guide the restoration process. To fully utilize the visual prompts and enhance the extraction of informative and rich patterns, we introduce a style-modulated aggregation transformation layer. Extensive experiments and applications demonstrate the superiority of our method in achieving high-quality blind face restoration. The source code is available at https://***/LonglongaaaGo/*** Codes 68U10 © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ST-Tree with Interpretability for Multivariate Time Series Classification

arXiv

引用

arXiv 2024年

作者： Du, Mingsen Wei, Yanxuan Tang, Yingxia Zheng, Xiangwei Wei, Shoushui Ji, Cun School of Control Science and Engineering Shandong University Jinan China School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan China

Multivariate time series classification is of great importance in practical applications and is a challenging task. However, deep neural network models such as Transformers exhibit high accuracy in multivariate time series classification but lack interpretability and fail to provide insights into the decision-making process. On the other hand, traditional approaches based on decision tree classifiers offer clear decision processes but relatively lower accuracy. Swin Transformer (ST) addresses these issues by leveraging self-attention mechanisms to capture both fine-grained local patterns and global patterns. It can also model multi-scale feature representation learning, thereby providing a more comprehensive representation of time series features. To tackle the aforementioned challenges, we propose ST-Tree with interpretability for multivariate time series classification. Specifically, the ST-Tree model combines ST as the backbone network with an additional neural tree model. This integration allows us to fully leverage the advantages of ST in learning time series context while providing interpretable decision processes through the neural tree. This enables researchers to gain clear insights into the model’s decision-making process and extract meaningful interpretations. Through experimental evaluations on 10 UEA datasets, we demonstrate that the ST-Tree model improves accuracy in multivariate time series classification tasks and provides interpretability through visualizing the decision-making process across different datasets. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer (ViT)-based Applications in Image Classification

Vision Transformer (ViT)-based Applications in Image Classif...

引用

IEEE International Conference on Big Data Security on Cloud (BigDataSecurity), High Performance and Smart Computing (HPSC) and Intelligent Data and Security (IDS)

作者： Yingzi Huo Kai Jin Jiahong Cai Huixuan Xiong Jiacheng Pang School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China the College of Computer Science and Electronics Engineering Hunan University Changsha China

In recent years, the ViT model has been widely used in the field of computer vision, especially for image classification tasks. This paper summarizes the application of ViT in image classification tasks, first introduces the image classification imple- mentation process and the basic architecture of the ViT model, then analyzes and summarizes the image classification methods, including traditional image classification methods, CNN-based image classification methods, and ViT-based image classification methods, and provides a comparative analysis of CNN and ViT. Subsequently, this paper outlines the application prospects of ViT in image classification and its future development and also outlines some shortcomings of ViT and its solutions.

关键词： Representation learning Analytical models Visualization Computational modeling Transformers Reservoirs Data models

来源：评论

学校读者我要写书评

暂无评论

Relay Assisted Covert Communications in Underlay Cognitive Radio Networks

Relay Assisted Covert Communications in Underlay Cognitive R...

引用

Ubiquitous Communication (Ucom), International Conference on

作者： Hongbin Fan Weiwei Yang Wenqiang Feng Chuanzhen Rong College of Communications Engineering PLA Army Engineering University Nanjing China College of Computer and Artificial Intelligence Xiangnan University Chenzhou China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350374216

ISBN: (纸本)9798350374223

Cognitive radio can meet the increasing demand for wireless spectrum in 5G and B5G, and relay can relay-assisted covert communications in underlay cognitive radio networks (UCRN) to reaching distant destinations. Therefore, we investigated relay-assisted covert communication in UCRN. In phase 1, the secondary source (SS) sends covert messages to the relay, and the relay sends interference signals to Willie. In phase 2, the relay decodes and forwards the covert information received in phase 1, and SS sends interference signals to Willie to ensure covert transmission. The average detection error probability, the transmission outage probability and the maximum effective covert rate of the system are derived. The simulation results show that the average minimum detection error probability in phase 1 and the transmission outage probability decrease with the increase of the maximum interference tolerance of primary destination (PD), and the maximum effective covert rate increases with the increase of the maximum interference tolerance of PD.

关键词： Error probability 5G mobile communication Simulation Collaboration Interference Power system reliability Performance analysis Cognitive radio Relays

来源：评论

学校读者我要写书评

暂无评论

TextIM: Part-aware Interactive Motion Synthesis from Text

arXiv

引用

arXiv 2024年

作者： Fan, Siyuan Du, Bo Cai, Xiantao Peng, Bo Sun, Longling National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Institute of Artificial Intelligence Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

In this work, we propose TextIM, a novel framework for synthesizing TEXT-driven human Interactive Motions, with a focus on the precise alignment of part-level semantics. Existing methods often overlook the critical roles of interactive body parts and fail to adequately capture and align part-level semantics, resulting in inaccuracies and even erroneous movement outcomes. To address these issues, TextIM utilizes a decoupled conditional diffusion framework to enhance the detailed alignment between interactive movements and corresponding semantic intents from textual descriptions. Our approach leverages large language models, functioning as a human brain, to identify interacting human body parts and to comprehend interaction semantics to generate complicated and subtle interactive motion. Guided by the refined movements of the interacting parts, TextIM further extends these movements into a coherent whole-body motion. We design a spatial coherence module to complement the entire body movements while maintaining consistency and harmony across body parts using a part graph convolutional network. For training and evaluation, we carefully selected and re-labeled interactive motions from HUMANML3D to develop a specialized dataset. Experimental results demonstrate that TextIM produces semantically accurate human interactive motions, significantly enhancing the realism and applicability of synthesized interactive motions in diverse scenarios, even including interactions with deformable and dynamically changing objects. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Linear time approximation algorithm for column subset selection with local search 24

Linear time approximation algorithm for column subset select...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yuanbin Zou Ziyun Huang Jinhui Xu Jianxin Wang Qilong Feng School of Computer Science and Engineering Central South University Changsha China and Xiangjiang Laboratory Changsha China Department of Computer Science and Software Engineering Penn State Erie The Behrend College Department of Computer Science and Engineering State University of New York at Buffalo NY School of Computer Science and Engineering Central South University Changsha China and Xiangjiang Laboratory Changsha China and The Hunan Provincial Key Lab of Bioinformatics Central South University Changsha China

ISBN: (纸本)9798331314385

The Column Subset Selection (CSS) problem has been widely studied in dimensionality reduction and feature selection. The goal of the CSS problem is to output a submatrix S, consisting of k columns from an n × d input matrix A that minimizes the residual error ||A – SS† A||2F where S† is the Moore-Penrose inverse matrix of S. Many previous approximation algorithms have non-linear running times in both n and d, while the existing linear-time algorithms have a relatively larger approximation ratios. Additionally, the local search algorithms in existing results for solving the CSS problem are heuristic. To achieve linear running time while maintaining better approximation using a local search strategy, we propose a local search-based approximation algorithm for the CSS problem with exactly k columns selected. A key challenge in achieving linear running time with the local search strategy is how to avoid exhaustive enumerations of candidate columns for constructing swap pairs in each local search step. To address this issue, we propose a two-step mixed sampling method that reduces the number of enumerations for swap pair construction from O(dk) to k in linear time. Although the two-step mixed sampling method reduces the search space of local search strategy, bounding the residual error after swaps is a non-trivial task. To estimate the changes in residual error after swaps, we propose a matched swap pair construction method to bound the approximation loss, ensuring a constant probability of loss reduction in each local search step. In expectation, these techniques enable us to obtain the local search algorithm for the CSS problem with theoretical guarantees, where a 53(k + 1)-approximate solution can be obtained in linear running time O(ndk4 log k). Empirical experiments show that our proposed algorithm achieves better quality and time compared to previous algorithms on both small and large datasets. Moreover, it is at least 10 times faster than state-of-the-art algorith

关键词：

来源：评论

学校读者我要写书评

暂无评论

MUSE: A Multi-Feature Semantic Fusion Method for ROS Node Search Based on Knowledge Graph

MUSE: A Multi-Feature Semantic Fusion Method for ROS Node Se...

引用

Asia-Pacific Conference on software engineering

作者： Yuxin Zhao Xinjun Mao Tanghaoran Zhang Zhang Zhang College of Computer National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China

Reusing ROS components, specifically ROS Nodes, is crucial for improving the efficiency and quality of robotic software development. However, developers face challenges in finding the desired ROS Nodes for reuse due to scattered organization of ROS Nodes and the ambiguity in their ROS Node name. To address these challenges, this paper proposes a MUlti-feature SEmantic fusion method (MUSE) that leverages a domain-specific ROS knowledge graph for searching ROS Nodes. Firstly, a large dataset is constructed, comprising code files and textual descriptions related to ROS Nodes obtained from GitHub and ROS Wiki. Secondly, an in-depth analysis of user queries regarding the reuse of ROS Nodes is conducted, leading to the selection of multiple features that provide a comprehensive representation of ROS Node semantics, including Function, Hardware, Input, and Output. Subsequently, a knowledge graph of ROS Nodes is developed based on the dataset, incorporating the selected features. This knowledge graph effectively organizes scattered knowledge and resolves the issue of diverse mentions through entity disambiguation and resolution. To eliminate the semantic gap between the descriptions of features mentioned in user queries and the entities in the knowledge graph, a pretrained transformer-based model was used to measure the multi-feature semantic similarity between user queries and ROS Nodes knowledge. Finally, we employ a linear regression model to integrate the multi-feature knowledge between user queries and ROS Nodes knowledge. The proposed method has shown a 20% improvement in performance on NDCG@1 compared to other ROS Node search methods. Further evaluations highlight the effectiveness of each feature incorporated in the knowledge graph, as well as the significance of each parameter within the regression model. These findings underscore the robustness of this research in optimizing the reuse of ROS Nodes and facilitating the development of robotics software.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TSCA: Enhancing Smartphone Security with a Touchpoints-Sensitive and Context-Aware Model for Touchscreen-Based Authentication

TSCA: Enhancing Smartphone Security with a Touchpoints-Sensi...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yingjie Wang Ruimin Hu National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Whuhan China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Whuhan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

With the widespread use of smartphones, more and more private information is stored on them, which requires a more secure authentication method. Continuous authentication methods show potential for privacy protection due to their continuous and transparent nature, as opposed to the entry-point authentication methods like PIN codes and facial recognition. Users' touchscreen behavior, being both common and unique, has been widely studied in the field. However, previous methods based on manual features and deep learning have certain shortcomings when mining patterns from touchscreen behaviors that are beneficial for authentication. First, the operating habits of different users lead to different importance of touch points in a single touchscreen swipe. Second, extracting features from each touchscreen swipe independently ignores useful information from the context. To address this problem, we propose a novel Touchpoints-Sensitive and Context-Aware model called TSCA, which is able to adaptively assign weights to different touch points in a touchscreen swipe while also taking into account information from the context of the touchscreen swipe. We evaluate the TSCA model on two publicly available datasets and show that the TSCA is able to deliver significant performance gains compared to baseline methods while reducing model complexity.

关键词： Deep learning Adaptation models Privacy Computational modeling Authentication Touch sensitive screens Feature extraction Complexity theory Smart phones Context modeling

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：