检索结果-内蒙古大学图书馆

International Conference on Engineering and Emerging Technologies (ICEET)

作者： Irfan Ahmed Sadia Naseer Umm - e - Habiba Jabar Mahmood Shehzad Ashraf Chaudhry Khadija Batool Department of Computer Science University of Sialkot Sialkot Pakistan State Key Laboratory of Blockchain School of Cyber Science and Technology College of Computer Science and Technology Zhejiang University Hangzhou China Department of Computer Science and Information Technology College of Engineering Abu Dhabi University Abu Dhabi U.A.E International Institute of Science Arts and Technology (IISAT) Gujranwala Pakistan

ISBN: (数字)9798331532895

ISBN: (纸本)9798331532901

Formal methods (FM) are innovative methods which employ mathematical notations to specify explicit and precise requirements. This paper presents a formal model of an automated teller machine (ATM) using Object Constraint Language (OCL) to illustrate the benefits of employing FM to develop commercial applications. FM provide a mathematically rigorous framework for specifying, developing, and verifying software systems. It enhances reliability, robustness, and security. FM plays a crucial role in the context of ATM, which requires high levels of trust and correctness due to their financial and security-critical nature. Using OCL, we demonstrate how formal specifications can be applied to define an ATM system's precise behavior and constraints. It allows for the early detection and correction of errors, reducing development costs and improving overall system quality. This study argues that adopting FM in commercial applications not only boosts the reliability and security of the systems but also increases customer satisfaction and trust. Results of ATM development under OCL have been compared with traditional methods (TM), showing reductions such as 51 % in development time, 53 % in cost, 94 % in ambiguity and 97% in quality and customer trust.

关键词： Frequency modulation Costs Automated teller machine software systems software reliability Security Formal specifications Stakeholders Testing software engineering

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning Point Cloud Transformers with Dynamic Aggregation

Fine-Tuning Point Cloud Transformers with Dynamic Aggregatio...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Jiajun Fei Zhidong Deng Department of Computer Science and Technology Institute for Artificial Intelligence Tsinghua University (THUAI) State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Point clouds play an important role in 3D analysis, which has broad applications in robotics and autonomous driving. The pre-training fine-tuning paradigm has shown great potential in the point cloud domain. Full fine-tuning is generally effective but leads to a heavy storage and computational burden, which becomes inefficient and unacceptable as the size of pre-trained models scales. Although efficient fine-tuning approaches have significant progress in other domains, they generally perform worse for point clouds. To overcome this dilemma, we revisit the official Point-MAE implementation and find the critical role of aggregation in fine-tuning performances. Inspired by such discoveries, we propose a novel dynamic aggregation (DA) method to replace previous static aggregation like mean or max pooling for pre-trained point cloud Transformers. Besides standard metrics such as accuracy or mIoU, we evaluate the number of tunable parameters and additional FLOPs for a fair comparison of our method to different fine-tuning approaches. We construct several DA variants and validate them through extensive experiments. Experimental results demonstrate that DA has competitive performances against full fine-tuning and other efficient fine-tuning approaches. The code is publicly available at https://***/JaronTHU/DynamicAggregation.

关键词： Point cloud compression Measurement Three-dimensional displays Codes Computational modeling Aggregates Transformers

来源：评论

学校读者我要写书评

暂无评论

Incorporating Rotation Invariance with Non-invariant Networks for Point Clouds

Incorporating Rotation Invariance with Non-invariant Network...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： Jiajun Fei Zhidong Deng Department of Computer Science and Technology Tsinghua University State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology (BNRist) Institute for Artificial Intelligence at Tsinghua University (THUAI) Beijing China

ISBN: (数字)9798350362459

ISBN: (纸本)9798350362466

Rotation invariance is a fundamental requirement of point cloud processing when input point clouds are not aligned. Many non-invariant networks performing well on aligned point clouds do not perform equivalent to rotated ones. Thus non-invariant and invariant networks are developed separately and only benefit a little from each other, leading to repetitive and wasteful research efforts. In this paper, we aim to bridge this gap and incorporate rotation invariance with non-invariant networks for point clouds. To this end, we propose a novel rotation invariant learning method based on efficient invariant poses (EIPs). EIPs do not rely on novel features or operations. Instead, they only rotate input point clouds into invariant poses and apply non-invariant networks in feature processing. As the name implies, EIPs have negligible complexities (efficient) and solid theoretical foundations (invariant). Experimental results demonstrate that EIPs have competitive performances on several tasks. Without using new features or operations, EIPs yield the best results on ScanObjectNN (PB T50 RS) classification and ShapeNetPart segmentation task. Our code is available at: https://***/JaronTHU/EIP.

关键词： Point cloud compression Bridges Representation learning Three-dimensional displays Codes Solids Complexity theory

来源：评论

学校读者我要写书评

暂无评论

BTM: Black-Box Testing for DNN Based on Meta-Learning

BTM: Black-Box Testing for DNN Based on Meta-Learning

引用

IEEE International Conference on software Quality, Reliability and Security (QRS)

作者： Zhuangyu Zhang Zhiyi Zhang Ziyuan Wang Fang Chen Zhiqiu Huang Collage of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing University of Aeronautics and Astronautics Nanjing China

Deep learning is widely used in security fields like autonomous driving, but testing deep learning models poses challenges due to low generation efficiency and limited error detection. Current white-box test case generation methods rely on neuron coverage, but black-box testing is crucial when model details cannot be accessed. Prior methods also needed more consideration for error diversity under lower time resources. In this paper, we propose a novel approach based on the intuition that two models trained on the same classification task learn similar rules at a coarse-grained level. We employ meta-learning to train universal meta perturbation on a surrogate model, which increases neuron coverage on the surrogate model while inducing misclassifications in the original model (thus enhancing the adequacy of the initial tests). Subsequently, we apply data initialization to discover a wider range of errors faster. To accelerate test case generation and reduce resource consumption, we introduce a set of acceleration techniques based on image prediction probabilities, minimizing the time spent exploring irrelevant regions in images. Finally, we evaluate our approach on a well-known dataset and several well-known models, demonstrating its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Uncovering Bugs in Code Coverage Profilers via Control Flow Constraint Solving”

引用

IEEE Transactions on software Engineering 2024年第1期50卷 158-158页

作者： Yang Wang Peng Zhang Maolin Sun Zeyu Lu Yibiao Yang Yutian Tang Junyan Qian Zhi Li Yuming Zhou State Key Laboratory for Novel Software Technology and the Department of Computer Science and Technology Nanjing University Nanjing China

In [1, p. 4967], a figure citation is incorrect and “Fig. 3(c)” should be “Fig. 1(c)” in the left column, the fourth line from the bottom. It is corrected below.

关键词： computer bugs Codes

来源：评论

学校读者我要写书评

暂无评论

Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation

arXiv

引用

arXiv 2025年

作者： Wang, Yin Li, Mu Liu, Jiapeng Leng, Zhiying Li, Frederick W.B. Zhang, Ziyao Liang, Xiaohui B. State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Department of Computer Science University of Durham United Kingdom Zhongguancun Laboratory Beijing China

We address the challenging problem of fine-grained text-driven human motion generation. Existing works generate imprecise motions that fail to accurately capture relationships specified in text due to: (1) lack of effective text parsing for detailed semantic cues regarding body parts, (2) not fully modeling linguistic structures between words to comprehend text comprehensively. To tackle these limitations, we propose a novel fine-grained framework Fg-T2M++ that consists of: (1) an LLMs semantic parsing module to extract body part descriptions and semantics from text, (2) a hyperbolic text representation module to encode relational information between text units by embedding the syntactic dependency graph into hyperbolic space, and (3) a multi-modal fusion module to hierarchically fuse text and motion features. Extensive experiments on HumanML3D and KIT-ML datasets demonstrate that Fg-T2M++ outperforms SOTA methods, validating its ability to accurately generate motions adhering to comprehensive text semantics. Copyright © 2025, 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

Location-Based Service Recommendation for Cold-Start in Mobile Edge Computing 17th

Location-Based Service Recommendation for Cold-Start in Mobi...

引用

17th IFIP WG 10.3 International Conference on Network and Parallel Computing, NPC 2020

作者： Yu, Mengshan Fan, Guisheng Yu, Huiqun Chen, Liang Department of Computer Science and Engineering East China University of Science and Technology Shanghai China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China

ISBN: (纸本)9783030794774

With the rapid development of the 5G and Internet of Things (IoT), mobile edge computing has gained considerable popularity in academic and industrial field, which provides physical resources closer to end users. Service recommendation in such a distributed environment is a hot issue. However, the cold-start problem for service recommendation in mobile edge computing is still urgent to be solved. In this paper, we propose a service recommendation method based on collaborative filtering (CF) and user location, by comprehensively considering the characteristic of services at the edge and mobility of users. In detail, we first synthesize the service characteristics of each dimension through multidimensional weighting method. We further introduce the idea of Inverse_CF_Rec to the traditional CF and then predict the lost QoS value to solve the problem of sparse data. Finally, a recommendation algorithm based on predicted QoS value and user geographic location is proposed to recommend appropriate services to users. The experimental results show that our multidimensional inverse similarity recommendation algorithm based on collaborative filtering (MDICF) outperforms Inverse_CF_Rec in terms of the accuracy of recommendation. © 2021, IFIP International Federation for Information Processing.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

MPANet: Multi-level Progressive Aggregation Network for Crowd Counting 28th

MPANet: Multi-level Progressive Aggregation Network for Cro...

引用

28th International Conference on Neural Information Processing, ICONIP 2021

作者： Meng, Chen Han, Run Pang, Chen Kang, Chunmeng Lyu, Chen Lyu, Lei School of Information Science and Engineering Shandong Normal University Jinan250358 China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan250358 China

ISBN: (纸本)9783030922375

Crowd counting has important applications in many fileds, but it is still a challenging task due to background occlusion, scale variation and uneven distribution of crowd. This paper proposes the Multi-level Progressive Aggregation Network (MPANet) to enhance the channel and spatial dependencies of feature maps and effectively integrate the multi-level features. Besides, the Aggregation Refinement (AR) module is designed to integrate low-level spatial information and high-level semantic information. The proposed AR module can effectively utilize the complementary properties between multi-level features to generate high-quality density maps. Moreover, the Multi-scale Aware (MA) module is constructed to capture rich contextual information through convolutional kernels of different sizes. Furthermore, the Semantic Attention (SA) module is designed to enhance spatial and channel response on feature maps, which can reduce false recognition of the background region. Extensive experiments on four challenging datasets demonstrate that our approach outperforms most state-of-the-art methods. © 2021, Springer Nature Switzerland AG.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

MRLATO: An Adaptive Task Offloading Mechanism Based on Meta Reinforcement Learning in Edge Computing Environment

引用

IEEE Transactions on Vehicular technology 2025年

作者： Zhang, Peiying Liu, Jiamin Guizani, Maher Wang, Jian Kumar, Neeraj Tan, Lizhuang Qingdao Institute of Software College of Computer Science and Technology Qingdao266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao266580 China Ministry of Education Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China University of Texas Arlington Computer Science and Engineering Department TX United States College of Science Qingdao266580 China Thapar University Department of Computer Science and Engineering Patiala147004 India Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Traditional cloud computing models struggle to meet the requirements of latency-sensitive applications when processing large amounts of data. As a solution, Multi-access Edge Computing (MEC) extends computing resources to the edge of the network to reduce processing delays and improve user experience. However, in dynamically changing edge computing environments, effective decision making on whether to offload tasks to edge servers remains a core challenge. For this purpose, we propose MRLATO, an adaptive task offloading mechanism based on Meta Reinforcement Learning (MRL), which exploits a large amount of a priori knowledge of different tasks to achieve fast adaptation. The task offloading process is modelled as multiple Markov Decision Processes (MDPs) and solved using a Sequence to Sequence (Seq2Seq) neural network integrating multi-head attention and recursive task sequencing. It is shown by the experimental results that the proposed method has the lowest latency in all experimental settings and the convergence efficiency is improved by 14.06% compared to the traditional Deep Reinforcement Learning (DRL) algorithm. This research fully demonstrates the significant benefits of the deep integration of MRL with the edge computing domain, providing new optimisation ideas for task offloading decisions. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

How Re-sampling Helps for Long-Tail Learning?

arXiv

引用

arXiv 2023年

作者： Shi, Jiang-Xin Wei, Tong Xiang, Yuke Li, Yu-Feng National Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Consumer BG Huawei Technologies Shenzhen China

Long-tail learning has received significant attention in recent years due to the challenge it poses with extremely imbalanced datasets. In these datasets, only a few classes (known as the head classes) have an adequate number of training samples, while the rest of the classes (known as the tail classes) are infrequent in the training data. Re-sampling is a classical and widely used approach for addressing class imbalance issues. Unfortunately, recent studies claim that re-sampling brings negligible performance improvements in modern long-tail learning tasks. This paper aims to investigate this phenomenon systematically. Our research shows that re-sampling can considerably improve generalization when the training images do not contain semantically irrelevant contexts. In other scenarios, however, it can learn unexpected spurious correlations between irrelevant contexts and target labels. We design experiments on two homogeneous datasets, one containing irrelevant context and the other not, to confirm our findings. To prevent the learning of spurious correlations, we propose a new context shift augmentation module that generates diverse training images for the tail class by maintaining a context bank extracted from the head-class images. Experiments demonstrate that our proposed module can boost the generalization and outperform other approaches, including class-balanced re-sampling, decoupled classifier re-training, and data augmentation methods. The source code is available at https://***/code_***. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

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：