检索结果-内蒙古大学图书馆

Error-Aware Generative Reasoning for Zero-Shot Visual Grounding

IEEE Transactions on Multimedia 2025年

作者： Bu, Yuqi Wu, Xin Cai, Yi Liu, Qiong Wang, Tao Huang, Qingbao South China University of Technology School of Software Engineering Guangzhou510006 China Guangzhou510006 China King's College London Department of Biostatistics and Health Informatics Institute of Psychiatry Psychology and Neuroscience LondonWC2R 2LS United Kingdom Guangxi University School of Electrical Engineering Institute of Artificial Intelligence Nanning530005 China

Zero-shot visual grounding is the task of identifying and localizing an object in an image based on a referring expression without task-specific training. Existing methods employ heuristic rules to step-by-step perform visual perception for visual grounding. Despite their remarkable performance, there are still two limitations. First, such a rule-based manner struggles with expressions that are not covered by predefined rules. Second, existing methods lack a mechanism for identifying and correcting visual perceptual errors of incomplete information, resulting in cascading errors caused by reasoning based on incomplete visual perception results. In this article, we propose an Error-Aware Generative Reasoning (EAGR) method for zero-shot visual grounding. To address the limited adaptability of existing methods, a reasoning chain generator is presented, which prompts LLMs to dynamically generate reasoning chains for specific referring expressions. This generative manner eliminates the reliance on human-written heuristic rules. To mitigate visual perceptual errors of incomplete information, an error-aware mechanism is presented to elicit LLMs to identify these errors and explore correction strategies. Experimental results on four benchmarks show that EAGR outperforms state-of-the-art zero-shot methods by up to 10% and an average of 7%. © 1999-2012 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes

arXiv

引用

arXiv 2024年

作者： Pan, Ziying Wang, Kun Li, Gang He, Feihong Lai, Yongxuan School of Informatics Xiamen University China Institute of Software Chinese Academy of Sciences China School of Mathematics and Information Engineering Longyan University China Shenyang Institute of Computing Technology of Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Computer Science and Technology Soochow University China

The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A more challenging task, large-scale fine-grained image generation, remains the boundary to explore. In this work, we present a parameter-efficient strategy, called FineDiffusion, to fine-tune large pre-trained diffusion models scaling to large-scale fine-grained image generation with 10,000 categories. FineDiffusion significantly accelerates training and reduces storage overhead by only fine-tuning tiered class embedder, bias terms, and normalization layers' parameters. To further improve the image generation quality of fine-grained categories, we propose a novel sampling method for fine-grained image generation, which utilizes superclass-conditioned guidance, specifically tailored for fine-grained categories, to replace the conventional classifier-free guidance sampling. Compared to full fine-tuning, FineDiffusion achieves a remarkable 1.56× training speed-up and requires storing merely 1.77% of the total model parameters, while achieving state-of-the-art FID of 9.776 on image generation of 10,000 classes. Extensive qualitative and quantitative experiments demonstrate the superiority of our method compared to other parameter-efficient fine-tuning methods. The code and more generated results are available at our project website: https://***/. © 2024, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Welcome to the Eighth International Workshop on Crowd-Based Requirements engineering (CrowdRE'24)

Welcome to the Eighth International Workshop on Crowd-Based ...

引用

IEEE International Requirements engineering Conference Workshops (REW)

作者： Julian Frattini Gouri Ginde Eduard C. Groen Oliver Karras Norbert Seyff Department of Software Engineering Blekinge Institute of Technology Karlskrona Sweden Dept. of Electrical and Software Engineering University of Calgary Canada Fraunhofer IESE Kaiserslautern Germany Department of Information and Computing Sciences Utrecht University Netherlands TIB - Leibniz Information Centre for Science and Technology Hannover Germany University of Applied Sciences and Arts Northwestern Switzerland Windisch Switzerland Department of Informatics University of Zurich Zurich Switzerland

ISBN: (数字)9798350395518

ISBN: (纸本)9798350395525

Welcome to the 8th International Workshop on Crowd-Based Requirements engineering (CrowdRE'24), where scientists and representatives engage in interactive discussions to analyze the state-of-the-art Crowd-Based Requirements engineering (CrowdRE) and to inspire each other in ways to move forward together. The discipline of CrowdRE seeks to address the challenges of traditional requirements engineering (RE) in scaling up to settings with thousands to millions of users of (software) products or (software-driven) services, who form a large and heterogeneous group that can be denoted as a ‘crowd’ [1], [2]. The online user feedback generated by the crowd, such as texts or usage data, can be a valuable source of requirements, problems, wishes, and needs. Responding quickly, effectively, and iteratively to this feedback can greatly increase a product's success. CrowdRE comprises any approach that provides RE with suitable means for this crowd paradigm, especially by involving the crowd and by collecting, harmonizing, analyzing, and interpreting their feedback.

关键词： Conferences Logic gates software Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Towards pragmatic interoperability: a conceptual framework for an energy IoT platform in the German energy sector

Towards pragmatic interoperability: a conceptual framework f...

引用

CIRED 2024 Vienna Workshop

作者： Alexandra Karmann Maximilian Kilthau Christian Derksen Florian Strobel Lukas Bittermann Kamil Korotkiewicz Jonas Ostmeyer Alexander Fay Institute of Automation Technology Helmut-Schmidt-University Hamburg Germany Research Group for Business Informatics and Software Engineering University Duisburg-Essen Essen Germany Institute of Electrical Power and Energy Technology University of Technology Hamburg Hamburg Germany PSI GridConnect GmbH Karlsruhe Germany PSI FLS Fuzzy Logik & Neuro Systeme GmbH Dortmund Germany

ISBN: (数字)9781837241224

This paper introduces an innovative conceptual framework for an Energy Internet of Things (eIoT) platform designed to address challenges related to grid congestion, voltage limit violations, and the growing demands on low-voltage grids due to increased electrification in the energy and heating sectors. The proposed platform seamlessly integrates cutting-edge technologies including advanced data collection, state estimation algorithms, AI-driven decision-making processes, and grid control functionalities. Its primary objective is to facilitate proactive measures aimed at enhancing energy distribution efficiency and effectively managing consumption devices while ensuring compliance with regulatory standards such as §14a of the Energy Industry Act (EnWG) in Germany.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-model Fusion Solution for IEEE UV 2022 'Vision Meets Algae' Object Detection Challenge 6

Multi-model Fusion Solution for IEEE UV 2022 'Vision Meets A...

引用

6th IEEE International Conference on Universal Village, UV 2022

作者： Peng, Xiaoxiao Wang, Yueyi Chen, Dayu Tian, Yuchen Huang, Keyu Zheng, Jianfeng Robot Technology Co. Ltd Department of Automatic Driving Software Engineering Shanghai China King's College London Department of Informatics London United Kingdom Didi Chuxing Department of Algorithm Strategy Hangzhou China Institute of Advanced Technology University of Science and Technology of China Anhui China Koto Communication Technology Co. Ltd Department of Algorithm Strategy Xiamen China

ISBN: (纸本)9781665474771

This report summarizes the fourth-place solution of the 'Vision Meets Algae' object detection challenge held on IEEE UV'2022 focuses on object detection in marine biology images obtained through the microscope. First, we experimented with a large number of backbones and necks to improve mAP by enhancing the model structure. Then, we designed and tested a variety of data augmentation schemes based on algal characteristics from a data perspective. Finally, with multiple models ensembled adopted, our methods achieve 57.579% mAP on the test set. © 2022 IEEE.

关键词： Algae

来源：评论

学校读者我要写书评

暂无评论

Growing Organizations with Patterns: Lessons from Drama 20

Growing Organizations with Patterns: Lessons from Drama

引用

2020 European Conference on Pattern Languages of Programs, EuroPLoP 2020

作者： Vranić, Valentino Vranić, Aleksandra Khail, Waheedullah Sulaiman Institute of Informatics Information Systems and Software Engineering Slovak University of Technology in Bratislava Slovakia Slovakia

ISBN: (纸本)9781450377690

Organizational patterns of software development have been mined in highly successful software organizations. Yet, no case of their application in a production setting has been reported. Our fear is that this is so because practitioners are expected to apply organizational patterns out of their descriptions. Organizational patterns of software development inspired explicitly stating and documenting drama patterns. We think that drama patterns have something to give back: interactivity and involvement exhibited by the process of building drama plays with drama patterns can be introduced into applying organizational patterns of software development. The key to this is that organizing people in software development is like creating a drama play. As in drama plays, the members of software development organizations take different roles and go through a number of situations in which they communicate and collaborate with each other. Although their drama plays will never be performed in front of the audience, these drama plays are going to determine the software systems they build. Coming out of two particular cases of pattern application related to people, one of which is about a software development organization built out of patterns with the applier not being aware of the notion of an organizational pattern, and the other about drama play built by intentionally applying drama patterns, some lessons have been drawn on how to apply organizational patterns of software development. © 2020 ACM.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

A progression model of software engineering goals, challenges, and practices in start-ups

arXiv

引用

arXiv 2023年

作者： Klotins, Eriks Unterkalmsteiner, Michael Chatzipetrou, Panagiota Gorschek, Tony Prikladnicki, Rafael Tripathi, Nirnaya Pompermaier, Leandro Bento The Software Engineering Research Lab Sweden Blekinge Institute of Technology Karlskrona Sweden Department of Informatics CERIS Örebro University School of Business ÖrebroSE-701 82 Sweden Software Engineering Research Lab. Blekinge Institute of Technology Karlskrona Sweden School of Technology The Pontifical Catholic University of Rio Grande do Sul Brazil M3S Research Unit University of Oulu Finland

Context: software start-ups are emerging as suppliers of innovation and software-intensive products. However, traditional software engineering practices are not evaluated in the context, nor adopted to goals and challenges of start-ups. As a result, there is insufficient support for software engineering in the start-up context. Objective: We aim to collect data related to engineering goals, challenges, and practices in start-up companies to ascertain trends and patterns characterizing engineering work in start-ups. Such data allows researchers to understand better how goals and challenges are related to practices. This understanding can then inform future studies aimed at designing solutions addressing those goals and challenges. Besides, these trends and patterns can be useful for practitioners to make more informed decisions in their engineering practice. Method: We use a case survey method to gather first-hand, in-depth experiences from a large sample of software start-ups. We use open coding and cross-case analysis to describe and identify patterns, and corroborate the findings with statistical analysis. Results: We analyze 84 start-up cases and identify 16 goals, 9 challenges, and 16 engineering practices that are common among startups. We have mapped these goals, challenges, and practices to start-up life-cycle stages (inception, stabilization, growth, and maturity). Thus, creating the progression model guiding software engineering efforts in start-ups. Conclusions: We conclude that start-ups to a large extent face the same challenges and use the same practices as established companies. However, the primary software engineering challenge in start-ups is to evolve multiple process areas at once, with a little margin for serious errors. © 2023, CC BY-NC-SA.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Dsh-Rsf-Lite Approach: Towards Lightweight Pneumonia Classification Network with Few-Shot Augmentation on Chest X-Ray Images

SSRN

引用

SSRN 2024年

作者： Chen, Hongbin Zhu, Zhou Wang, Wei Yang, Chunfeng Li, Jie Liu, Chengyu Kiong, Loo Chu Wang, Zhelong Li, Jianqing Xiang, Wentao The Engineering Research Center of Intelligent Theranostics Technology and Instruments Ministry of Education School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing211166 China The School of Software Engineering Jinling Institute of Technology Nanjing211169 China Nanjing China The State Key Laboratory of Digital Medical Engineering School of Instrument Science and Engineering Southeast University Nanjing China Kuala Lumpur50603 Malaysia The School of Control Science and Engineering Dalian University of Technology Dalian116024 China

Pneumonia classification using chest X-ray images has significant clinical diagnosis values with its rapid image acquisition, low radiation dose and rich volume ***, they may suffer from class imbalance and redundant characteristics. To address these issues, the DSH-RSF-Lite approach is proposed with three core parts: 1) DSHNet is a few-shot augmentation approach that integrates spectral normalization into deep convolutional generative adversarial network and employs hinge adversarial loss to augment chest X-ray images for balancing positive and negative samples, 2) RSFNet is a residual network that incorporates spatial attention blocks and early-late feature fusion, enhancing the model focus on key regions within chest X-ray images meanwhile enriching overall information representation, 3) RSF-Lite is a lightweight model that employs geometric median-based pruning strategy to eliminate redundant filters in RSFNet, significantly reducing model parameters and computational complexity. Experimental results on the chest X-ray 2017 dataset demonstrate that: 1) our proposed DSHNet achieves Fréchet Inception Distance of 36.92 and Kernel Inception Distance of 0.03 for generating chest X-ray images, outperforming three classical GAN-based approaches, 2) our proposed DSH-RSFNet achieves accuracy, precision, recall and F1-score of 95.51%, 95.15%, 95.30% and 95.22%, surpassing both baseline and recent CNN-based approaches, 3) compared to DSH-RSFNet, our proposed DSH-RSF-Lite approach obtains a significant decrease in model parameters, storage space, floating point operations and latency by more than 68.20%, 67.72%, 69.46% and 22.68%, while it has only 0.64%, 0.14%, 1.28% and 0.75% reduction in accuracy, precision, recall and F1-score, respectively. Extensive comparative experiments validate the effectiveness of our proposed DSH-RSF-Lite approach, highlighting its efficiency in augmenting chest X-ray images, improving the performance of pneumonia classification

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Designing Quantum-Safe Lattice-Based Multi-Authority CP-ABE Scheme for Blockchain-Enabled IoT-Based Consumer Healthcare Electronics

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Bagchi, Prithwi Bisht, Abhishek Das, Ashok Kumar Saxena, Neetesh Hossain, M. Shamim International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500 032 India Department of Computer Science and Engineering College of Informatics Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of Cardiff University School of Computer Science and Informatics CardiffCF24 4AG United Kingdom King Saud University College of Computer and Information Sciences Department of Software Engineering Riyadh13273 Saudi Arabia

Despite edge computing reducing communication delays associated with cloud computing, privacy concerns remain a significant challenge when sharing data from edge-based consumer electronics (CE) or Internet-of-Things (IoT) devices. Ciphertext policy attribute-based encryption (CP-ABE) is a cryptographic tool that facilitates intricate and refined access control. It can deliver more flexible, secure, compact, and effective access control policies for the cloud data. In the case of a conventional CP-ABE scheme, the keys can only be issued and disseminated by a trusted central authority (CA). However, if the CA is compromised, the entire system becomes more susceptible to assaults or failures, which leads to a single-point failure. In this article, we propose a Ring-Learning with Errors (Ring-LWE)-based MA-CP-ABE scheme that is effectively resolved by the multi-authority CP-ABE (MA-CP-ABE), and it ensures the security against quantum attacks. The threshold secret sharing by Shamir and the Lagrange interpolation formula are applied in the key-generation and decryption procedures of the proposed scheme, which make it easier to segment and restore the private keys. The proposed scheme is implemented in the CE-enabled IoT-based smart healthcare applications using the blockchain technology as a secure storage. A detailed comparative study, security analysis and experimental results with the existing relevant schemes shows that the proposed scheme exhibits superior security and better efficiency as compared to other schemes, demonstrating its feasibility in practical IoT-based healthcare applications. © 2025 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

A Formal Approach for Traceability Preservation in software Development Process 41st

A Formal Approach for Traceability Preservation in Softwar...

引用

41st National Conference of Theoretical Computer Science, NCTCS 2023

作者： Wen, Hao Wu, Jinzhao Jiang, Jianmin Li, Jianqing Hong, Zhong Chengdu Institute of Computer Applications Chinese Academy of Sciences Chengdu China University of Chinese Academy of Sciences Beijing China College of Software Engineering Chengdu University of Information Technology Chengdu China College of Mathematics and Informatics Fujian Normal University Fuzhou China

ISBN: (纸本)9789819977420

Traceability is the ability to trace the usage of artifacts during the software lifecycle process. Though the benefits of establishing a traceability software system have been widely recognized, it is difficult to be applied well in actual development. In this paper, we propose a new method for traceability preservation which may be used in the practical software development process. A formal model for the traceability of software artifacts is first presented, which consists of variable traceability relations, classification and version number controls. We then present the composition, restriction and refinement operations in the software development process. Next, the preservation of traceability under these three operations is discussed respectively. To demonstrate the effectiveness of our approach, we finally develop a prototype tool named Formalized software Management System (FSMS). © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Formal methods

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：