检索结果-内蒙古大学图书馆

Correction to: Consistent Prompt Tuning for Generalized Category Discovery (International Journal of Computer Vision, (2025), 10.1007/s11263-024-02343-w)

引用

International Journal of Computer Vision 2025年 1-10页

作者： Yang, Muli Yin, Jie Gu, Yanan Deng, Cheng Zhang, Hanwang Zhu, Hongyuan Singapore Singapore School of Electronic Engineering Xidian University Xi’an China Norinco Group Testing and Research Institute Xi’an China College of Computing and Data Science Nanyang Technological University Singapore Singapore

The original publication of this article was published with several errors and has been corrected as follows. In the Section 4.3.1, the hyperlink for the Section 5 citation was missing and has been included. In Table 6, the significance ‘Reimplemented using CLIP’s image encoder’ was incorrectly provided for the method ‘CPT (Ours) and has been removed. In Table 12, the method name was incorrectly listed as ‘CLIP-GC’ but should read as ‘CLIP-GCD’. Additionally, the significance ‘Reimplemented using (Open/Meta) CLIP’s image encoder’ was missing for the method ‘CLIP-GCD’ and has been included. In Table 15, the incorrect significance ‘Reimplemented using CLIP’s image encoder’ was provided for the methods GCD (2022a), SimGCD (2023) and GPC (2023). This should be removed and the correct significance ‘Training with estimated category number’ has been included. In Table 22, the species "andrias acropora acuminata (staghorn coral)" was missing and has been included before the species "andrias davidianus (chinese giant salamander)." For completeness and transparency, the old incorrect and the corrected versions of Tables are displayed below. The original article has been corrected. Incorrect Table 6: GCD accuracy (%) in the customized setting on NICO dataset dataset → NICO-10 NICO-33 NICO-100 Method ↓ All Old New All Old New All Old New GCD (2022a) 95.1 97.3 94.0 38.6 58.4 25.1 48.0 67.0 39.1 PromptCAL (2023b) 89.6 80.9 93.6 30.5 42.4 22.5 45.3 53.4 41.5 SimGCD (2023) 97.3 97.0 97.4 45.9 67.7 46.3 65.1 37.4 PIM (2023) 96.4 97.2 96.0 42.2 67.6 24.9 49.5 67.5 41.0 GCD† 98.0 39.3 65.0 21.8 51.6 54.5 PromptCAL† 97.5 97.1 29.2 41.8 20.6 48.9 64.4 41.7 SimGCD† 97.5 46.6 29.1 69.4 44.6 PIM† 97.5 97.0 71.8 50.0 39.2 CPT (Ours)† 98.5 Bold value indicates the best results and underlined value indicates the second best results †Reimplemented using CLIP’s image encoder Corrected Table 6: GCD accuracy (%) in the customized setting on NICO dataset dataset → NICO-10 NICO-33 NICO-100 Method ↓

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robotic Cognitive Behavioural Therapy: rCBT 16th

Robotic Cognitive Behavioural Therapy: rCBT

引用

16th International Conference on Social Robotics, ICSR + BioMed 2024

作者： Samani, Hooman Zaraki, Abolfazl Davies, Daisy-Rose Fernando, Owen Noel Newton Creative Computing Institute University of the Arts London London United Kingdom and Robotics Research Group University of Hertfordshire Hatfield United Kingdom School of Engineering Computing and Mathematics University of Plymouth Plymouth United Kingdom College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9789819789627

This paper introduces Robotic Cognitive Behavioural Therapy (rCBT) as a novel approach to overcoming the limitations of traditional Cognitive Behavioural Therapy (CBT) in treating emotional and psychological issues. After a brief overview of CBT and its inherent challenges, this paper explores the innovative application of physical robots in therapy, building on the success of technology-based CBT methods that have effectively treated various mental health conditions. The proposed rCBT solution is a compact, portable, and cost-effective 3D-printed robot designed to aid individuals with anxiety or depression. This robot includes interactive features such as a diary, health questionnaires, daily mood monitoring, to-do lists, mindfulness exercises, and a crisis helpline, enabling users to track their emotional states and activities. These functions support healthcare professionals and users in identifying emotional patterns and triggers. The robot can monitor physiological signals like heart rate. This research aims to enhance the accessibility and effectiveness of CBT, suggesting that rCBT could significantly broaden the therapy’s reach and improve mental health outcomes for a larger population. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation 31

Debate-to-Write: A Persona-Driven Multi-Agent Framework for ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Hu, Zhe Chan, Hou Pong Li, Jing Yin, Yu Department of Computing The Hong Kong Polytechnic University Hong Kong DAMO Academy Alibaba Group China Research Centre for Data Science & Artificial Intelligence Hong Kong Department of Computer and Data Sciences Case Western Reserve University United States

ISBN: (纸本)9798891761964

Writing arguments is a challenging task for both humans and machines. It entails incorporating high-level beliefs from various perspectives on the topic, along with deliberate reasoning and planning to construct a coherent narrative. Current language models often generate outputs autoregressively, lacking explicit integration of these underlying controls, resulting in limited output diversity and coherence. In this work, we propose a persona-based multi-agent framework for argument writing. Inspired by the human debate, we first assign each agent a persona representing its high-level beliefs from a unique perspective, and then design an agent interaction process so that the agents can collaboratively debate and discuss the idea to form an overall plan for argument writing. Such debate process enables fluid and nonlinear development of ideas. We evaluate our framework on argumentative essay writing. The results show that our framework generates more diverse and persuasive arguments by both automatic and human evaluations. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Virtualizing Next-Generation Programmable Networks: Techniques, Use Cases, and Promising Future Directions

引用

IEEE Network 2025年第3期39卷 148-155页

作者： Chen, Xiang Du, Hongyang Liu, Wenjing Liu, Hongyan Zhang, Jianshan Yang, Xu Zhang, Dong Wu, Chunming Liu, Xuan Niyato, Dusit Zhejiang University College of Computer Science and Technology Hangzhou310027 China The University of Hong Kong Department of Electrical and Electronic Engineering Pokfulam Hong Kong Zhejiang Media Group Hangzhou310005 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Data Science Fuzhou350108 China Fuzhou University College of Computer and Data Science Fuzhou350108 China Yangzhou University College of Information Engineering College of Artificial Intelligence Yangzhou225009 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore

For decades, network virtualization plays a crucial role in modern networks, e.g., 6G mobile networks: tenants construct arbitrary virtual networks on the same physical network. However, production networks are becoming programmable and need more ways of network configurations. So prior techniques like SDN hypervisors are deprecated since they cannot configure programmable networks. In response, a new category of network virtualization techniques has emerged recently to virtualize programmable networks, i.e., programmable network hypervisors (PNHs). This article first reviews this trend to comprehensively survey PNHs. To understand their benefits, we build a testbed with hardware switches and sophisticated topologies. Our testbed experiments stress-test hypervisors and demonstrate that they outperform prior works with higher acceptance ratios of virtual networks under large-scale scenarios and heavy loads. Finally, we highlight the open issues of these techniques to shed light on the future directions in this promising topic. © 1986-2012 IEEE.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Q-Rung Orthopair Fuzzy Sets-Enhanced FMEA for COVID-19 Risk Assessment

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第1期49卷 81-92页

作者： Abdullah, Lazim Awang, Noor Azzah Qiyas, Muhammad Special Interest Group of Modelling and Data Analytics Faculty of Computer Science and Mathematics Universiti Malaysia Terengganu Kuala Nerus21030 Malaysia College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Department of Mathematics Riphah International University Failsabad Campus Pakistan

Failure Modes and Effects Analysis (FMEA) is a widely used tool for risk analysis, primarily to identify risk factors affecting system quality. Due to the limitations of the traditional FMEA model, several recent models incorporating advanced fuzzy set extensions have been developed to enhance the reliability of risk assessment outcomes. However, most of these models limit expert flexibility in expressing preferences and often overlook the impact of unequal expert weights and the stability of risk ranking results. This study introduces a new FMEA model based on Q-Rung Orthopair Fuzzy Sets (Q-ROFSs), termed Q-ROFSs-FMEA. Q-ROFSs, an extension of intuitionistic fuzzy sets, introduce a new linguistic term. The Q-ROFSs-FMEA model considers the unequal weights of experts, enabling a dynamic representation of expert preferences. These weights and the linguistic evaluation of risk factors are integrated through an aggregation operator, facilitating consensus among experts. The model is applied to a case study on COVID-19 risk factors, revealing that ‘older age’ (risk priority number 0.000012) is the highest risk factor, while ‘gender’ (risk priority number -0.0037) is the lowest. It is found that the ranking of risk factors determined by the Q-ROFSs-FMEA model is obtained as FM1 FM3 FM6 FM4 FM5 FM7 FM8 FM2 . Furthermore, a comparative analysis indicates consistent ranking results across different models, demonstrating the reliability of the proposed model. The case study and comparative analysis validate the effectiveness and applicability of the Q-ROFSsbased risk assessment model. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Failure modes

来源：评论

学校读者我要写书评

暂无评论

CONTINUAL LEARNING WITH EMBEDDING LAYER SURGERY AND TASK-WISE BEAM SEARCH USING WHISPER

arXiv

引用

arXiv 2025年

作者： Kwok, Chin Yuen Yip, Jia Qi Chng, Eng Siong College of Computing and Data Science Nanyang Technological University Singapore Alibaba Group Singapore

Current Multilingual ASR models only support a fraction of the world’s languages. Continual Learning (CL) aims to tackle this problem by adding new languages to pre-trained models while avoiding the loss of performance on existing languages, also known as Catastrophic Forgetting (CF). However, existing CL methods overlook the adaptation of the token embedding lookup table at the decoder, despite its significant contribution to CF. We propose Embedding Layer Surgery where separate copies of the token embeddings are created for each new languages, and one of the copies is selected to replace the old languages embeddings when transcribing the corresponding new language. Unfortunately, this approach means LID errors also cause incorrect ASR embedding selection. Our Task-wise Beam Search allows self-correction for such mistakes. By adapting Whisper to 10 hours of data for each of 10 unseen languages from Common Voice, results show that our method reduces the Average WER (AWER) of pre-trained languages from 14.2% to 11.9% compared with Experience Replay, without compromising the AWER of the unseen languages. © 2025, CC BY-NC-ND.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

Machine learning approach to identity resolution for criminal profiling

引用

Journal of Cyber Security Technology 2025年

作者： Kazemian, Hassan Shrestha, Subeksha AI and Data Science Research Group School of Computing and Digital Media London Metropolitan University London United Kingdom

A common dilemma when working on criminal data is that often people manipulate their details to disguise themselves and hide their identities which leads to creating ambiguous and false identities. Deep Neural Network (DNN) is applied to work well on fraudulent and imbalanced data. Two subcategories of DNN, the Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) with Python libraries such as TensorFlow and Keras are applied to the dataset for the detection of suspects with false identities to assist the process of analytical investigation by law enforcement agencies. Upon application of this approach to the anonymized policing dataset from SPIRIT Project funded by European Union’s Horizon, 5 main suspects with false identities were identified out of 23 targets on 39 million records. As working on criminal data is quite sensitive so to avoid data leakage while training and testing the data, K-fold validation has been applied. Furthermore, cascading both MLP and LSTM models on the policing dataset resulted in improved model prediction and accuracy compared to using each model individually. The cascaded model notably reduced false predictions for the recurring criminal patterns such as age-specific trends and most prevalent crime activities. © 2025 Informa UK Limited, trading as Taylor & Francis group.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Who Should I Trust? A Visual Analytics Approach for Comparing Net Load Forecasting Models

Who Should I Trust? A Visual Analytics Approach for Comparin...

引用

2025 IEEE PES Grid Edge Technologies Conference and Exposition, Grid Edge 2025

作者： Bhattacharjee, Kaustav Kundu, Soumya Chakraborty, Indrasis Dasgupta, Aritra New Jersey Institute of Technology Department of Data Science United States Pacific Northwest National Laboratory Optimization and Control Group United States Lawrence Livermore National Laboratory Center for Applied Scientific Computing United States

ISBN: (纸本)9798350352528

Net load forecasting is crucial for energy planning and facilitating informed decision-making regarding trade and load distributions. However, evaluating forecasting models' performance against benchmark models remains challenging, thereby impeding experts' trust in the model's performance. In this context, there is a demand for technological interventions that allow scientists to compare models across various timeframes and solar penetration levels. This paper introduces a visual analytics-based application designed to compare the performance of deep-learning-based net load forecasting models with other models for probabilistic net load forecasting. This application employs carefully selected visual analytic interventions, enabling users to discern differences in model performance across different solar penetration levels, dataset resolutions, and hours of the day over multiple months. We also present observations made using our application through a case study, demonstrating the effectiveness of visualizations in aiding scientists in making informed decisions and enhancing trust in net load forecasting models. © 2025 IEEE.

关键词： AI/ML net load forecasting visual analytics

来源：评论

学校读者我要写书评

暂无评论

TrapNet: Model Inversion Defense via Trapdoor

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4469-4483页

作者： Ma, Wanlun Wang, Derui Song, Yiliao Xue, Minhui Wen, Sheng Li, Zhengdao Xiang, Yang Swinburne University of Technology School of Science Computing and Engineering Technologies MelbourneVIC3122 Australia Cybersecurity and Quantum Systems Group CSIRO’s Data61 EveleighNSW2015 Australia The University of Adelaide School of Computer and Mathematical Sciences AdelaideSA5005 Australia Guangzhou University School of Artificial Intelligence Guangzhou511370 China

Model inversion (MI) attacks, for which effective defense strategies are still lacking, pose significant risks to privacy by reconstructing private training data through access to well-trained classifiers. Addressing this concern, this study introduces TrapNet, designed to defend against advanced MI attacks while maintaining good model utility. TrapNet intentionally injects trapdoors into the classification manifold of the protected target model. In this way, TrapNet can effectively mislead MI attack optimization. Specifically, TrapNet leverages a conditional GAN (cGAN) trained on the private dataset to generate diverse and realistic trapdoor samples. In addition, we propose a graph-matching self-obfuscation strategy and an entropy regularization technique to optimize trapdoor injection while preserving model utility. Compared to the existing defense, TrapNet can provide universal protection to all target classes without access to any auxiliary public data. Extensive experiments on CelebA, VGG-Face, and VGG-Face2 datasets demonstrate TrapNet’s superior performance over existing defenses, including the most advanced NetGuard and BiDO, against state-of-the-art model inversion attacks, i.e., PLG-MI, LOMMA, and Plug&Play. © 2005-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Discovering multi-agent systems for resource-centric business process simulation

引用

Process science 2025年第1期2卷 1-26页

作者： Kirchdorfer, Lukas Blümel, Robert Kampik, Timotheus van der Aa, Han Stuckenschmidt, Heiner SAP Signavio Walldorf Germany Data and Web Science Group University of Mannheim Mannheim Germany Faculty of Computer Science University of Vienna Vienna Austria Department of Computing Science Umeå University Umeå Sweden

Business process simulation (BPS) is a powerful tool for estimating process performance across different scenarios, offering critical support for organizational process redesign and optimization. Traditional BPS approaches predominantly rely on a control-flow-first perspective by enriching a process model with simulation parameters. While these approaches seem suitable for capturing centrally orchestrated processes, such as those managed by workflow systems, they fall short of accurately reflecting real-world processes characterized by decentralized decision-making and distinct resource behaviors. To overcome this limitation, we propose AgentSimulator, a resource-first BPS approach that discovers a multi-agent system from an event log. By modeling the distinct behaviors and interaction patterns of individual resources, AgentSimulator effectively simulates the underlying process. Our approach automatically identifies whether resource behavior is rather orchestrated or autonomous, adapting to the specific decision-making structure of the process. Experimental results reveal that AgentSimulator achieves state-of-the-art simulation accuracy while ensuring high adaptability to various process types.

关键词：

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：