检索结果-内蒙古大学图书馆

15th Asian Conference on computer Vision, ACCV 2020

作者： Han, Wenhui Ren, Xinlin Lin, Hangyu Fu, Yanwei Xue, Xiangyang School of Data Science Computer Science and MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9783030695439

This paper studies the recognition of oracle character, the earliest known hieroglyphs in China. Essentially, oracle character recognition suffers from the problem of data limitation and imbalance. Recognizing the oracle characters of extremely limited samples, naturally, should be taken as the few-shot learning task. Different from the standard few-shot learning setting, our model has only access to large-scale unlabeled source Chinese characters and few labeled oracle characters. In such a setting, meta-based or metric-based few-shot methods are failed to be efficiently trained on source unlabeled data;and thus the only possible methodologies are self-supervised learning and data augmentation. Unfortunately, the conventional geometric augmentation always performs the same global transformations to all samples in pixel format, without considering the diversity of each part within a sample. Moreover, to the best of our knowledge, there is no effective self-supervised learning method for few-shot learning. To this end, this paper integrates the idea of self-supervised learning in data augmentation. And we propose a novel data augmentation approach, named Orc-Bert Augmentor pre-trained by self-supervised learning, for few-shot oracle character recognition. Specifically, Orc-Bert Augmentor leverages a self-supervised BERT model pre-trained on large unlabeled Chinese characters datasets to generate sample-wise augmented samples. Given a masked input in vector format, Orc-Bert Augmentor can recover it and then output a pixel format image as augmented data. Different mask proportion brings diverse reconstructed output. Concatenated with Gaussian noise, the model further performs point-wise displacement to improve diversity. Experimentally, we collect two large-scale datasets of oracle characters and other Chinese ancient characters for few-shot oracle character recognition and Orc-Bert Augmentor pre-training. Extensive experiments on few-shot learning demonstrate the effe

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects

arXiv

引用

arXiv 2024年

作者： Li, Na Zhou, Chunyi Gao, Yansong Chen, Hui Fu, Anmin Zhang, Zhi Yu, Shui School of Cyberspace Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Data61 CSIRO CanberraACT2601 Australia Department of Computer Science and Software Engineering University of Western Australia PerthWA6009 Australia School of Computer Science University of Technology Sydney SydneyNSW2007 Australia

Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. data users have been endowed with the 'right to be forgotten' of their data. In the course of machine learning (ML), the forgotten right requires a model provider to delete user data and its subsequent impact on ML models upon user requests. Machine unlearning emerges to address this, which has garnered ever-increasing attention from both industry and academia. While the area has developed rapidly, there is a lack of comprehensive surveys to capture the latest advancements. Recognizing this shortage, we conduct an extensive exploration to map the landscape of machine unlearning including the (fine-grained) taxonomy of unlearning algorithms under centralized and distributed settings, debate on approximate unlearning, verification and evaluation metrics, challenges and solutions for unlearning under different applications, as well as attacks targeting machine unlearning. The survey concludes by outlining potential directions for future research, hoping to serve as a guide for interested scholars. Copyright © 2024, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Searching with Extended Guard and Pivot Loop

Searching with Extended Guard and Pivot Loop

引用

2021 Prague Stringology Conference, PSC 2021

作者： Pakalén, Waltteri Tarhio, Jorma Watson, Bruce W. Department of Computer Science Aalto University Finland Information Science Centre for AI Research School for Data-Science & Computational Thinking Stellenbosch University South Africa

ISBN: (纸本)9788001068694

We explore practical optimizations on comparison-based exact string matching algorithms. We present a guard test that compares q-grams between the pattern and the text before entering the match loop, and evaluate experimentally the benefit of optimization of this kind. As a result, the Brute Force algorithm gained most from the guard test, and it became faster than many other algorithms for short patterns. In addition, we present variations of a recent algorithm that uses a special skip loop where a pivot, a selected position of the pattern, is tested at each alignment of the pattern and in case of failure;the pattern is shifted based on the last character of the alignment. The variations include alternatives for the pivot and the shift function. We show the competitiveness of the new algorithm variations by practical experiments. © Czech Technical University in Prague, Czech Republic.

关键词： String searching algorithms

来源：评论

学校读者我要写书评

暂无评论

Contract-Inspired Contest Theory for Controllable Image Generation in Mobile Edge Metaverse

引用

IEEE Transactions on Mobile Computing 2025年

作者： Liu, Guangyuan Du, Hongyang Wang, Jiacheng Niyato, Dusit Kim, Dong In Nanyang Technological University College of Computing and Data Science Energy Research Institute @ NTU Interdisciplinary Graduate Program Singapore University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong Hong Kong Nanyang Technological University College of Computing and Data Science Singapore Sungkyunkwan University Department of Electrical and Computer Engineering Korea Republic of

The rapid advancement of immersive technologies has propelled the development of the Metaverse, where the convergence of virtual and physical realities necessitates the generation of high-quality, photorealistic images to enhance user experience. However, generating these images, especially through Generative Diffusion Models (GDMs), in mobile edge computing environments presents significant challenges due to the limited computing resources of edge devices and the dynamic nature of wireless networks. This paper proposes a novel framework that integrates contract-inspired contest theory, Deep Reinforcement Learning (DRL), and GDMs to optimize image generation in these resource-constrained environments. The framework addresses the critical challenges of resource allocation and semantic data transmission quality by incentivizing edge devices to efficiently transmit high-quality semantic data, which is essential for creating realistic and immersive images. The use of contest and contract theory ensures that edge devices are motivated to allocate resources effectively, while DRL dynamically adjusts to network conditions, optimizing the overall image generation process. Experimental results demonstrate that the proposed approach not only improves the quality of generated images but also achieves superior convergence speed and stability compared to traditional methods. This makes the framework particularly effective for optimizing complex resource allocation tasks in mobile edge Metaverse applications, offering enhanced performance and efficiency in creating immersive virtual environments. © 2002-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Noro: A Noise-Robust One-shot Voice Conversion System with Hidden Speaker Representation Capabilities

arXiv

引用

arXiv 2024年

作者： He, Haorui Song, Yuchen Wang, Yuancheng Li, Haoyang Zhang, Xueyao Wang, Li Huang, Gongping Chng, Eng Siong Wu, Zhizheng School of Data Science Chinese University of H ong Kong Shenzhen518172 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore School of Electronic Information Wuhan University Wuhan430072 China

One-shot voice conversion (VC) aims to alter the timbre of speech from a source speaker to match that of a target speaker using just a single reference speech from the target, while preserving the semantic content of the original source speech. Despite advancements in one-shot VC, its effectiveness decreases in real-world scenarios where reference speeches, often sourced from the internet, contain various disturbances like background noise. To address this issue, we introduce Noro, a Noise Robust One-shot VC system. Noro features innovative components tailored for VC using noisy reference speeches, including a dual-branch reference encoding module and a noise-agnostic contrastive speaker loss. Experimental results demonstrate that Noro outperforms our baseline system in both clean and noisy scenarios, highlighting its efficacy for real-world applications. Additionally, we investigate the hidden speaker representation capabilities of our baseline system by repurposing its reference encoder as a speaker encoder. The results shows that it is competitive with several advanced self-supervised learning models for speaker representation under the SUPERB settings, highlighting the potential for advancing speaker representation learning through one-shot VC task. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Redesign Incentives in Proof-of-Stake Ethereum: An Interdisciplinary Approach of Reinforcement Learning and Mechanism Design

Redesign Incentives in Proof-of-Stake Ethereum: An Interdisc...

引用

data-driven Optimization of Complex Systems (DOCS), International Conference on

作者： Xinyu Tian Zesen Zhuang Luyao Zhang Department of Computer Science Duke University Durham United States Pratt School of Engineering Duke University Durham United States Data Science Research Center and Social Science Division Duke Kunshan University Suzhou China

ISBN: (数字)9798350377842

ISBN: (纸本)9798350377859

The Merge changes Ethereum from Proof-of-Work (PoW) to the more secure and less energy-intensive Proof-of-Stake (PoS) mechanism. However, the existence of malicious valida tors still threatens the security of Ethereum, primarily through a discouragement attack. How can we redesign the incentive mech-anism in PoS Ethereum for a more secure blockchain? For this quest, we, for the first time, apply the cutting-edge reinforcement mechanism design method-an interdisciplinary approach at the intersection of reinforcement learning (RL) and mechanism design-to staking mechanism designs. We abstract a generalized staking mechanism as a game environment and implement an RL method for the blockchain as a mechanism designer to explore the optimal incentive design. Our reinforcement mechanism design outperforms the status quo in cultivating honest validators. Furthermore, we identify Advantage Actor-Critic (A2C) as the most efficient RL algorithm among the three alternatives, which intuitively performs better when the initial proportion of honest validator is larger. Our interdisciplinary approach of generalized abstraction could be adapted to analyze the incentive design in any PoS blockchain and beyond.

关键词： Proof of stake Mechanism design Reinforcement learning Games Proof of Work Security Complex systems Optimization

来源：评论

学校读者我要写书评

暂无评论

H-FLTN: A Privacy-Preserving Hierarchical Framework for Electric Vehicle Spatio-Temporal Charge Prediction

arXiv

引用

arXiv 2025年

作者： Marlin, Robert Jurdak, Raja Abuadbba, Alsharif School of Computer Science Queensland University of Technology Australia CSIRO’s Data61 Cyber Security Cooperative Research Centre Australia CSIRO’s Data61 Australia

The widespread adoption of Electric Vehicles (EVs) poses critical challenges for energy providers, particularly in predicting charging time (temporal prediction), ensuring user privacy, and managing resources efficiently in mobility-driven networks. This paper introduces the Hierarchical Federated Learning Transformer Network (H-FLTN) framework to address these challenges. H-FLTN employs a three-tier hierarchical architecture comprising EVs, community Distributed Energy Resource Management Systems (DERMS), and the Energy Provider data Centre (EPDC) to enable accurate spatio-temporal predictions of EV charging needs while preserving privacy. Temporal prediction is enhanced using Transformer-based learning, capturing complex dependencies in charging behavior. Privacy is ensured through Secure Aggregation, Additive Secret Sharing, and Peer-to-Peer (P2P) Sharing with Augmentation, which allow only secret shares of model weights to be exchanged while securing all transmissions. To improve training efficiency and resource management, H-FLTN integrates Dynamic Client Capping Mechanism (DCCM) and Client Rotation Management (CRM), ensuring that training remains both computationally and temporally efficient as the number of participating EVs increases. DCCM optimises client participation by limiting excessive computational loads, while CRM balances training contributions across epochs, preventing imbalanced participation. Our simulation results based on large-scale empirical vehicle mobility data reveal that DCCM and CRM reduce the training time complexity with increasing EVs from linear to constant. By mitigating key FL challenges including data heterogeneity, computational overhead, and bias H-FLTN provides a secure, resource-efficient solution for predicting EV charging behavior. Its integration into real-world smart city infrastructure enhances energy demand forecasting, resource allocation, and grid stability, ensuring reliability and sustainability in future mobility ec

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

RBDQ: A Reliable LLM-based Text-to-SQL System for Business data Queries 25

RBDQ: A Reliable LLM-based Text-to-SQL System for Business D...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Fenglin Bi Dongdong Cao Zhiyu Wang Yang Chen Fangliang Zhao Tao Hu Zhi Li Yanbin Zhang Wei Wang School of Data Science and Engineering East China Normal University Shanghai China ByteDance Inc Shanghai China School of Computer Science Fudan University Shanghai China and Shanghai Key Lab of Intelligent Information Processing Shanghai China

ISBN: (纸本)9798400713316

Using large language models (LLMs) to convert natural language (NL) into SQL simplifies data access for users by allowing them to use everyday language. However, business departments often distrust LLM-based text-to-SQL systems due to the probabilistic nature of SQL generation, which can result in incorrect but executable SQL queries caused by model hallucinations. This leads to significant concerns regarding the accuracy and reliability of the queried data. In this paper, we present RBDQ, a novel LLM-based text-to-SQL system designed to address the unique challenges of business data queries. RBDQ innovatively introduces the Hierarchical Metrics Query Method and integrates advanced Retrieval-Augmented Generation (RAG) methods along with a self-reflection mechanism to tackle these challenges. RBDQ effectively meets the requirements of business metric queries in real-world scenarios. Currently implemented in the Quality Assurance department at ByteDance, RBDQ has significantly improved operational efficiency and query flexibility. Our experiments demonstrate the system's effectiveness, achieving an Execution Accuracy of 96.20%.

关键词： business data queries

来源：评论

学校读者我要写书评

暂无评论

TOM2C: TARGET-ORIENTED MULTI-AGENT COMMUNICATION AND COOPERATION WITH THEORY OF MIND 10

TOM2C: TARGET-ORIENTED MULTI-AGENT COMMUNICATION AND COOPERA...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Wang, Yuanfei Zhong, Fangwei Xu, Jing Wang, Yizhou Center for Data Science Peking University China School of Artificial Intelligence Peking University China Center on Frontiers of Computing Studies School of Computer Science Peking University China Adv. Inst. of Info. Tech Peking University China China

Being able to predict the mental states of others is a key factor to effective social interaction. It is also crucial for distributed multi-agent systems, where agents are required to communicate and cooperate. In this paper, we introduce such an important social-cognitive skill, i.e. Theory of Mind (ToM), to build socially intelligent agents who are able to communicate and cooperate effectively to accomplish challenging tasks. With ToM, each agent is capable of inferring the mental states and intentions of others according to its (local) observation. Based on the inferred states, the agents decide "when" and with "whom" to share their intentions. With the information observed, inferred, and received, the agents decide their sub-goals and reach a consensus among the team. In the end, the low-level executors independently take primitive actions to accomplish the sub-goals. We demonstrate the idea in two typical target-oriented multi-agent tasks: cooperative navigation and multi-sensor target coverage. The experiments show that the proposed model not only outperforms the state-of-the-art methods on reward and communication efficiency, but also shows good generalization across different scales of the environment. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network-based image tamper detection with Error Level Analysis

Convolutional Neural Network-based image tamper detection wi...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Manjunatha S Swetha M D Rashmi S Ananda Kumar Subramanian Vinoth Kumar V Mallikarjuna Swamy S Department of Information Science and Engineering Global Academy of Technology Bengaluru India Department of Computer Science and Engineering BNM Institute of Technology Bengaluru India Department of Computer Science and Engineering (Data Science) Dayananda Sagar College of Engineering Bengaluru India Dept of Computational Intelligence School of Computer Science Engineering VIT – University Vellore India School of Computer Science Engineering and Information Systems VIT – University Vellore India Dept of Electronics and Communication Engineering JSS Academy of Technical Education Bengaluru India

Photography is the most important, powerful, and reliable means of expression. Today, digital images not only provide disinformation but also act as agents for secret communication. Users and editing professionals work with digital images for a variety of purposes. Images are often regarded as facts or proof of reality, so they are misleading and fake news or publications of any form that use images manipulated in a highly misleading way. To recognize image tampering needs multiple image data and a model that can handle all the pixels in the image. Furthermore, training the data more efficiently and needed flexibility support everyday use. Models based on Deep learning such as Convolutional Neural Networks with error level analysis (ELA) are the perfect solution.

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：