检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jiang, Kai Huang, Jiaxing Xie, Weiying Lei, Jie Li, Yunsong Shao, Ling Lu, Shijian State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China S-lab School of Computer Science and Engineering Nanyang Technological University Singapore UCAS-Terminus AI Lab University of Chinese Academy of Sciences Beijing China School of Electrical and Data Engineering The University of Technology Sydney Australia

Large-vocabulary object detectors (LVDs) aim to detect objects of many categories, which learn super objectness features and can locate objects accurately while applied to various downstream data. However, LVDs often struggle in recognizing the located objects due to domain discrepancy in data distribution and object vocabulary. At the other end, recent vision-language foundation models such as CLIP demonstrate superior open-vocabulary recognition capability. This paper presents KGD, a Knowledge Graph Distillation technique that exploits the implicit knowledge graphs (KG) in CLIP for effectively adapting LVDs to various downstream domains. KGD consists of two consecutive stages: 1) KG extraction that employs CLIP to encode downstream domain data as nodes and their feature distances as edges, constructing KG that inherits the rich semantic relations in CLIP explicitly;and 2) KG encapsulation that transfers the extracted KG into LVDs to enable accurate cross-domain object classification. In addition, KGD can extract both visual and textual KG independently, providing complementary vision and language knowledge for object localization and object classification in detection tasks over various downstream domains. Experiments over multiple widely adopted detection benchmarks show that KGD outperforms the state-of-the-art consistently by large margins. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

How Deep is Love in LLMs’ Hearts? Exploring Semantic Size in Human-like Cognition

arXiv

引用

arXiv 2025年

作者： Yao, Yao Yang, Yifei Ma, Xinbei Yang, Dongjie Zhang, Zhuosheng Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan University Wuhan430072 China

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival human capabilities in various domains, we are presented with a unique testbed to investigate human cognition through a new lens. Among the many facets of cognition, one particularly crucial aspect is the concept of semantic size—the perceived magnitude of both abstract and concrete words or concepts. This study seeks to investigate whether LLMs exhibit similar tendencies in understanding semantic size, thereby providing insights into the underlying mechanisms of human cognition. We begin by exploring metaphorical reasoning, comparing how LLMs and humans associate abstract words with concrete objects of varying sizes. Next, we examine LLMs’ internal representations to evaluate their alignment with human cognitive processes. Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding, suggesting that real-world, multi-modal experiences are similarly vital for human cognitive development. Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario. The results show that multi-modal LLMs are more emotionally engaged in decision-making, but this also introduces potential biases, such as the risk of manipulation through clickbait headlines. Ultimately, this study offers a novel perspective on how LLMs interpret and internalize language, from the smallest concrete objects to the most profound abstract concepts like ‘love’. The insights gained not only improve our understanding of LLMs but also provide new avenues for exploring the cognitive abilities that define human intelligence. Our code and dataset is publicly available at https://***/Zoeyyao27/LLM-Semantic-Size-Understanding. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ZuantuSet: A Collection of Historical Chinese Visualizations and Illustrations 25

ZuantuSet: A Collection of Historical Chinese Visualizations...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Mei, Xiyao Zhang, Yu Yang, Chaofan Shi, Rui Yuan, Xiaoru Peking University Beijing China University of Oxford Oxford United Kingdom National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Department of Computer Science University of Oxford United Kingdom Center for Research on Ancient Chinese History Peking University China National Engineering Laboratory for Big Data Analysis and Application Peking University China PKU-WUHAN Institute for Artificial Intelligence China

ISBN: (纸本)9798400713941

Historical visualizations are a valuable resource for studying the history of visualization and inspecting the cultural context where they were created. When investigating historical visualizations, it is essential to consider contributions from different cultural frameworks to gain a comprehensive understanding. While there is extensive research on historical visualizations within the European cultural framework, this work shifts the focus to ancient China, a cultural context that remains underexplored by visualization researchers. To this aim, we propose a semi-automatic pipeline to collect, extract, and label historical Chinese visualizations. Through the pipeline, we curate ZuantuSet, a dataset with over 71K visualizations and 108K illustrations. We analyze distinctive design patterns of historical Chinese visualizations and their potential causes within the context of Chinese history and culture. We illustrate potential usage scenarios for this dataset, summarize the unique challenges and solutions associated with collecting historical Chinese visualizations, and outline future research directions. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Flow visualization

来源：评论

学校读者我要写书评

暂无评论

Pre-classification Supporting Reasoning for Document-level Relation Extraction 21

Pre-classification Supporting Reasoning for Document-level R...

引用

Proceedings of the 10th International Joint Conference on Knowledge Graphs

作者： Jiehao Zhao Guiduo Duan Tianxi Huang School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Computer Science and Engineering Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province University of Electronic Science and Technology of China China Department of Fundamental Courses Chengdu Textile College China

ISBN: (纸本)9781450395656

The document-level relation extraction task aims to extract relational triples from a document consisting of multiple sentences. Most previous models focus on modeling the dependency between the entities and neglect the reasoning mechanism. Some other models construct paths implicitly between co-sentence entities to find semantic relations. However, they ignore that there are interactions between different triples, especially some triples play an import role in predicting others. In this short research paper, we propose a new two stage framework PCSR(Pre-classification Supporting Reasoning) which captures the interactions between triples and utilizes these information for reasoning. Specifically, we make a pre-classification for each entity pair in the first stage. Then we aggregate the embeddings of predicted triples to enhance entity representation and make a new classification. Since the second classification could find triples missed in the first stage, we take the result as the supplement of the prior one. Experiments on DocRED show that our method achieves an F1 score of 62.11. Compared with the previous state-of-the-art model, our model increase by 0.81 on the test set, which demonstrates the effectiveness of our reasoning mechanism.

关键词： BERT Information Extraction Document-level Relation Extraction Reasoning Mechanism

来源：评论

学校读者我要写书评

暂无评论

GoMORE: Global Model Reuse for Resource-Constrained Wireless Federated Learning

arXiv

引用

arXiv 2023年

作者： Yao, Jiacheng Yang, Zhaohui Xu, Wei Chen, Mingzhe Niyato, Dusit Southeast University Nanjing210096 China The Zhejiang Lab Hangzhou311121 China The College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The School of Computer Science and Engineering Nanyang Technological University 308232 Singapore

Due to the dynamics of wireless environment and limited bandwidth, wireless federated learning (FL) is challenged by frequent transmission errors and incomplete aggregation from devices. In order to overcome these challenges, we propose a Global MOdel REuse strategy (GoMORE) that reuses the outdated global model to replace the local model parameters once a transmission error occurs. We analytically prove that the proposed GoMORE is strictly superior over the existing strategy, especially at low signal-to-noise ratios (SNRs). In addition, based on the derived expression of weight divergence, we further optimize the number of participating devices in the model aggregation to maximize the FL performance with limited communication resources. Numerical results verify that the proposed GoMORE successfully approaches the performance upper bound by an ideal transmission. It also mitigates the negative impact of non-independent and non-identically distributed (non-IID) data while achieving over 5 dB reduction in energy consumption. Copyright © 2023, The Authors. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: Adaptive rate and modulation scheme for M2M communication using quantum optical and 5G communication

引用

Optical and Quantum Electronics 2024年第10期56卷 1-2页

作者： Chillakuru, Prameela Devi Vignesh, G. D. Maheswari, S. Sabeenian, R. S. Mouleswararao, B. Markkandan, S. Artificial Intelligence and Data Science Velammal Institute of Technology Panchetti Ponneri Chennai India Department of ECE St Joseph’s College of Engineering Chennai India Department of ECE Panimalar Engineering College Chennai India Department of ECE Sona College of Technology Salem India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur dt India School of Electronics Engineering (SENSE) Vellore Institute of Technology Chennai India

来源：评论

学校读者我要写书评

暂无评论

IoT data analytic algorithms on edge-cloud infrastructure:A review

引用

Digital Communications and Networks 2023年第6期9卷 1486-1515页

作者： Abel E.Edje M.S.Abd Latiff Weng Howe Chan School of Computing Faculty of EngineeringUniversiti Teknologi Malaysia81310SkudaiJohorMalaysia Department of Computer Science Delta State UniversityAbrakaP.M.B 01 AbrakaDelta StateNigeria UTM Big Data Centre Ibnu Sina Institute of Scientific and Industrial ResearchUniversiti Teknologi Malaysia81310SkudaiJohorMalaysia

The adoption of Internet of Things(IoT)sensing devices is growing rapidly due to their ability to provide realtime ***,it is constrained by limited data storage and processing *** offloads its massive data stream to edge devices and the cloud for adequate storage and *** further leads to the challenges of data outliers,data redundancies,and cloud resource load balancing that would affect the execution and outcome of data *** paper presents a review of existing analytics algorithms deployed on IoT-enabled edge cloud infrastructure that resolved the challenges of data outliers,data redundancies,and cloud resource load *** review highlights the problems solved,the results,the weaknesses of the existing algorithms,and the physical and virtual cloud storage servers for resource load *** addition,it discusses the adoption of network protocols that govern the interaction between the three-layer architecture of IoT sensing devices enabled edge cloud and its prevailing challenges.A total of 72 algorithms covering the categories of classification,regression,clustering,deep learning,and optimization have been *** classification approach has been widely adopted to solve the problem of redundant data,while clustering and optimization approaches are more used for outlier detection and cloud resource allocation.

关键词： Internet of things Cloud platform Edge Analytic algorithms Processes Network communication protocols

来源：评论

学校读者我要写书评

暂无评论

Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams

arXiv

引用

arXiv 2022年

作者： Chen, Yongrui Guo, Xinnan Wu, Tongtong Qi, Guilin Li, Yang Dong, Yang School of Computer Science and Engineering Southeast University China Department of Data Science & AI Monash University Australia Alibaba Group China Ant Group China

Conventional text-to-SQL studies are limited to a single task with a fixed-size training and test set. When confronted with a stream of tasks common in real-world applications, existing methods struggle with the problems of insufficient supervised data and high retraining costs. The former tends to cause overfitting on unseen databases for the new task, while the latter makes a full review of instances from past tasks impractical for the model, resulting in forgetting of learned SQL structures and database schemas. To address the problems, this paper proposes integrating semi-supervised learning (SSL) and continual learning (CL) in a stream of text-to-SQL tasks and offers two promising solutions in turn. The first solution VANILLA is to perform self-training, augmenting the supervised training data with predicted pseudo-labeled instances of the current task, while replacing the full volume retraining with episodic memory replay to balance the training efficiency with the performance of previous tasks. The improved solution SFNET takes advantage of the intrinsic connection between CL and SSL. It uses in-memory past information to help current SSL, while adding high-quality pseudo instances in memory to improve future replay. The experiments on two datasets shows that SFNET outperforms the widely-used SSL-only and CL-only baselines on multiple metrics. © 2022, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

MMFNet: A Multi-modal and Multi-attention Fusion Network for Multi-task Skin Disease Classification

MMFNet: A Multi-modal and Multi-attention Fusion Network for...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xinlei Zhu Pengjiang Qian Chuang Wang Li Liu Ming Gao Weiwei Cai Eddie Yin-Kwee Ng School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Engineering Research Center of Intelligent Technology for Healthcare Ministry of Education Jiangnan University Wuxi China Big Data Center Affiliated Hospital of Jiangnan University Wuxi China School of Mechanical and Aerospace Engineering Nanyang Technological University Nanyang Singapore

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Skin diseases rank among the most prevalent ailments in humans, which underscores the critical importance of early detection and diagnosis. Considering clinical practice, the integration of information from various modalities holds significant potential to enhance diagnostic accuracy and precision. In this study, we propose a multi-modal and multi-attention fusion network for multi-task skin disease classification. We initially devise the Shifted Window Cross-attention Fusion (SWCF) module based on the shifted window self-attention mechanism, leveraging the advantages of the attention mechanism to learn the correlations between different modalities and fully integrate multi-modal features. Subsequently, taking into account the heterogeneity of the data, we employ the Heterogeneous data Cross-attention Fusion (HDCF) module using the idea of information decoupling and separation processing to integrate image and text data. Additionally, we suggest the Dynamic Loss Weight Allocation (DLWA) method for multi-task learning to refine the training procedure. We confirm the superiority of the proposed method on the publicly available multi-modal skin lesion dataset, Derm7pt. The average accuracy of multi-modal skin disease classification is 79.14%, surpassing the current state-of-the-art methods.

关键词： Training Attention mechanisms Accuracy Fuses Multitasking Dynamic scheduling Skin Resource management Lesions Diseases

来源：评论

学校读者我要写书评

暂无评论

InstruPro: Instrumenting Programmable Logic Controller (PLC) based on Model Checking

InstruPro: Instrumenting Programmable Logic Controller (PLC)...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Abdullah Al Farooq Manash Sarker School of Computing and Data Science Wentworth Institute of Technology Boston MA USA Department of Computer and Communication Engineering Potuakhali Science and Technology University Potuakhali Bangladeshi

ISBN: (纸本)9781665487696

Programmable Logic Controller (PLC) suffers from various types of attacks due to misconfiguration in its logic system. These misconfigurations cannot be found by looking at the logic/rules only. Therefore, we propose a methodology where temporal logic is used to find the misconfigurations in the subsequent rules. Our framework is capable of finding the codes in PLC that are responsible for abnormal behavior in PLC. Having accomplished that, an automated approach to instrument the code. We run our methodology on some real world PLC program applications and found that our approach can eradicate a good number of abnormal behaviors successfully.

关键词： Codes Instruments Programmable logic devices Model checking Control systems Behavioral sciences Security

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：