检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Benavent-Lledo, Manuel Mulero-Perez, David Ortiz-Perez, David Garcia-Rodriguez, Jose Department of Computer Technology University of Alicante Spain ValgrAI - Valencian Graduate School and Research Network of Artificial Intelligence Valencia Spain Institute of Informatics Research University of Alicante Alicante Spain

Detecting actions as they occur is essential for applications like video surveillance, autonomous driving, and human-robot interaction. Known as online action detection, this task requires classifying actions in streaming videos, handling background noise, and coping with incomplete actions. Transformer architectures are the current state-of-the-art, yet the potential of recent advancements in computer vision, particularly vision-language models (VLMs), remains largely untapped for this problem, partly due to high computational costs. In this paper, we introduce TOAD: a Text-driven Online Action Detection architecture that supports zero-shot and few-shot learning. TOAD leverages CLIP (Contrastive Language-Image Pretraining) textual embeddings, enabling efficient use of VLMs without significant computational overhead. Our model achieves 82.46% mAP on the THUMOS14 dataset, outperforming existing methods, and sets new baselines for zero-shot and few-shot performance on the THUMOS14 and TVSeries datasets. © 2025, CC BY-NC-SA.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Improving Prediction Quality of Face Image Preference Using Combinatorial Fusion Algorithm 16th

Improving Prediction Quality of Face Image Preference Using...

引用

16th International Conference on Brain informatics, BI 2023

作者： Zhang, Zihan Schweikert, Christina Shimojo, Shinsuke Hsu, D. Frank Laboratory of Informatics and Data Mining Department of Computer and Information Science Fordham University YorkNY10023 United States Division of Computer Science Mathematics and Science St. John’s University QueensNY11439 United States Division of Biology and Biological Engineering/Computation and Neural Systems California Institute of Technology PasadenaCA91125 United States

ISBN: (纸本)9783031430749

When two face images are shown to a subject, the subject’s preference choice is influenced by many factors. Although it is a challenging task, one way to detect a subject’s preference is to analyze the eye movement gaze cascade in the recorded video sequence together with a set of extracted attributes (features). Combinatorial fusion algorithm (CFA) is a new information fusion and machine learning paradigm for combining multiple scoring systems using rank-score characteristic (RSC) function and cognitive diversity (CD). In this paper, we apply CFA in the analysis of the eye movement gaze cascade sequence. In particular, we characterize each of the attributes and measure the diversity between two attributes using RSC function and CD respectively. The novelty of the combinatorial fusion approach is the new paradigm of incorporating both score function and rank function as well as using both score combination and rank combination. In addition, our results demonstrate that weighted rank combination has some advantage over weighted score combination when the weight is measured using diversity strength. Since diversity strength depends only on cognitive diversity between two attributes but not on any specific sequence in the eye movement gaze cascade, our result facilitates learning and modeling in an unsupervised manner. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Virtual Network Embedding: Literature Assessment, Recent Advancements, Opportunities, and Challenges

引用

IEEE Communications Surveys and Tutorials 2025年

作者： Satpathy, Anurag Sahoo, Manmath Narayan Swain, Chittaranjan Bellavista, Paolo Guizani, Mohsen Muhammad, Khan Bakshi, Sambit Missouri University of Science and Technology Department of Computer Science RollaMO United States National Institute of Technology Visual Surveillance Laboratory Department of Computer Science and Engineering Odisha Rourkela769008 India Atal Bihari Vajpayee Indian Institute of Information Technology and Management Department of Computer Science and Engineering Gwalior India Department of Computer Science and Engineering Italy Machine Learning Department Abu Dhabi United Arab Emirates Department of Applied Artificial Intelligence School of Convergence College of Computing and Informatics Seoul03063 Korea Republic of

Network virtualization (NV) allows service providers (SPs) to instantiate logically isolated entities called virtual networks (VNs) on top of a substrate network (SN). Though VNs bring about multiple benefits, particularly in terms of economic costs and elasticity, they also force various technical challenges to be addressed. The primary one is the issue of optimally allocating resources to VNs, also termed virtual network embedding (VNE). This paper presents an exhaustive survey of VNE by extensively covering the state-of-the-art research field in this very active field and focusing on the emerging research trends in industry and academia over the last decade. In addition, this survey originally contributes to the literature by proposing a novel taxonomy for existing VNE solutions and providing a thorough comparative study of their strategies. © 1998-2012 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

A Framework for Democratizing Open-Source Decision-Making using Decentralized Autonomous Organization

A Framework for Democratizing Open-Source Decision-Making us...

引用

Computing and informatics (ICCI), International Conference on

作者： Khalifa H. Afifi Khaled M. Fouad Heba K. Aslan Faculty of Information Technology and Computer Science Nile University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Faculty of Computers and Engineering New Mansoura University Egypt Informatics Department Electronics Research Institute (ERI) Cairo Egypt Center of Informatics Science Faculty of Information Technology and Computer Science Nile University Cairro Egypt

The open Source Software (OSS) became the backbone of the most heavily used technologies, including operating systems, cloud computing, AI, Blockchain, Bigdata Systems, IoT, and many more. Although the OSS individual contributors are the primary power for developing the OSS projects, they do not contribute to the OSS project's decisionmaking as much as their contributions in the OSS Projects development. This paper proposes a framework to democratize the OSS Project's decision-making using a blockchain-related technology called Decentralized Autonomous Organization (DAO). Using DAO, contributors get incentive tokens as a reward in return for contributions. The earned tokens can be used in the process of decision-making governance. This governance model tends to allow OSS individual contributors to have a public voice in the OSS project's development roadmap in particular, and the OSS decision making governance in general.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel End-to-End Ensemble UNet Network Based on Edge Computing for Tool Wear Detection 24

A Novel End-to-End Ensemble UNet Network Based on Edge Compu...

引用

3rd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2024

作者： Chen, Jianwen Tsai, Meng-Shiun Lin, Wan-Ju Hung, Che-Lun Department of Computer Science National Tsing Hua University Hsinchu300044 Taiwan Department of Mechanical Engineering National Taiwan University Taipei106319 Taiwan Department of Mold and Die Engineering National Kaohsiung University of Science and Technology Kaohsung807618 Taiwan Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taipei11221 Taiwan

ISBN: (纸本)9798400716416

Automated tool wear condition monitoring is essential for ensuring product quality. However, achieving both high detection precision and utilizing edge computing are critical for advancing intelligent manufacturing. Consequently, this article develops a tool wear detection system utilizing edge computing techniques. Firstly, a novel end-to-end ensemble UNet-based model is proposed. Through end-to-end feature fusion training, it effectively addresses the robustness and accuracy issues inherent in single models. Secondly, multiple neural computing sticks are involved to reduce the need for cloud transmission and preserve data privacy, thereby enabling scalability and flexibility in deployment. Experiments demonstrate that mean intersection over union (mIoU) and mean dice coefficient (mDice) in tool wear detection can be improved by over 3% and 2%, respectively. Furthermore, the execution time can be accelerated by a factor of 4. © 2024 ACM.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

LSTM and CNN hybrid model for enhanced fingerprint recognition

引用

Emerging Trends in Drugs, Addictions, and Health 2025年 5卷 100174-100174页

作者： Sameer, Nahla Abdulnabee Nema, Bashar M. Informatics Institute for Postgraduate Studies Information Technology & Communications University Baghdad Iraq Department of Computer Science Faculty of Sciences Mustansiriyah University Baghdad Iraq

The paper introduces an advanced hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enhance fingerprint detection and matching within large datasets. The CNN component is employed for feature extraction and learning from image data, while the LSTM component is utilized for sequence prediction in temporal series, yielding optimal results compared to existing methods based on specific criteria. This hybrid approach achieves a fingerprint recognition accuracy of 99.85 %. The proposed method effectively reduces errors in recognition and false rejection rates in fingerprint recognition systems, thereby improving overall usability and security. The integration of CNN and LSTM in fingerprint recognition signifies a substantial advancement in biometric authentication technology, with potential applications in law enforcement, border security, and access control systems. © 2025

关键词： Biometric recognition Classification methods CNN Fingerprint forgery detection Image feature engineering LSTM

来源：评论

学校读者我要写书评

暂无评论

Estimation of Circadian Rhythms Using Complexity Analysis with Temporal Scale Dependency in Electroencephalogram Signals 20

Estimation of Circadian Rhythms Using Complexity Analysis wi...

引用

20th IEEE International Conference on Cognitive informatics and Cognitive Computing, ICCI*CC 2021

作者： Iinuma, Yuta Nobukawa, Sou Takagi, Sho Nishimura, Haruhiko Chiba Institute of Technology Department of Computer Science Chiba Japan University of Hyogo Graduate School of Applied Informatics Kobe Japan

ISBN: (纸本)9781665421195

Disturbances in circadian rhythms have been recently associated with a variety of healthy states and psychiatric pathologies. Therefore, estimating the degree of circadian rhythm disturbance is important for discriminating psychiatric disorders from healthy conditions. Electroencephalogram (EEG) allows to detect brain activity directly, but the recorded signal combines neural activity across multiple time scales. The complexity of brain activity across multiple time scales has been previously quantified using multiscale entropy (MSE) analysis. In this study, we investigated whether MSE analysis of EEG data can detect circadian rhythms. Our results show that in the daytime, the complexity of brain activity is increased at larger temporal scale, and that MSE analysis detects these changes more accurately than conventional power analysis. Because complexity at large temporal scales arises from the long-range connectivity in brain networks, we suggest that the decrease in this EEG pattern complexity by night is mediated by melatonin, which suppresses neural firing and reduces wide-range interactions between brain regions. Our method can be applied for the EEG-based analysis of circadian rhythms in longitudinal studies and may help to diagnose healthy states and psychiatric conditions. © 2021 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Measurement of Synthetic-Dimension Band Structures in Silicon Coupled Ring Resonators 16

Measurement of Synthetic-Dimension Band Structures in Silico...

引用

16th Pacific Rim Conference on Lasers and Electro-Optics, CLEO-PR 2024

作者： Zhang, Ruming Li, Liucun Kamata, Mikiya Baba, Toshihiko Ozawa, Tomoki Ota, Yasutomo Iwamoto, Satoshi Research Center for Advanced Science and Technology The University of Tokyo Tokyo153-8904 Japan Yokohama National University Department of Electrical and Computer Engineering Yokohama240-8501 Japan Advanced Institute for Materials Research Tohoku University Sendai980-8577 Japan Keio University Department of Applied Physics and Physico-Informatics Yokohama223-8533 Japan

We fabricated integrated silicon coupled-ring resonators and measured photonic band structures for synthetic frequency lattices with different configurations. A phase difference between two modulation signals introduc... 详细信息

ISBN: (纸本)9798350372076

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

RadioModRec-l: A Large Scale Radio Frequency Dataset for Automatic Modulation Recognition Research 4

RadioModRec-l: A Large Scale Radio Frequency Dataset for Aut...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Adetiba, Emmanuel Olasina, Jamiu R. Obiyemi, Obiseye Covenant University Covenant Applied Informatics and Communication Africa Center of Excellence Dept. of Electrical and Information Engineering Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban4001 South Africa Federal Polytechnic Ilaro Dept. of Computer Engineering Ilaro Nigeria Durban University of Technology Space Science Centre Dept. of Electrical Power Engineering Durban South Africa

ISBN: (纸本)9798350353266

Access to well-curated large datasets remains a significant bottleneck in AI-based research within wireless communication. Rapid advancements in neighbouring fields, such as computer vision and natural language processing, are largely due to the availability of extensive open-access datasets. However, similar progress has not been observed in wireless communication. To address this gap, we curated a comprehensive dataset for fifteen digital modulation schemes, including 4QAM, 16QAM, 64QAM, 256QAM, 8PSK, 16PSK, 32PSK, 64PSK, 128PSK, 256PSK, CPFSK, DBPSK, DQPSK, GFSK, and GMSK. Our dataset considers Rayleigh and Rician channel models under Additive White Gaussian Noise (A WGN) with SNRs ranging from -20dB to + 20dB in 5dB increments. The data samples were converted to constellation signal images and carefully pre-processed. Named RadioModRec, this dataset provides a valuable resource for researchers to train and evaluate AI models. It is freely accessible on Kaggle, promoting further innovation in the wireless communication domain. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Multi-View Learning-Based Bayesian Ruleset Extraction Algorithm For Accurate Hepatotoxicity Prediction

A Multi-View Learning-Based Bayesian Ruleset Extraction Algo...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Chen, Siyang Wu, Lianlian Xu, Yong Liu, Kunhong He, Song Bo, Xiaochen Xiamen University School of Informatics Xiamen China Tianjin University Academy of Medical Engineering and Translational Medicine Tianjin China Fujian University of Technology School of Computer Science and Mathematics Fuzhou China Xiamen University School of Film Department of Digital Media Technology Xiamen China Institute of Health Service and Transfusion Medicine Department of Bioinformatics Beijing China

ISBN: (纸本)9798350337488

The interpretable machine learning method is important in drug discovery. Unlike traditional ensemble learning methods, this paper proposes an interpretable algorithm based on Bayesian rule extraction to obtain reliable and explainable results for hepatotoxicity prediction. To extract information from different types of omics data, our algorithm employs a multi-view learning strategy to enhance performance. Specifically, a random forest is trained in each view, and then the Bayesian rule extraction algorithm is designed to select an optimal rule subset, controlling the size and accuracy of the ruleset through probabilities. These rule sets are integrated through multi-view voting to get the final decisions. The performance of our algorithm is tested on the hepatotoxicity dataset, demonstrating that compared to traditional machine learning algorithms and rule-based algorithms, our approach maintains excellent performance while achieving high interpretability in most cases. Our python source code and the related Supplementary Materials are available at: ***/MLDMXM2017/MV-BRS. © 2023 IEEE.

关键词： Bayesian Ruleset Hepatotoxicity Prediction Interpretable Machine Learning Multi-view Learning

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：