检索结果-内蒙古大学图书馆

Graph visualization efficiency of popular web-based libraries

Visual Computing for Industry, Biomedicine, and Art 2025年第1期8卷 1-17页

作者： Zhao, Xin Wang, Xuan Zou, Xianzhe Liang, Huiming Bai, Genghuai Zhang, Ning Huang, Xin Zhou, Fangfang Zhao, Ying School of Computer Science and Engineering Central South University Hunan Changsha410083 China QAX Security Center Qi An Xin Technology Group Inc. Beijing100044 China

Web-based libraries, such as ***, ***, and ***, are widely used to generate node-link graph visualizations. These libraries allow users to call application programming interfaces (APIs) without identifying the details of the encapsulated techniques such as graph layout algorithms and graph rendering methods. Efficiency requirements, such as visualizing a graph with 3k nodes and 4k edges within 1 min at a frame rate of 30 fps, are crucial for selecting a proper library because libraries generally present different characteristics owing to the diversity of encapsulated techniques. However, existing studies have mainly focused on verifying the advantages of a new layout algorithm or rendering method from a theoretical viewpoint independent of specific web-based libraries. Their conclusions are difficult for end users to understand and utilize. Therefore, a trial-and-error selection process is required. This study addresses this gap by conducting an empirical experiment to evaluate the performance of web-based libraries. The experiment involves popular libraries and hundreds of graph datasets covering node scales from 100 to 200k and edge-to-node ratios from 1 to 10 (including complete graphs). The experimental results are the time costs and frame rates recorded using the libraries to visualize the datasets. The authors analyze the performance characteristics of each library in depth based on the results and organize the results and findings into application-oriented guidelines. Additionally, they present three usage cases to illustrate how the guidelines can be applied in practice. These guidelines offer user-friendly and reliable recommendations, aiding users in quickly selecting the desired web-based libraries based on their specific efficiency requirements for node-link graph visualizations. © The Author(s) 2025.

关键词： Flow visualization

来源：评论

学校读者我要写书评

暂无评论

Interactive Agent Foundation Model: A Meta-Learning Strategy

Interactive Agent Foundation Model: A Meta-Learning Strategy

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Mani Dwivedi Anuj Kr. Dwivedi Department of Computer Science and Engineering KIET Group of Institutions Delhi-NCR Ghaziabad India Department of Computer Science and Engineering Galgotias College of Engineering and Technology India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Artificial intelligence (AI) systems are evolving from static, task-specific models to dynamic, agent-based systems that perform well in a variety of scenarios. We present an Interactive Agent Foundation Model using a novel multi-task agent training methodology that includes many pretraining techniques such as language modelling, visual masked autoencoders, and next-action prediction. This framework's adaptability and versatility have been shown in the robotics, gaming AI, and healthcare sectors, yielding results that are pertinent to the situation. Effective multimodal and multitask learning is made possible by utilizing a variety of data sources, such as textual information, gaming data, robotics sequences, and large-scale video datasets. Our method offers a viable way forward for creating adaptable, proactive, multimodal systems.

关键词： Training Adaptation models Visualization Foundation models Soft sensors Medical services Predictive models Multitasking Data models Robots

来源：评论

学校读者我要写书评

暂无评论

Optimizing Distributed Training Approaches for Scaling Neural Networks

arXiv

引用

arXiv 2025年

作者： Baligodugula, Vishnu Vardhan Amsaad, Fathi Department of Computer Science and Engineering Wright State University

This paper presents a comparative analysis of distributed training strategies for large-scale neural networks, focusing on data parallelism, model parallelism, and hybrid approaches. We evaluate these strategies on image classification tasks using the CIFAR-100 dataset, measuring training time, convergence rate, and model accuracy. Our experimental results demonstrate that hybrid parallelism achieves a 3.2× speedup compared to single-device training while maintaining comparable accuracy. We propose an adaptive scheduling algorithm that dynamically switches between parallelism strategies based on network characteristics and available computational resources, resulting in an additional 18% improvement in training efficiency. © 2025, CC BY.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

A New Benchmark and Algorithm for Clothes-Changing Video Person Re-Identification

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 1993-2005页

作者： Wang, Likai Zhang, Xiangqun Han, Ruize Wei, Yanjie Wang, Song Feng, Wei Tianjin University College of Intelligence and Computing Tianjin300350 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518107 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

Person re-identification (Re-ID) is a classical computer vision task and has significant applications for public security and information forensics. Recently, long-term Re-ID with clothes-changing has attracted increasing attention. However, existing methods mainly focus on image-based setting, where richer temporal information is overlooked. In this paper, we focus on the relatively new yet practical problem of Clothes-Changing Video-based Re-ID (CCVReID), which is less studied. First, given the dataset shortage, we build two new benchmark datasets for CCVReID problem, including a large-scale synthetic video dataset and a real-world one, both containing human sequences with various clothing changes. Moreover, we systematically study this problem by simultaneously considering the classical appearance feature and temporal feature contained in the video. We develop a dual-branch fusion framework that makes use of the information from both clothes-aware appearance feature and clothes-free gait feature. For better information fusion, a confidence-guided re-ranking strategy is proposed to adaptively balance the weight of these two categories of features. We have released the benchmark and code proposed in this work to the public at https://***/kkw98/CCVReID. © 2025 IEEE.

关键词： Reamers

来源：评论

学校读者我要写书评

暂无评论

A Review on Binary Code Analysis Datasets 18th

A Review on Binary Code Analysis Datasets

引用

18th International Conference on Wireless Artificial Intelligent Computing Systems and Applications, WASA 2024

作者： Huang, Zhijian Song, Shuguang Liu, Han Kuang, Hongyu Zhang, Jingjing Hu, Pengfei National Key Laboratory of Science and Technology on Information System Security Systems Engineering Institute Academy of Military Sciences Beijing China School of Computer Science and Technology Shandong University Qingdao China

ISBN: (纸本)9783031714696

Binary code analysis serves as the foundation for research in vulnerability discovery, software protection, and malicious code analysis. However, analyzing binary files is challenging due to the lack of high-level semantic information, leading to heavy dependence on analysts’ expertise and significantly impacting the efficiency of binary code analysis. Recent years has witnessed the blossom of machine learning models for binary analysis, but few researches address the problem of binary code datasets. In this paper, we review all the existing and available datasets, and make classification according to their application. We set up experiments to illustrate how dataset quality could affect the performance of machine learning models in binary function recognition. Based on the experimental evaluation, we present a discussion on the ground truth as well as quality evaluation problems for binary code datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Capabilities and Limitations of Generative AI Applications, Challenges, and Future Directions

Exploring the Capabilities and Limitations of Generative AI ...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Singh, Gulbir Meenakshi Sharma, Poonam Bhardwaj, Anjul Graphic Era Hill University Department of Computer Science and Engineering Haldwani Campus Uttarakhand Nanital India Mmict&bm Mullana Haryana Ambala India Divine Institute of Management & Studies Dept. of Computer Application Ziradei Bihar Siwan India

ISBN: (纸本)9798331508685

Unprecedented capabilities for content generation, predictive analytics, and automation are made available by the introduction of Generative Artificial Intelligence (AI) technologies, which uses in a new age of industrial innovation. The purpose of this study is to investigate the transformational potential of generative AI from the perspective of exploring its capabilities and limitations and highlighting its role in the development of future technological developments. With the help of this study, we want to highlight important unsolved issues in contemporary generative AI paradigms. These challenges need to be addressed in order to further improve the capabilities, variety, and dependability of these concepts. Our goal is to give researchers with significant insights that will allow them to explore successful research areas, which will ultimately lead to the creation of generative AI systems that are more robust and accessible. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Identification of Sounds from Construction Sites: A Machine Learning Approach 4th

Identification of Sounds from Construction Sites: A Machin...

引用

4th International Conference on Emerging Trends and Technologies on Intelligent Systems, ETTIS 2024

作者： Maji, Sayantan Mukherjee, Himadri Dhar, Ankita Marciano, Matteo Roy, Kaushik Department of Computer Science and Engineering Sister Nivedita University Kolkata India TISA Lab Department of Computer Science West Bengal State University Kolkata India Gazelien Records Lab Department of Arts and Humanities Music Program New York University Abu Dhabi Abu Dhabi United Arab Emirates

ISBN: (纸本)9789819757022

The rate at which the world is evolving is astonishing with cutting-edge technologies being introduced every day. There have been developments in every field ranging from constructing gigantic architectures to enhancing the ease and comfort with which we can commute daily. Nevertheless, this has given rise to different types of pollution, sound pollution being one of them. Although the impact of sound pollution is not instantaneously noticed, it has a distinct effect on humans and nature which is observed over a period of time. There are multiple sources that cause sound pollution. Sounds from ongoing construction sites are one of them. Such sounds disrupt the daily lifestyle of people, their health, and daily productivity. Mostly, these sounds start very early in the day thereby making it difficult for people to manually take precautions like shutting doors and windows or deploying mobile soundproofing solutions. Machine learning has advanced significantly over the years leading to the refinement of artificial intelligence. This has aided in the development of multifarious solutions to ease and simplify our daily lifestyle. This sets the stage for an autonomous system, that can detect sounds from construction sites very early to automatically deploy precautionary measures so that the effect of these sounds on close by residents can be minimized. In this paper, a system is presented that models audio clips using MFCC-based features for the identification of sounds from construction sites in the Urban environment. Experiments were performed on a dataset of over 6K clips composed of the varied construction sounds as well as ambient urban sounds and a maximum accuracy of 98.02% was achieved using random forest-based classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Traffic Crash Severity: Predicting Property Damage and Injury Collision Through Machine Learning Models 7th

Traffic Crash Severity: Predicting Property Damage and Injur...

引用

7th International Conference of Transportation Research Group of India, CTRG 2023

作者： Agrawal, Toshini Mohan, Ranju Department of Computer Science and Engineering Vellore Institute of Technology Madhya Pradesh Bhopal466114 India Department of Civil and Infrastructure Engineering Indian Institute of Technology Jodhpur Rajasthan Jodhpur342030 India

ISBN: (纸本)9789819799428

The types of collisions during road crashes and the factors contributing to them are many. Chances of collisions can be reduced by predicting the probability of types of collisions at various locations and providing drivers with real-time details of the risk of collision while they travel. This paper aims to predict the severity of collisions at intersections, specifically two types of collisions—‘Property damage’ and ‘Injury Collision’, through machine learning models. The paper uses a dataset from the Kaggle website which the police department of Seattle regularly updates. It consists of values of different variables such as road condition, weather condition, junction type, and the attention span of the driver, hitting a parked car, light condition, and speeding. Four different conventional machine learning algorithms, namely, Random Forest, K-Nearest Neighbour, Decision tree, and Linear Regression are applied for collision prediction. The Random Forest model is observed to have the highest accuracy (0.7506) followed by the K-Nearest Neighbours algorithm (0.7442), Decision Tree (0.7385) and Linear regression (0.6999). The most featured attributes were weather conditions, road conditions and temperature and predicted more property damage than injury collision. An ensemble of the above models is also tried for crash prediction and observed as with the highest accuracy (0.7519). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

PCGAUNet: Pixel Correlation and Gaussian Attention Driven Network for Text Segmentation 27th

PCGAUNet: Pixel Correlation and Gaussian Attention Driven Ne...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Roy, Ayush Palaiahnakote, Shivakumara Pal, Umapada Antonacopoulos, Apostolos Ramachandra, Raghavendra Computer Vision and Pattern Recognition Indian Statistical Institute Kolkata India School of Science Engineering and Environment University of Salford Manchester United Kingdom Norwegian University of Science and Technology Trondheim Norway

ISBN: (纸本)9783031784460

Text-line segmentation is still considered challenging for complex background scene images. The success of text detection and recognition depends on the success of the text segmentation. This study presents a new method for text segmentation to facilitate reliable detection and recognition. Therefore, we introduce a new model called Pixel Correlation and Gaussian Attention Driven Network (PCGAUNet) for text segmentation. To extract pixel correlation, we modified the MultiResUnet architecture, which leverages pixel-wise correlation to effectively highlight foreground pixels. In addition, the proposed model utilizes the prior spatial statistics of bottleneck features to create a learnable Gaussian distribution, which guides the decoder for accurate text segmentation. Experimental results on three standard scene text segmentation datasets, ICDAR13 FST, Total Text, and COCO-TS, show that the proposed model outperforms existing methods. Furthermore, the results for the underwater dataset UTS-55 show that our model is robust and generic. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Autonomous 3D Reconstruction with Small Unmanned Aerial Vehicle (UAV) using Structure from Motion: Practical Aspects

Autonomous 3D Reconstruction with Small Unmanned Aerial Vehi...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Rayon, Nathan Stevens, Raymond Sevil, Hakki Erhan Department of Computer Science University of West Florida FL32514 United States Department of Electrical and Computer Engineering University of West Florida FL32514 United States Department of Intelligent Systems & Robotics University of West Florida FL32514 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This paper explores the practical considerations and challenges involved in achieving autonomous 3D reconstruction utilizing small Unmanned Aerial Vehicles (UAVs) through the framework of Structure from Motion (SFM). The utilization of small UAVs equipped with lightweight cameras presents a promising resource for cost-effective and rapid 3D mapping in various domains such as disaster response, infrastructure inspection, and search and rescue. In this study, the critical practical aspects of this process, including height level for taking images, UAV selection, number of images, image acquisition strategies, and computational time. The effectiveness and limitations of autonomous 3D reconstruction with small UAVs through practical insights are summarized, with discussions on potential advancements and areas for future research. This paper serves as a guide for researchers interested in utilizing small UAVs for autonomous 3D reconstruction tasks applications. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

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：