检索结果-内蒙古大学图书馆

17th Pacific visualization conference (Pacificvis)

作者： Han, Dongming Zhu, Haiyang Chen, Wei Pan, Rusheng Liu, Yijing Zhou, Jiehui Feng, Haozhe Zhang, Tianye Wang, Xumeng Zhu, Minfeng Tao, Jianrong Fan, Changjie Zhang, Xiaolong (Luke) Zhejiang Univ State Key Lab CAD&CG Hangzhou Peoples R China Hithink RoyalFlush Informat Network Co Ltd Hangzhou Peoples R China Zhejiang Univ Minist Educ Lab Art & Archaeol Image Hangzhou Peoples R China Nankai Univ Coll Comp Sci Tianjin Peoples R China Zhejiang Univ Hangzhou Peoples R China Netease Fuxi AI Lab Hangzhou Peoples R China Penn State Univ University Pk PA 16802 USA Wuchan Zhongda Digital Technol Co Ltd Hangzhou Peoples R China

ISBN: (纸本)9798350393811;9798350393804

This paper presents GraphFederator, a novel approach to construct federated representations of multi-party graphs and supports privacy-preserving visual analysis of graphs. Inspired by the concept of federated learning, we reformulate the analysis of multi-party graphs into a decentralization process. The new federation framework consists of a shared module that is responsible for federated modeling and analysis, and a set of local modules that run on respective graph data. Specifically, we propose a Federated Graph Representation Model (FGRM) that is learned from encrypted characteristics of multi-party graphs in local modules. We also design multiple visualization tools for federated visualization, exploration, and analysis of multi-party graphs. Experimental results on two datasets demonstrate the effectiveness of our approach.

关键词： Federated learning Graph analysis Graph visual analysis Representation learning

来源：评论

学校读者我要写书评

暂无评论

The TMMTA Model: Momentum Tracking and analysis of Tennis Matches 24

The TMMTA Model: Momentum Tracking and Analysis of Tennis Ma...

引用

2024 International conference on Smart City and Information System, ICSCIS 2024

作者： Chen, Feiyang Guo, Yang Wang, Tianqi School of Management Northeastern University at Qinhuangdao Qinhuangdao Hebei066099 China School of Mathematics and Statistics Northeastern University at Qinhuangdao Qinhuangdao Hebei066099 China

ISBN: (纸本)9798400710155

In sports, the generation and change of momentum are always accompanied, and tennis is no exception. It is of great significance for winning to analyze how the momentum generates, changes and its impact on the score in the tennis match. Most of the existing studies theoretically study the nature and influence of momentum in tennis matches or focus on the point results and whether winning or losing the match. However, the analysis of momentum changes in data series and the exploration of the relationship and influence degree of specific behavior and data features with momentum are missing. To this end, this study constructs a Tennis Matches Momentum Tracking and analysis Model (TMMTA) based on the time-series analysis to analyze the data of five games Carlos Alcaraz participated in and the model is applied to multiple players and multiple matches to verify the prediction effect and conclusion of the model. Experiments show that the visual analysis results are very good, which can effectively analyze the momentum changes and specific performance in players' matches and provide insight for player training and match strategy. The three game behaviors, double errors, untouchable winning shots and unforced errors, have the most weight on scoring and are closely related to strategic momentum. Strategic momentum has a higher impact on matches score than mental momentum, and the combination of the two is the best prediction. This has important implications for coaches to value and utilize the role of Momentum. © 2024 ACM.

关键词： Tennis

来源：评论

学校读者我要写书评

暂无评论

Stock Market Prediction Based on Time Series data and Multimodal Sentiments 10

Stock Market Prediction Based on Time Series Data and Multim...

引用

IEEE 10th International conference on Big data Computing Service and Machine Learning Applications (IEEE BigdataService)

作者： Zhao, Jikang Deng, Yancong Univ Leeds Sch Comp Leeds W Yorkshire England Univ Calif San Diego Jacob Sch Engn La Jolla CA 92093 USA

ISBN: (纸本)9798350366396;9798350366389

Investor sentiment significantly influences stock market dynamics, often displaying pronounced volatility. Concurrently, objective financial news remains a crucial determinant of market shifts. This study sourced an extensive collection of textual comments from the StockTwits trading platform. We then implemented a semi-supervised GAN-Bert methodology to perform sentiment analysis on these unlabeled remarks. Following this, the Inception v3 model facilitated sentiment evaluation of financial visuals from The Wall Street Journal (WSJ). Upon validation and integration of sentiment scores from these visuals, we amalgamated sentiments derived from both textual and visual data into a Bi-LSTM framework. This integrated model underwent training for predictive analytics, underpinning trading simulations based on anticipated returns. The experimental results demonstrated a notable return of 30.41% during our evaluation period, showcasing an improvement over single sentiment feature analysis.

关键词： Bi-LSTM Semi-Supervised Learning Sentiment analysis Stock forecasting

来源：评论

学校读者我要写书评

暂无评论

exploration of Brand visual Communication Innovation Design Method Based on AIGC Technology 11th

Exploration of Brand Visual Communication Innovation Design ...

引用

11th International conference on Applications and Techniques in Cyber Intelligence, ATCI 2023

作者： Chen, Tiantian Pang, Bingnan Ma, Chuhua Shao, Wenwen Animation and Digital Creative College Hainan College of Software Technology Qionghai China

This paper discusses the innovative application and challenges of generative artificial intelligence technology (AIGC) in brand visual communication and creative design of advertisements. AIGC has subverted the traditional communication method by virtue of its high efficiency and intelligence, realizing personalized customization and precise push ads, effectively improving the conversion effect and saving costs, and enhancing the brand's rapid response to the market and the efficiency of creative output. At the same time, this technology can promote the digitalization and intelligence of the advertising industry by tapping into big data resources. Accompanied by issues such as data security, privacy protection, talent shortage, creative quality control, brand image maintenance and regulatory adaptability, the industry needs to strengthen data security protection, cultivate cross-discipline AIGC technology and design talents, and establish a rigorous content audit system, so as to inject a strong impetus for brand visual innovation and design, and lead the brand visual communication and advertising creative design into a new stage of AI empowerment. © 2024 The Authors. Published by Elsevier B.v.

关键词： Marketing

来源：评论

学校读者我要写书评

暂无评论

Coronal Plane Alignment Classification of Arthritic Knees in a South Indian Population and Functional Outcome Comparison Post-mechanical Alignment Total Knee Arthroplasty

引用

INDIAN JOURNAL OF ORTHOPAEDICS 2024年第6期58卷 740-746页

作者： Palanisamy, Yuvarajan Natarajan, Sugumar Prasad, Arjun R. Rajan, David v. Ortho One Orthopaed Special Ctr Coimbatore 641005 Tamil Nadu India

Study BackgroundMechanical alignment has always been considered as the gold standard in total knee arthroplasty (TKA), but various other coronal alignment strategies have been proposed to enhance native knee kinematics and thus elevate patient satisfaction levels. Coronal plane alignment of the knee (CPAK) classification introduced by MacDessi is a simple yet comprehensive system to classify knees based on their coronal plane alignment. It categorizes knees into nine phenotypes based on medial proximal tibial angle (MPTA) and lateral distal femoral angle (LDFA).Materials and MethodsThis study investigates the distribution of classification of primary arthritic knees (CPAK) types among arthritic knees in the South Indian population and compares the functional outcomes following total knee arthroplasty (TKA) using traditional mechanical alignment among various CPAK types. The research, spanning from September 2021 to August 2023, encompasses a comprehensive analysis of 324 patients with 352 knees in the first part and 48 patients with 72 knees in the second part of the study who underwent TKA, incorporating demographic data and radiological *** indicate a predominant distribution of CPAK type 1, followed by type 2 and type 4 among the South Indian population. In the functional outcomes analysis, regardless of CPAK type, patients exhibited significant improvements in Knee Injury and Osteoarthritis Outcome Score (KOOS), Oxford Knee Score (OKS), and visual analog scale (vAS) scores *** distribution among the South Indian population is comparable to other Indian study and studies with an Asian population, but varies with studies among the White population. Significant improvement of functional outcome among all CPAK types signifies the robust nature of conventional mechanical alignment strategy. Thus, our study serves as an initial exploration into the knee phenotype of the South Indian population and findings contribute

关键词： Total knee arthroplasty Knee arthritis SouthIndian population Coronal plane knee alignment CPAK Knee Phenotype classification Mechanical alignment TKA Knee Injury and Osteoarthritis Outcome Score Oxford Knee Score visual analog scale

来源：评论

学校读者我要写书评

暂无评论

An In-Depth exploration of Image Captioning Training Approaches and Performance analysis 9

An In-Depth Exploration of Image Captioning Training Approac...

引用

9th IEEE International conference for Convergence in Technology, I2CT 2024

作者： Kushal, K. Manoj, Madhav Reddy, Kevansh Nair, Priyanka C. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350394474

In the rapidly evolving landscape of computer vision, image captioning has emerged as a challenging task. This report explores the techniques involved in image captioning using deep learning techniques, especially the encoder-decoder framework. Models such as CNN-LSTM, CNN-GRU,Xception - YOLO v4, GIT Based Model are used. Recognition is given to the significance of ample and well-annotated datasets in teaching the algorithms to understand the complex relationships between visual elements and textual descriptions. Along with traditional evaluation metrics like BLEU score, this study also employs metrics such as METEOR, ROUGE-L, and SPICE to compare performance between models. The findings highlight on the impact of deep learning in enabling computers to generate captions for diverse visual content. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

MISTA: A LARGE-SCALE dataSET FOR MULTI-MODAL INSTRUCTION TUNING ON AERIAL IMAGES

MISTA: A LARGE-SCALE DATASET FOR MULTI-MODAL INSTRUCTION TUN...

引用

IEEE International conference on Multimedia and Expo (ICME)

作者： Wu, Hao Lu, Ke Li, Yuqiu Huang, Junhao Xue, Jian Univ Chinese Acad Sci Sch Engn Sci Beijing 100049 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

ISBN: (纸本)9798350390155;9798350390162

This paper introduces MISTA, a novel dataset for visual instruction tuning on aerial imagery, designed to enhance large multi-modal model applications in remote sensing. Originating from the renowned DOTA-v2.0 aerial object detection benchmark, MISTA uniformly processes high-resolution images into 2048.2048 pixels, creating a detailed and complex dataset tailored for remote sensing analysis. To craft this dataset, we design an automated annotation pipeline, employing advanced language models such as GPT-4 and LLavA1.5, to generate diverse and specialized instruction-following data. The annotations include various instruction types like multi-turn conversation, detailed description, and complex reasoning, each reflecting the intricacies inherent in remote sensing tasks. The innovative approach of subdividing aerial images into individually annotated sub-patches significantly enhances the richness of the dataset and allows for a more granular analysis of visual content. As a robust foundation for multi-modal model development in remote sensing, MISTA represents a significant advancement, setting the stage for future research and further applications in the field.

关键词： visual instruction tuning aerial images large multi-modal model self-annotation remote sensing tasks

来源：评论

学校读者我要写书评

暂无评论

Democratizing co-production of thematic co-explorations for Citizen Observatories 9

Democratizing co-production of thematic co-explorations for ...

引用

9th International conference on Smart and Sustainable Technologies (SpliTech)

作者： Lopez-de-Ipina, Diego Sanchez-Corcuera, Ruben Eduardo vergara, Felipe Emaldi, Mikel Wolosiuk, Dawid Casado-Mansilla, Diego Feliciotti, Alessandra Peters-Anders, Jan Univ Deusto Fac Engn Bilbao Spain Univ Deusto DeustoTech Bilbao Spain VRVis Forsch GmbH Visual Analyt Grp Vienna Austria MindEarth Biel Switzerland AIT Austrian Inst Technol GmbH Vienna Austria

ISBN: (纸本)9798350390797;9789532901351

Citizen Observatories are a promising instrument to drive societal behaviour change towards greener more sustainable practices. However, assembling Citizen Observatories is not easy, since apart from the continuous engagement of their participants, there is the need to have some specialized domain and technical knowledge. data quality, continuous engagement and retention and factual impact into decision making are three usual roadblocks which impend a wider adoption of this practice. This paper explains how GREENGAGE project aims to democratize the co-production of thematic co-explorations and overcome those barriers.

关键词： Citizen Observatory thematic co-exploration co-production data analysis Green Deal

来源：评论

学校读者我要写书评

暂无评论

Interpreting Autonomous Driving Corner Cases: A visual Analytics Approach 17

Interpreting Autonomous Driving Corner Cases: A Visual Analy...

引用

17th Pacific visualization conference (Pacificvis)

作者： Sun, Yi Shao, Zekai Qiu, Xingyu Li, Yun Liu, Ting Xiang, Linbing Sun, Dong Chen, Siming Fudan Univ Shanghai Peoples R China NIO Shanghai Peoples R China

ISBN: (纸本)9798350393811;9798350393804

With the progression of artificial intelligence, there has been substantial advancement in autonomous driving technology. However, even the most advanced systems may confront failures in certain corner cases, necessitating enhanced analytical approaches. Traditional approaches focused on the numerical analysis of isolated sensor data, are often insufficient for deriving meaningful insights in such situations. To address this inadequacy, we propose a visual analytics approach, crafted to aid domain experts in performing analyses and extracting system improvements from cases with unexpected behaviors. This approach intricately integrates extensive driving scenarios and low-level module behaviors into the autonomous driving decision-making process, utilizing rich visualizations and an interface for interactive exploration and systematic synthesis of findings. Uniquely, our system opens the "black box" of modules in the decision-making pipeline during corner cases, taking into account both the overall decision-making pipeline and the fine-grained behaviors of the modules in the pipeline, setting our approach apart from previous works. To validate our system's effectiveness, we perform two case studies, inviting domain experts for evaluation, and the results confirm our system's efficacy in allowing experts to obtain crucial insights into autonomous driving systems.

关键词： visual Analytics-data visualization-Interactive visualization Autonomous Driving-AD Simulations-Corner Cases

来源：评论

学校读者我要写书评

暂无评论

High-level Grammars for visualization and visual Analytics 36

High-level Grammars for Visualization and Visual Analytics

引用

36th SIBGRAPI conference on Graphics, Patterns and Images (SIBGRAPI)

作者： Moreira, Gustavo Laget, Marcos FerwiraI, Nivan Miranda, Fabio Univ Illinois Chicago IL 60680 USA Univ Fed Fluminense Niteroi RJ Brazil Univ Fed Pernambuco Recife PE Brazil

ISBN: (纸本)9798350338737;9798350338720

The increase in data availability and the popularization of data science brought a continuously growing need to use visualizations to explore complex data. Creating new visualizations, however, is a difficult task that often requires extensive programming expertise. High-level grammars for authoring visualizations provide a systematic and flexible way to specify visualizations in a declarative manner, lowering the entry barrier for data analysis. Such grammars effectively assist in the exploration of the visualization design space and of complex datasets. The goal of this tutorial paper is to then provide a summary of recently proposed grammars, so that a broad audience (e.g., students, researchers, practitioners) can better understand how they are designed and used in practice for visualization and visual analytics tasks.

关键词： visual analytics

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：