检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Big Data, BigData 2023

作者： Marek, Dariusz Paszkuta, Marcin Szygula, Jakub Biernacki, Piotr Domanski, Adam Szczygiel, Marta Krol, Marcel Wojciechowski, Konrad Silesian University of Technology Dept. of Distributed Systems and Informatic Devices Warsaw Poland Polish-Japanese Academy of Information Technology ul. Koszykowa 86 Warsaw02-008 Poland Silesian University of Technology Dept. of Computer Graphics Vision and Digital Systems Warsaw Poland Institute of Theoretical and Applied Informatics Polish Academy of Sciences Warsaw Poland Silesian University of Technology Warsaw Poland

ISBN: (纸本)9798350324457

In the presented paper, detailed schematics and descriptions concerning communication in the context of swarm drone control are introduced. Methods and technologies behind them are discussed. The implementation of the presented concept was verified through a series of tests. Simulation results which confirm the effectiveness and efficiency of the proposed solutions are presented. The obtained results prove the correctness implementation of the presented methods and also demonstrate the benefits derived from the proposed approach. The presented concept of controlling a swarm of drones represents the current state of knowledge and technology in the field of drones and their control. By utilizing advanced communication technologies, positioning, and analysis of communication structures, this work makes a significant contribution to the UAV (Unmanned Aerial Vehicle) field. © 2023 IEEE.

关键词： Control Concepts Industrial Environment Industry 4.0 simulation environments Swarm of Drones UAV

来源：评论

学校读者我要写书评

暂无评论

Characteristics Analysis of Moving Conversations to Detect Events on Twitter 14

Characteristics Analysis of Moving Conversations to Detect E...

引用

14th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022

作者： Senaratne, Hansi Lehle, Dominic Schreck, Tobias Earth Observation Center German Aerospace Center Oberpfaffenhofen Germany Advanced Research & Technologies Avira Tettnang Germany Inst. of Computer Graphics & Knowledge Visualization Graz University of Technology Graz Austria

ISBN: (纸本)9781665456616

A conversation is an exchange of thoughts, news, or ideas about a particular topic between two or more people. On Twit-ter, hashtags allow its users to collate all conversations pertaining to a particular topic. The progressions that occur in such conversations through the geographic space, the time, or the thematic contexts, create trajectories of conversations on Twitter, and they can give us valuable insights into interesting events that take place around us. In this paper we develop an approach based on data analysis and visualisation, to (1) construct such conversation trajectories for chosen popular hashtags, (2) analyse the various geospatial-and content-characteristics of the conversation trajectories (e.g., distance variance, speed of propagation, topic diversity, or credibility) to determine co-located events, and (3) rank and sort the resulting conversation trajectories according to a user-defined interestingess-measure, to narrow down the search space for interesting conversation trajectories. Our approach is among the first to introduce the us-age of movement of conversations across geographic space and time for the exploratory detection and analysis of events, whereas most existing works use keyword-based text analysis to detect events on Twitter. All the three stages of the approach (construct, analyse, rank & sort) are presented in a visual-interactive interface that allows us to explore Twitter text data without extensive prior knowledge, and benefit from the pure exploratory capabilities of the tool. The usefulness of our approach is demonstrated as a proof-of-concept to detect sports-related events, where we were able to identify the outcome of a contest for Major League Baseball sportsmen on Twitter. © 2022 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Sparse Message Passing Network with Feature Integration for Online Multiple Object Tracking

arXiv

引用

arXiv 2022年

作者： Wang, Bisheng Possegger, Horst Bischof, Horst Cao, Guo School of Computer Science and Engerring Nanjing University of Science and Technology China Institute of Computer Graphics and Vision Graz University of Technology Austria

Existing Multiple Object Tracking (MOT) methods design complex architectures for better tracking performance. However, without a proper organization of input information, they still fail to perform tracking robustly and suffer from frequent identity switches. In this paper, we propose two novel methods together with a simple online Message Passing Network (MPN) to address these limitations. First, we explore different integration methods for the graph node and edge embeddings and put forward a new IoU (Intersection over Union) guided function, which improves long term tracking and handles identity switches. Second, we introduce a hierarchical sampling strategy to construct sparser graphs which allows to focus the training on more difficult samples. Experimental results demonstrate that a simple online MPN with these two contributions can perform better than many state-of-the-art methods. In addition, our association method generalizes well and can also improve the results of private detection based methods. © 2022, CC BY-NC-SA.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Standard representation space for spectral imaging 31

Standard representation space for spectral imaging

引用

31st Color and Imaging Conference - Color Science and Engineering Systems, Technologies, and Applications, CIC 2023

作者： Thomas, Jean-Baptiste Lapray, Pierre-Jean Derhak, Max Farup, Ivar Université de Bourgogne Dpt IEM IMVIA Dijon France Université de Haute-Alsace IRIMAS UR 7499 MulhouseF-68100 France ONYX Graphics Inc. United States Norwegian University of Science and Technology Department of Computer Science Gjøvik Norway

ISBN: (纸本)9780892083640

The variety of spectral imaging systems makes the portability of imaging solutions and the generalization of research difficult. We advocate for the creation of a standard representation space for spectral imaging. We propose a space that allows connection to colorimetric standards and to spectral reflectance factors, while keeping a low and practical dimension. The performance of one instance of this standard is evaluated through simulations. Results demonstrate that this space may show reduced performance in accuracy than some native camera spaces, especially instances with a number of bands larger than the standardized dimension, but this limitation comes with benefit in size and standardization. © 2023 Society for Imaging Science and technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Forgery Detection Model Analysis using Statistical Splicing Method for Architecture Learning and Feature Extraction

Image Forgery Detection Model Analysis using Statistical Spl...

引用

2024 OPJU International technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Pagare, Shreyas Shukla, Surendra Kumar Pandey, Priyank Gupta, Vishan Kumar Jindal, Himanshu Jain, Amit Chameli Devi Group of Institutions Department of Cse MP Indore India SVKM'S Nmims Mpstme Shirpur Campus Department of Computer Engineering India Graphics Era Deemed to Be University Department of Cse Dehradun India Amity University Punjab Amity School of Engineering and Technology Mohali India Op Jindal University Department of Cse Raigarh India

ISBN: (纸本)9798350373783

The underlying concept behind envision forgeries is the use of digital image modification to manipulate data in these pictures. Image forgeries can be roughly categorized using broader methodologies. The active approach uses digital watermarking and requires a digital signature, whereas the passive approach depends on the mood of the specific photographs. These days, several digital scams have been created, such as those that involve copy-migration, retouching, and image classification. Image splitting creates a composite image by merging two or more photos. Image retrieving is the process of improving image properties like sharpness, color correction, and white balance. The primary focus of the work area is the forgery's passive method aspect. The suggested analysis combines the centroid and Hu moments. The major goal of this study project is to lower the dimensionality of the feature by analyzing the central with Hu moments. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Integrating AEC Domain-Specific Multidisciplinary Knowledge for Informed and Interactive Feedback in Early Design Stages 1

引用

19th International Conference on Computing in Civil and Building Engineering, ICCCBE 2022

作者： Reisinger, Julia Rasoulzadeh, Shervin Kovacs, Balint Istvan Ferschin, Peter Vasylevska, Khrystyna Hensel, Michael Kovacic, Iva Wimmer, Michael Department for Integrated Planning and Industrial Building TU Wien Vienna Austria Department for Digital Architecture and Planning TU Wien Vienna Austria Research Unit of Computer Graphics TU Wien Vienna Austria Institute of Visual Computing & Human-Centered Technology TU Wien Vienna Austria

ISBN: (数字)9783031325151

ISBN: (纸本)9783031325144

In the context of digitalization in the industry, a variety of technologies has been developed for system integration and enhanced team collaboration in the Architecture, Engineering and Construction (AEC) industry. Multidisciplinary design requirements are characterized by a high degree of complexity. Early design methods often rely on implicit or experiential design knowledge, whereas contemporary digital design tools mostly reflect domain-specific silo thinking with time-consuming iterative design processes. Yet, the early design stages hold the greatest potential for design optimization. This paper presents a framework of a multidisciplinary computational integration platform for early design stages that enables integration of AEC domain-specific methods from architecture, engineering, mathematics and computer science. The platform couples a semantic integrative mixed reality sketching application to a shape inference machine-learning based algorithm to link methods for different computation, simulation and digital fabrication tasks. A proof of concept of the proposed framework is presented for the use case of a freeform geometry wall. Future research will explore the potential of the framework to be extended to larger building projects with the aim to connect the method into BIM-processes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

DRT: Detection Refinement for Multiple Object Tracking 32

DRT: Detection Refinement for Multiple Object Tracking

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Wang, Bisheng Fruhwirth-Reisinger, Christian Possegger, Horst Bischof, Horst Cao, Guo School of Computer Science and Engineering Nanjing University of Science and Technology China Christian Doppler Laboratory for Embedded Machine Learning Austria Institute of Computer Graphics and Vision Graz University of Technology Austria

Deep learning methods have led to remarkable progress in multiple object tracking (MOT). However, when tracking in crowded scenes, existing methods still suffer from both inaccurate and missing detections. This paper proposes Detection Refinement for Tracking (DRT) to address these two issues for people tracking. First, we construct an encoder-decoder backbone network with a novel semi-supervised heatmap training procedure, which leverages human heatmaps to obtain a more precise localization of the targets. Second, we integrate a "one patch, multiple predictions" mechanism into DRT which refines the detection results and recovers occluded pedestrians at the same time. Additionally, we leverage a data-driven LSTM-based motion model which can recover lost targets at a negligible computational cost. Compared with strong baseline methods, our DRT achieves significant improvements on publicly available MOT datasets. In addition, DRT generalizes well, i.e. it can be applied to any detector to improve their performance. © 2021. The copyright of this document resides with its authors.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Discovery of COVID-19 Symptomatic Experience Reported by Twitter Users 32

Discovery of COVID-19 Symptomatic Experience Reported by Twi...

引用

32nd Medical Informatics Europe Conference, MIE 2022

作者： Jiang, Keyuan Zhu, Minghao Bernard, Gordon R. Department of Computer Information Technology and Graphics Purdue University Northwest HammondIN46323 United States College of Electronic & Information Engineering Tongji University Shanghai China Vanderbilt University NashvilleTN United States

ISBN: (纸本)9781643682846

Since the beginning of the COVID-19 pandemic, patients shared their personal experiences of the viral infection on social media. Gathering their symptomatic experiences reported on Twitter may help better understand the infectious disease and supplement our knowledge of the disease gathered by healthcare workers. In this study, we identified personal experience tweets related to COVID-19 infection using a pre-trained and fine-tuned language model, and annotated the machine-identified tweets in order to extract the information of infection status, symptom concepts, and the days the symptomatic experience occurred. Our result shows that the top 10 most common symptoms mentioned in the collected Twitter data are in line with those published by WHO and CDC. The symptoms along with the day information appear to provide additional insight on how the infection progresses in infected individuals. © 2022 European Federation for Medical Informatics (EFMI) and IOS Press.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Improving energy compaction of adaptive fourier decomposition 28

Improving energy compaction of adaptive fourier decompositio...

引用

28th European Signal Processing Conference, EUSIPCO 2020

作者： Borowicz, Adam Faculty of Computer Science Department of Digital Media and Computer Graphics Bialystok University of Technology Wiejska str. 45A Bialystok15-351 Poland

ISBN: (纸本)9789082797053

Adaptive Fourier decomposition (AFD) provides an expansion of an analytic function into a sum of basic signals, called mono-components. Unlike the Fourier series decomposition, the AFD is based on an adaptive rational orthogonal system, hence it is better suited for analyzing non-stationary data. The most popular algorithm for the AFD decomposes any signal in such a way that the energy of the low-frequency components is maximized. Unfortunately, this results in poor energy compaction of high-frequency components. In this paper, we develop a novel algorithm for the AFD. The key idea is to maximize the energy of any components no matter how big or small the corresponding frequencies are. A comparative evaluation was conducted of the signal reconstruction efficiency of the proposed approach and several conventional algorithms by using speech recordings. The experimental results show that with the new algorithm, it is possible to get a better performance in terms of the reconstruction quality and energy compaction property. © 2021 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

LuxKnit: Fabricating Interactive Display Textiles Integrated with Sensing by Machine Knitting 25

LuxKnit: Fabricating Interactive Display Textiles Integrated...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Tongyan Wang Mohan Chi Yue Yu Kedi Yan Mo Li Yiyue Luo Rua Mae Williams Purdue University West Lafayette Indiana USA Computer and Information Technology Purdue University West Lafayette Indiana USA University of Washington Seattle Washington USA ECE University of Washington Seattle Washington USA Computer Graphics and Technology Purdue University West Lafayette Indiana USA

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：