检索结果-内蒙古大学图书馆

31st International Conference on Multimedia Modeling, MMM 2025

作者： Stroh, Michael Kloda, Vojtěch Verner, Benjamin Vopálková, Zuzana Buchmüller, Raphael Jäckl, Bastian Hajko, Jakub Lokoč, Jakub Visual Computing Department of Computer Science Faculty of Natural Sciences Konstanz University Konstanz Germany SIRET Research Group Department of Software Engineering Faculty of Mathematics and Physics Charles University Prague Czech Republic Data Analysis and Visualization Department of Computer Science Faculty of Natural Sciences Konstanz University Konstanz Germany

ISBN: (纸本)9789819620739

We present a third version of the PraK system designed around an effective text-image and image-image search model. The system integrates sub-image search options for localized context search for CLIP and image color/texture and interfaces tailored to specific task types. A user study shows the benefits of sub-image search in homogeneous video collections. We further enhance the user experience of the PraK framework by re-designing the frontend and introducing task-specific views. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Building a dynamic opinion dashboard to categorize tweets for real-time sentiment analysis

引用

International Journal of Information Technology (Singapore) 2025年 1-7页

作者： Adekoya-Cole, Temitope Fernando, Sandra Maroju, Abhilash Samal, Chandra Kanta Aggarwal, Saurabh Brahma, Biswajit Assistive Technology Research Group SCDM London Metropolitan University London United Kingdom Department of Information Technology University of the Cumberlands Williamsburg United States Department of Computer Science Acharya Narendra Dev College Delhi University Delhi India San Jose State University San Jose United States Senior Data & Visualization Engineer McKesson Corporation 32559 Lake Bridgeport St Fremont United States

Twitter, a popular social media, and networking tool has evolved into an important source of real-time news and a hub for public opinions. Using Twitter data, the given paper investigates the possibility of applying sentiment analysis to identify tweets as positive, negative, or neutral and then presenting the results visually, resulting in an in-depth analysis of public opinion. To do this, a dynamic opinion dashboard is designed comprising three modules viz. the user interface built on HTML, the backend application running in Python and Twitter, and the data source. The dashboard is built on a Python Flask app that interacts with a Twitter API to collect tweets, a sentiment analysis library to classify the tweets, and a variety of visualization libraries to create charts and graphs. The proposed dashboard provides users with real-time insights from text data in a user-friendly way. The proposed work is validated and compared with existing studies as well as pre-trained sentiment analysis models based on evaluation metrics such as accuracy, precision, recall and F1 score. © Crown 2025.

关键词： data visualization Dynamic dashboard Sentiment analysis TweetNLP

来源：评论

学校读者我要写书评

暂无评论

Enhancing medical vision-language contrastive learning via inter-matching relation modelling

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Li, Mingjian Meng, Mingyuan Fulham, Michael Feng, David Dagan Bi, Lei Kim, Jinman University of Sydney Biomedical data analysis and visualization lab School of Computer Science NSW Australia Royal Prince Alfred Hospital Department of Molecular Imaging NSW Australia Shanghai Jiao Tong University Institute of Translational Medicine Shanghai China

Medical image representations can be learned through medical vision-language contrastive learning (mVLCL) where medical imaging reports are used as weak supervision through image-text alignment. These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation. Recent mVLCL methods attempt to align image sub-regions and the report keywords as local-matchings. However, these methods aggregate all local-matchings via simple pooling operations while ignoring the inherent relations between them. These methods therefore fail to reason between local-matchings that are semantically related, e.g., local-matchings that correspond to the disease word and the location word (semantic-relations), and also fail to differentiate such clinically important local-matchings from others that correspond to less meaningful words, e.g., conjunction words (importance-relations). Hence, we propose a mVLCL method that models the inter-matching relations between local-matchings via a relation-enhanced contrastive learning framework (RECLF). In RECLF, we introduce a semantic-relation reasoning module (SRM) and an importance-relation reasoning module (IRM) to enable more fine-grained report supervision for image representation learning. We evaluated our method using six public benchmark datasets on four downstream tasks, including segmentation, zero-shot classification, linear classification, and cross-modal retrieval. Our results demonstrated the superiority of our RECLF over the state-of-the-art mVLCL methods with consistent improvements across single-modal and cross-modal tasks. These results suggest that our RECLF, by modelling the inter-matching relations, can learn improved medical image representations with better generalization capabilities. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Oil Palm Plantations and Mangroves in Se Asia Among Igbp Land Cover Units Mapped by the Modis

SSRN

引用

SSRN 2025年

作者： Ye Myint, Yadanar Percival, Joseph Emile Honour Kitajima, Kaoru Division of Forest and Biomaterials Sciences Graduate School of Agriculture Kyoto University Kyoto Japan Spatial Data Analysis and Visualization Lab University of Hawaii at Hilo Hilo WI96720-4091 United States Department of Geography & Environmental Science University of Hawai‘i at Hilo HiloHI96720 United States

Moderate Resolution Imaging Spectroradiometer (MODIS) Land Cover type product (MODIS-LC) is widely used for global land cover classification to follow the International Geosphere-Biosphere Programme (IGBP) scheme. The geographical dimension of 1200 km x 1200 km is appropriate for regional and national level tracking of deforestation in SE Asia (4.5 million ha), where oil palm plantations are a key driver of forest loss in SE Asia. Here, we examined forest conversion to other land cover types in eight SE Asian countries during two periods (2001-2010 and 2010-2018) using the MODIS MCD12Q1 data in ArcMap 10.8.2. The results showed that 12% and 9% of forested areas were converted to woody savanna and savanna in 2001-2010 and 2010-2018, respectively. Then, we selected 260 random subsamples (500 m polygons) from each of the common land cover types in SE Asia and verified or reclassified their vegetation with visual examination of high-resolution Google Earth imagery. However, verification with high-resolution images reduced these estimates to 5.1 % and 4.1 %, because 44% and 46% of areas initially classified as woody savannas and savannas were actually oil palms. Using calibration factor for each vegetation type, 47.2 % and 47.9 % of forest losses were estimated to be attributable to conversion to oil palm plantations, whereas the remaining forest loss was attributed to degradation to savannas and grassland. In addition, the IGBP land cover type of permanent wetland was found to consist of mangroves (63%), aqua farms (20%), and oil palms (8%) rather than permanent wetland per se. While MODIS-LC is a powerful dataset for global analyses, regional calibration with high-resolution imagery, as demonstrated in this study, provides insight that can better inform policy makers. © 2025, The Authors. All rights reserved.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

Personal Protection Equipment Training as a Virtual Reality Game in Immersive Environments: Development Study and Pilot Randomized Controlled Trial

引用

JMIR Serious Games 2025年 13卷 e69021页

作者： Zhou, Liang Liu, Haoyang Fan, Mengjie Liu, Jiahao Yu, Xingyao Zhao, Xintian Zhang, Shaoxing Institute of Medical Technology Peking University Health Science Center Beijing China National Institute of Health Data Science Peking University Beijing China Beijing Forestry University Beijing China Visualization Research Center (VISUS) University of Stuttgart Stuttgart Germany Department of Healthcare-Associated Infection Management Peking University Third Hospital Beijing China Department of Otolaryngological Peking University Third Hospital Beijing China

Background: Proper donning and doffing of personal protection equipment (PPE) and hand hygiene in the correct spatial context of a health facility is important for the prevention and control of nosocomial infections. On-site training is difficult due to the potential infectious risks and shortages of PPE, whereas video-based training lacks immersion which is vital for the familiarization of the environment. Virtual reality (VR) training can support the repeated practice of PPE donning and doffing in an immersive environment that simulates a realistic configuration of a health facility. Objective: This study aims to develop and evaluate a VR simulation focusing on the correct event order of PPE donning and doffing, that is, the item and hand hygiene order in the donning and doffing process but not the detailed steps of how to don and doff an item, in an immersive environment that replicates the spatial zoning of a hospital. The VR method should be generic and support customizable sequencing of PPE donning and doffing. Methods: An immersive VR PPE training tool was developed by computer scientists and medical experts. The effectiveness of the immersive VR method versus video-based learning was tested in a pilot study as a randomized controlled trial (N=32: VR group, n=16;video-based training, n=16) using questionnaires on spatial-aware event order memorization questions, usability, and task workload. Trajectories of participants in the immersive environment were also recorded for behavior analysis and potential improvements of the real environment of the health facility. Results: Comparable sequence memorization scores (VR mean 79.38, SD 12.90 vs video mean 74.38, SD 17.88;P=.37) as well as National Aeronautics and Space Administration Task Load Index scores (VR mean 42.9, SD 13.01 vs video mean 51.50, SD 20.44;P=.16) were observed. The VR group had an above-average usability in the System Usability Scale (mean 74.78>70.0) and was significantly better than the video g

关键词： human computer interaction nosocomial infections control personal protection equipment PPE virtual reality training visualization

来源：评论

学校读者我要写书评

暂无评论

Developing diverse ensemble architectures for automatic brain tumor classification

引用

Multimedia Tools and Applications 2024年 1-44页

作者： Bogacsovics, Gergo Harangi, Balazs Hajdu, Andras Department of Data Science and Visualization Faculty of Informatics University of Debrecen PO Box 400 Debrecen4002 Hungary

Brain tumors pose a serious threat in our modern society, with a clear increase in global cases each year. Therefore, developing robust solutions that could automatically and reliably detect brain tumors in their early stages is of utmost importance. In our paper, we revisit the problem of building performant ensembles for clinical usage by maximizing the diversity of the member models during the training procedure. We present an improved, more robust, extended version of our framework and propose solutions that could be integrated into a Computer-Aided Diagnosis system to accurately classify some of the most common types of brain tumors: meningioma, glioma, and pituitary tumors. We show that the new framework based on the histogram loss can be seen as a natural extension of the former approach, as it also calculates the inner products of the latent vectors produced by each member to measure similarity, but at the same time, it also makes it possible to capture more complex patterns. We also present several variants of our framework to incorporate member models with varying dimensional feature vectors and to cope with imbalanced datasets. We evaluate our solutions on a clinically tested dataset of 3,064 T1-weighted contrast-enhanced magnetic resonance images and show that they greatly outperform other state-of-the-art approaches and the base architectures as well, achieving over 92% accuracy, 92% macro and weighted precision, 91% macro and 92% weighted F1 score, and over 90% macro and 92% weighted sensitivity. © The Author(s) 2024.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Asymptotically efficient parameter estimation for ordinary differential equations

引用

science China Mathematics 2017年第11期60卷 2263-2286页

作者： PANG TianXiao YAN PeiSi ZHOU Harrison H. School of Mathematical Sciences Zhejiang University Center for Computing and Visualization Brown University Department of Statistics and Data Science Yale University

Parameter estimation for ordinary differential equations arises in many fields of science and engineering. To be the best of our knowledge, traditional methods are often either computationally intensive or inaccurate for statistical inference. Ramsay et al.(2007) proposed a generalized profiling procedure. It is easily implementable and has been demonstrated to have encouraging numerical performance. However, little is known about statistical properties of this procedure. In this paper, we provide a theoretical justification of the generalized profiling procedure. Under some regularity conditions, the procedure is shown to be consistent for a broad range of tuning parameters. When the tuning parameters are sufficiently large, the procedure can be further shown to be asymptotically normal and efficient.

关键词： asymptotic efficiency consistency generalized profiling procedure ordinary differential equations splines

来源：评论

学校读者我要写书评

暂无评论

Marching diamonds for unstructured meshes

Marching diamonds for unstructured meshes

引用

VIS 05: IEEE visualization 2005, Proceedings

作者： Anderson, John C. Bennett, Janine C. Joy, Kenneth I. Institute for Data Analysis and Visualization Computer Science Department University of California Davis

ISBN: (纸本)0780394623

We present a higher-order approach to the extraction of isosurfaces from unstructured meshes. Existing methods use linear interpolation along each mesh edge to find isosurface intersections. In contrast, our method determines intersections by performing barycentric interpolation over diamonds formed by the tetrahedra incident to each edge. Our method produces smoother, more accurate isosurfaces. Additionally, interpolating over diamonds, rather than linearly interpolating edge endpoints, enables us to identify up to two isosurface intersections per edge. This paper details how our new technique extracts isopoints, and presents a simple connection strategy for forming a triangle mesh isosurface. © 2005 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Assessing Conventional and Deep Learning-Based Approaches for Named Entity Recognition in Unstructured Hungarian Medical Reports 22

Assessing Conventional and Deep Learning-Based Approaches fo...

引用

2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics, SAMI 2024

作者： Bogacsovics, Gergo Harangi, Balazs Beregi-Kovacs, Marcell Kupas, David Lakatos, Robert Serban, Norbert Daniel Tiba, Attila Toth, Janos University of Debrecen Faculty of Informatics Department of Data Science and Visualization Debrecen Hungary

ISBN: (纸本)9798350317206

In digital healthcare, much patient data is available in text format. The structuring of this data, according to standards, has yet to be widely used, including in Hungary, where it is available in unstructured form. To make these patient records easy to filter and search, they must be processed and structured. Using modern natural language processing and deep learning techniques has resulted in effective systems for implementing such workflows. However, selecting appropriate algorithms for specific text-processing tasks is still a challenging issue. This is due to the scarcity of benchmarks and the variety of architectures available. This article evaluates models for named entity recognition (NER) in digital medical reports written in Hungarian. We evaluate traditional, recurrent neural network, and transformer-based approaches for NER using a dataset comprising 801 positron emission tomography scans and annotated medical reports. The medical reports were annotated to cover six different entity classes and reviewed by clinical experts to ensure accuracy. We present a comprehensive assessment of various methods and provide insight into addressing NER problems in the case of low-resource languages such as Hungarian. © 2024 IEEE.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

A foveal inset for large display environments

A foveal inset for large display environments

引用

ACM International Conference on Virtual Reality Continuum and its Applications, VRCIA 2006

作者： Staadt, Oliver G. Ahlborn, Benjamin A. Kreylos, Oliver Hamann, Bernd Institute for Data Analysis and Visualization Department of Computer Science University of California Davis United States

ISBN: (纸本)1595933247

We introduce a system that adds a foveal inset to large-scale projection displays. The effective resolution of the foveal inset projection is higher than the original display resolution, allowing the user to see more details and finer features in large data sets. The foveal inset is generated by projecting a high-resolution image onto a mirror mounted on a pan - tilt unit that is controlled by the user with a laser pointer. Our implementation is based on Chromium and supports many OpenGL applications without modifications. We present experimental results using high-resolution image data from medical imaging and areal photography. © 2006 ACM.

关键词： Calibration

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

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

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：