检索结果-内蒙古大学图书馆

46th Annual Conference of the German Association for Pattern Recognition, DAGM-GCPR 2024

作者： Glaszner, Lukas Zach, Martin Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/II Graz8010 Austria

ISBN: (纸本)9783031851803

Diffusion models have been successfully applied to many inverse problems, including MRI and CT reconstruction. Researchers typically re-purpose models originally designed for unconditional sampling without modifications. Using two different posterior sampling algorithms, we show empirically that such large networks are not necessary. Our smallest model, effectively a ResNet, performs almost as good as an attention U-Net on in-distribution reconstruction, while being significantly more robust towards distribution shifts. Furthermore, we introduce models trained on natural images and demonstrate that they can be used in both MRI and CT reconstruction, out-performing model trained on medical images in out-of-distribution cases. As a result of our findings, we strongly caution against simply re-using very large networks and encourage researchers to adapt the model complexity to the respective task. Moreover, we argue that a key step towards a general diffusion-based prior is training on natural images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Recognition and evaluation of cutaneous condition through assorted artificial intelligence reliant algorithms

引用

International Journal of Information Technology (Singapore) 2025年 1-13页

作者： Mishra, Manmohan Yadav, Ajay Kumar Mazumdar, Bireshwar Dass Gupta, Prashant K. Panwar, Arvind Bharadwaj, Shivam Department of Computer Application United Institute of Management Prayagraj India School of Computer Science & Engineering Technology Bennett University Plot Nos 8-11 TechZone II Uttar Pradesh Greater Noida 201310 India Galgotias University Plot No. 2 Yamuna Expy opposite Buddha International Circuit Sector 17A Uttar Pradesh Prayagraj 203201 India

Our skin is the hefty organ that envelops and shields body. It prevents us from numerous fatal and non fatal diseases. It is observed that due to bacteria or other causes of infection, skin faces certain minor or life threatening diseases. The most prioritized step toward restoring health is early illness signs identification. Identifying Cutaneous Condition from clinical images is one of the foremost challenges in medical image investigation. In the presented study we will enlighten the various Artificial Intelligence techniques falling under the categories of supervised machine learning including Probabilistic classifier (Naïve Bayes), Statistical algorithm (Logistic Regression), Ensemble learning (Random Decision Trees), Data analysis technique (Convolutional Neural Network) and Kernel approach (Support Vector Machine) to identify and classify the cutaneous condition appropriately so that corrective measures of skin treatment can be endow with. The proposed approach entails collecting images as input, preprocessing, segmenting, feature extraction and lastly applying the classification algorithms to derive the Cutaneous Condition categories. Additional trials are conducted using the different approaches as indicated and it was discovered from the suggested tests that the Convolutional Neural Network strategy yields the best results overall. The proposed model is trained, tested, and evaluated using the International Skin Imaging Collaboration (ISIC) 2019 challenge dataset and Human Against Machine with 10,000 training images (HAM10000) for the detection of manifold Cutaneous Condition. © Bharati Vidyapeeth's institute of computer Applications and Management 2025.

关键词： Artificial intelligence Confusion matrix Convolutional neural networks Cutaneous condition Image processing Machine learning

来源：评论

学校读者我要写书评

暂无评论

AI-based character generation for disease stories: a case study using epidemiological data to highlight preventable risk factors

引用

i-com 2025年第1期24卷 259-281页

作者： Mittenentzwei, Sarah Garrison, Laura A. Budich, Beatrice Lawonn, Kai Dockhorn, Alexander Preim, Bernhard Meuschke, Monique Department of Simulation and Graphics Otto-von-Guericke University of Magdeburg Universitätsplatz 2 Magdeburg39106 Germany Department of Informatics University of Bergen Thormøhlens Gate 55 Bergen5020 Norway Faculty of Mathematics and Computer Science University of Jena Ernst-Abbe-Platz 2 Jena07743 Germany Institute of Information Processing Leibniz University Hannover Welfengarten 1 Hannover30167 Germany

Data-driven storytelling has grown significantly, becoming prevalent in various fields, including healthcare. In medical narratives, characters are crucial for engaging audiences, making complex medical information accessible, and potentially influencing positive behavioral and lifestyle changes. However, designing characters that are both educational and relatable to effectively engage audiences is challenging. We propose a GenAI-assisted pipeline for character design in data-driven medical stories, utilizing Stable Diffusion, a deep learning text-to-image model, to transform data into visual character representations. This approach reduces the time and artistic skills required to create characters that reflect the underlying data. As a proof-of-concept, we generated and evaluated two characters in a crowd-sourced case study, assessing their authenticity to the underlying data and consistency over time. In a qualitative evaluation with four experts with knowledge in design and health communication, the characters were discussed regarding their quality and refinement opportunities. The characters effectively conveyed various aspects of the data, such as emotions, age, and body weight. However, generating multiple consistent images of the same character proved to be a significant challenge. This underscores a key issue in using generative AI for character creation: the limited control designers have over the output. © 2025 the author(s), published by De Gruyter, Berlin/Boston.

关键词： data-storytelling GenAI medicine healthcare character generation

来源：评论

学校读者我要写书评

暂无评论

FX-MAD: Frequency-Domain Explainability and Explainability-Driven Unsupervised Detection of Face Morphing Attacks

FX-MAD: Frequency-Domain Explainability and Explainability-D...

引用

IEEE Winter Applications and computer Vision Workshops (WACVW)

作者： Marco Huber Pedro C. Neto Ana F. Sequeira Naser Damer Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Department of Computer Science Technische Universität Darmstadt Germany INESC TEC Porto Portugal Faculry of Engineering University of Porto Portugal

ISBN: (数字)9798331536626

ISBN: (纸本)9798331536633

Face recognition (FR) systems are vulnerable to morphing attacks, which refer to face images created by morphing the facial features of two different identities into one face image to create an image that can match both identities, allowing serious security breaches. In this work, we apply a frequency-based explanation method from the area of explainable face recognition to shine a light on how FR models behave when processing a bona fide or attack pair from a frequency perspective. In extensive experiments, we used two different state-of-the-art FR models and six different morphing attacks to investigate possible differences in behavior. Our results show that FR models rely differently on different frequency bands when making decisions for bona fide pairs and morphing attacks. In the following step, we show that this behavioral difference can be used to detect morphing attacks in an unsupervised setup solely based on the observed frequency-importance differences in a generalizable manner.

关键词： computer vision Correlation Face recognition Soft sensors Frequency-domain analysis Conferences Benchmark testing Security Facial features

来源：评论

学校读者我要写书评

暂无评论

Diff-3DCap: Shape Captioning With Diffusion Models

引用

IEEE Transactions on Visualization and computer graphics 2025年 PP卷 PP页

作者： Shu, Zhenyu Wen, Jiawei Li, Shiyang Xin, Shiqing Liu, Ligang NingboTech University School of Computer and Data Engineering Ningbo315100 China Zhejiang University Ningbo Institute Ningbo315100 China Zhejiang University College of Computer Science and Technology Hangzhou China ShanDong University School of Computer Science and Technology Jinan China University of Science and Technology of China Graphics & Geometric Computing Laboratory School of Mathematical Sciences Anhui China

The task of 3D shape captioning occupies a significant place within the domain of computer graphics and has garnered considerable interest in recent years. Traditional approaches to this challenge frequently depend on the utilization of costly voxel representations or object detection techniques, yet often fail to deliver satisfactory outcomes. To address the above challenges, in this paper, we introduce Diff-3DCap, which employs a sequence of projected views to represent a 3D object and a continuous diffusion model to facilitate the captioning process. More precisely, our approach utilizes the continuous diffusion model to perturb the embedded captions during the forward phase by introducing Gaussian noise and then predicts the reconstructed annotation during the reverse phase. Embedded within the diffusion framework is a commitment to leveraging a visual embedding obtained from a pre-trained visual-language model, which naturally allows the embedding to serve as a guiding signal, eliminating the need for an additional classifier. Extensive results of our experiments indicate that Diff-3DCap can achieve performance comparable to that of the current state-of-the-art methods. © 1995-2012 IEEE.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Bigger Isn’t Always Better: Towards a General Prior for Medical Image Reconstruction

arXiv

引用

arXiv 2025年

作者： Glaszner, Lukas Zach, Martin Institute of Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/II Graz8010 Austria Biomedical Imaging Group École polytechnique fédérale de Lausanne Lausanne1015 Switzerland Center for Biomedical Imaging Lausanne1015 Switzerland

Diffusion model have been successfully applied to many inverse problems, including MRI and CT reconstruction. Researchers typically re-purpose models originally designed for unconditional sampling without modifications. Using two different posterior sampling algorithms, we show empirically that such large networks are not necessary. Our smallest model, effectively a ResNet, performs almost as good as an attention U-Net on in-distribution reconstruction, while being significantly more robust towards distribution shifts. Furthermore, we introduce models trained on natural images and demonstrate that they can be used in both MRI and CT reconstruction, out-performing model trained on medical images in out-of-distribution cases. As a result of our findings, we strongly caution against simply re-using very large networks and encourage researchers to adapt the model complexity to the respective task. Moreover, we argue that a key step towards a general diffusion-based prior is training on natural images. © 2025, CC BY-SA.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A novel eXplainable AI agent for social interaction training of people with Autism Spectrum Disorder (ASD)

引用

International Journal of Information Technology (Singapore) 2025年 1-13页

作者： Gupta, Prashant K. Mazumdar, Bireshwar Dass Mishra, Manmohan Chadha, Rubina Komaragiri, Rama S. School of Computer Science Engineering and Technology Bennett University Plot Nos 8-11 TechZone II Uttar Pradesh Greater Noida 201310 India Department of Computer Applications United Institute of Management A-31 UPSIDC Industrial Area Naini Chak Noor Uttar Pradesh Prayagraj 211010 India Psychology / Counselling The Neuroaid and Research Foundation (NRF) C-19 Pamposh Enclave Delhi New Delhi 110048 India School of Engineering Galgotias University Plot No. 2 Yamuna Expy opposite Buddha International Circuit Sector 17A Uttar Pradesh Greater Noida 203201 India

Autism Spectrum Disorder (ASD) is a neurological disorder that impacts a subject’s ability to be involved in a social interaction. Machine learning (ML) and deep learning (DL) models have been mainly used for ASD detection, which are however criticized for their ‘black-boxness’, advocating the use of eXplainable artificial intelligence (XAI) algorithms. As per the literature search so far, no social interaction model-based eXplainable Autism Spectrum Disorder (ASD) care agent exists for social interaction training of an ASD subject. Therefore, this work makes a beginning in this direction. A novel architecture of an eXplainable ASD care agent for social interaction training of ASD subjects, with an underlying intelligent AI algorithm is presented. Its working is elucidated through six representative social interaction scenarios and some practical considerations are also presented when the agent is put in practice with the ASD subject. The working of the proposed ASD care agent is also depicted through a suitable case study. © Bharati Vidyapeeth's institute of computer Applications and Management 2025.

关键词： AI Agent Artificial intelligence (AI) Autism spectrum disorder EXplainable AI Neurological disorders Social interaction training

来源：评论

学校读者我要写书评

暂无评论

Embryonic heart development as an immersive experience: Unveiling learning effects and influential factors in virtual learning environments

引用

computers in Biology and Medicine 2025年 187卷 109638-109638页

作者： Kunz, Matthias Schott, Danny Wunderling, Tom Halloul, Martin Hansen, Christian Albrecht, Anne Braun-Dullaeus, Rüdiger C. Otto von Guericke University Medical Faculty Department of Internal Medicine/Cardiology and Angiology Magdeburg Germany Otto von Guericke University Faculty of Computer Science Department of Simulation and Graphics Magdeburg Germany Otto von Guericke University Medical Faculty Institute of Anatomy Magdeburg Germany

As the quality and availability of Virtual Reality (VR) technologies improve, their potential applications in medical education, particularly VR Learning Environments (VRLEs), are increasingly explored. VRLEs offer a dynamic platform where educators and students can interact, access materials, and engage in learning beyond traditional classrooms. However, questions remain about their long-term learning effects and potential confounding factors. This study investigates these aspects through a VR application designed for teaching heart embryology. For this reason we conducted a user study with medical students in their early years of training (N = 143). Our findings reveal significant short-term and sustained learning outcomes two to four weeks following a single VR session. Importantly, these outcomes appear largely independent of users’ technical affinity and are minimally influenced by their immersion tendencies. Instead, the quality of the VRLE and its user experience emerge as critical factors. These results underscore the efficacy of well-designed VRLEs in higher education and highlight key areas for future development. © 2025 The Authors

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Innovative Approaches to the Use of Multifunctional Materials in Building Envelopes 7th

Innovative Approaches to the Use of Multifunctional Material...

引用

7th International Conference on Construction, Real Estate, Infrastructure, and Project Management, ICCRIP 2023

作者： Kumari, Soni Suresh Kumar, R. Abhishek, Kumar Pathak, B.N. Nijhawan, Ginni Khayoon, Ali Talib Rajalakshmi, B. Kalra, Ravi Department of Mechanical Engineering GLA University UP Mathura India Department of Civil Engineering Institute of Aeronautical Engineering Hyderabad500043 India Gujarat Ahmedabad380026 India Department of Mechanical Engineering IMS Engineering College Ghaziabad India Lovely Professional University Panjab Phagwara India College of Engineering Technology National University of Science and Technology Dhi Qar Iraq Department of Computer Science New Horizon College of Engineering Bangalore India Lloyd Institute of Engineering and Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India

ISBN: (纸本)9789819649013

Multifunctional materials have become a hot topic in building envelope design due to their ability to simultaneously perform several functions such as structural support, insulation, energy harvesting, and storage. This paper reviews recent developments in the use of multifunctional materials in building envelopes, including their composition, properties, and potential applications. The paper also examines innovative approaches to integrating these materials into building envelopes to enhance their performance and sustainability. The potential benefits and challenges of using multifunctional materials in building envelopes are discussed, along with future directions for research in this field. However, there are also challenges associated with the use of these materials, including their high cost, complexity of integration, and potential durability issues, which require further research and development. Overall, this review provides insights into the current state and potential of multifunctional materials in building envelopes, highlighting opportunities for future research and application. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Thermal comfort

来源：评论

学校读者我要写书评

暂无评论

GaussEdit: Adaptive 3D Scene Editing with Text and Image Prompts

引用

IEEE Transactions on Visualization and computer graphics 2025年

作者： Shu, Zhenyu Yu, Junlong Chao, Kai Xin, Shiqing Liu, Ligang NingboTech University School of Computer and Data Engineering Ningbo315100 China Zhejiang University Ningbo Institute Ningbo315100 China Zhejiang University School of Software Technology Hangzhou China Xi'an Jiaotong University School of Big Data and Artificial Intelligence Management Xi'an China ShanDong University School of Computer Science and Technology Jinan China University of Science and Technology of China Graphics & Geometric Computing Laboratory School of Mathematical Sciences Anhui China

This paper presents GaussEdit, a framework for adaptive 3D scene editing guided by text and image prompts. GaussEdit leverages 3D Gaussian Splatting as its backbone for scene representation, enabling convenient Region of Interest selection and efficient editing through a three-stage process. The first stage involves initializing the 3D Gaussians to ensure high-quality edits. The second stage employs an Adaptive Global-Local Optimization strategy to balance global scene coherence and detailed local edits and a category-guided regularization technique to alleviate the Janus problem. The final stage enhances the texture of the edited objects using a sophisticated image-to-image synthesis technique, ensuring that the results are visually realistic and align closely with the given prompts. Our experimental results demonstrate that GaussEdit surpasses existing methods in editing accuracy, visual fidelity, and processing speed. By successfully embedding user-specified concepts into 3D scenes, GaussEdit is a powerful tool for detailed and user-driven 3D scene editing, offering significant improvements over traditional methods. © 1995-2012 IEEE.

关键词： 3D modeling

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：