检索结果-内蒙古大学图书馆

General 3D Room Layout from a Single View by Render-and-Compare 1

学校读者我要写书评

暂无评论

16th European Conference on computer Vision, ECCV 2020

作者： Stekovic, Sinisa Hampali, Shreyas Rad, Mahdi Sarkar, Sayan Deb Fraundorfer, Friedrich Lepetit, Vincent Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Université Paris-Est École des Ponts ParisTech Paris France

ISBN: (数字)9783030585174

ISBN: (纸本)9783030585167

We present a novel method to reconstruct the 3D layout of a room—walls, floors, ceilings—from a single perspective view in challenging conditions, by contrast with previous single-view methods restricted to cuboid-shaped layouts. This input view can consist of a color image only, but considering a depth map results in a more accurate reconstruction. Our approach is formalized as solving a constrained discrete optimization problem to find the set of 3D polygons that constitute the layout. In order to deal with occlusions between components of the layout, which is a problem ignored by previous works, we introduce an analysis-by-synthesis method to iteratively refine the 3D layout estimate. As no dataset was available to evaluate our method quantitatively, we created one together with several appropriate metrics. Our dataset consists of 293 images from ScanNet, which we annotated with precise 3D layouts. It offers three times more samples than the popular NYUv2 303 benchmark, and a much larger variety of layouts. © 2020, Springer Nature Switzerland AG.

关键词： Iterative methods

PIEMAP: Personalized Inverse Eikonal Model from Cardiac Electro-Anatomical Maps 11th

学校读者我要写书评

暂无评论

PIEMAP: Personalized Inverse Eikonal Model from Cardiac Elec...

11th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2020 held in Conjunction with MICCAI 2020

作者： Grandits, Thomas Pezzuto, Simone Lubrecht, Jolijn M. Pock, Thomas Plank, Gernot Krause, Rolf Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Center for Computational Medicine in Cardiology Institute of Computational Science Università della Svizzera italiana Lugano Switzerland Institute of Biophysics Medical University of Graz Graz Austria BioTechMed-Graz Graz Austria

ISBN: (纸本)9783030681067

Electroanatomical mapping, a keystone diagnostic tool in cardiac electrophysiology studies, can provide high-density maps of the local electric properties of the tissue. It is therefore tempting to use such data to better individualize current patient-specific models of the heart through a data assimilation procedure and to extract potentially insightful information such as conduction properties. Parameter identification for state-of-the-art cardiac models is however a challenging task. In this work, we introduce a novel inverse problem for inferring the anisotropic structure of the conductivity tensor, that is fiber orientation and conduction velocity along and across fibers, of an eikonal model for cardiac activation. The proposed method, named PIEMAP, performed robustly with synthetic data and showed promising results with clinical data. These results suggest that PIEMAP could be a useful supplement in future clinical workflowss of personalized therapies. © 2021, Springer Nature Switzerland AG.

关键词： Heart

Speculative Vulnerability: Uncovering the Temporalities of Vulnerability in People s Experiences of the Pandemic

学校读者我要写书评

暂无评论

Proceedings of the ACM on Human-computer Interaction 2022年第CSCW2期6卷 1-27页

作者： Seberger, John S. Obi, Ike Loukil, Mariem Liao, William Wild, David J. Patil, Sameer Department of Information Science College of Computing and Informatics Drexel University 3675 Market Street PhiladelphiaPA19104 United States Department of Computer Graphics Technology Purdue Polytechnic Institute Purdue University 401 N. Grant St. West LafayetteIN47907 United States Mediterranean Institute of Technology Les Jardins du Lac 2 Tunis1053 Tunisia Department of Informatics Luddy School of Informatics Computing and Engineering Indiana University Bloomington 901 E. Tenth Street BloomingtonIN48104 United States School of Computing University of Utah 50 Central Campus Dr. Salt Lake CityUT84112 United States

Pandemic-tracking apps may form a future infrastructure for public health surveillance. Yet, there has been relatively little exploration of the potential societal implications of such an infrastructure. In semi-structured interviews with 23 participants from India, the Middle East and North Africa (MENA), and the United States, we discussed attitudes and preferences regarding the deployment of apps that support contact tracing to contain the spread of COVID-19. Through interpretive analysis, we examined the relationship between persistent discomfort and vulnerability when using such apps. Such an examination yielded three temporal forms of vulnerability: real, anticipatory, and speculative. By identifying and defining the temporalities of vulnerability through an analysis of people's pandemic-related thoughts and experiences, we develop the overlapping discourses of humanistic infrastructure studies and infrastructural speculation. In doing so, we explore the concept of vulnerability itself and present implications for the study of vulnerability in Human-computer Interaction (HCI) and for the oversight of app-based public health surveillance. © 2022 Owner/Author.

关键词： Public health

Gaussian Process Emulators for Few-Shot Segmentation in Cardiac MRI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Viti, Bruno Thaler, Franz Kapper, Kathrin Lisa Urschler, Martin Holler, Martin Karabelas, Elias Department of Mathematics and Scientific Computing University of Graz Graz Austria Institute for Medical Informatics Statistics and Documentation Medical University of Graz Graz Austria Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Gottfried Schatz Research Center: Medical Physics and Biophysics Medical University of Graz Graz Austria BioTechMed-Graz Graz Austria

Segmentation of cardiac magnetic resonance images (MRI) is crucial for the analysis and assessment of cardiac function, helping to diagnose and treat various cardiovascular diseases. Most recent techniques rely on deep learning and usually require an extensive amount of labeled data. To overcome this problem, few-shot learning has the capability of reducing data dependency on labeled data. In this work, we introduce a new method that merges few-shot learning with a U-Net architecture and Gaussian Process Emulators (GPEs), enhancing data integration from a support set for improved performance. GPEs are trained to learn the relation between the support images and the corresponding masks in latent space, facilitating the segmentation of unseen query images given only a small labeled support set at inference. We test our model with the M&Ms-2 public dataset to assess its ability to segment the heart in cardiac magnetic resonance imaging from different orientations, and compare it with state-of-the-art unsupervised and few-shot methods. Our architecture shows higher DICE coefficients compared to these methods, especially in the more challenging setups where the size of the support set is considerably small. The code is available on GitLab 6 © 2024, CC BY-NC-ND.

关键词： Gaussian distribution

HEALTH DISPARITIES THROUGH GENERATIVE AI MODELS: A COMPARISON STUDY USING A DOMAIN SPECIFIC LARGE LANGUAGE MODEL

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bautista, Yohn Jairo Parra Lima, Vinicious Theran, Carlos Aló, Richard Computing Information Science Department Florida A&M University TallahasseeFL32317 United States Computer Graphics Department Purdue University West LafayetteIN47906 United States College of Science and Technology Florida A&M University TallahasseeFL32317 United States

Health disparities are differences in health outcomes and access to healthcare between different groups, including racial and ethnic minorities, low-income people, and rural residents. An artificial intelligence (AI) program called large language models (LLMs) can understand and generate human language, improving health communication and reducing health disparities. There are many challenges in using LLMs in human-doctor interaction, including the need for diverse and representative data, privacy concerns, and collaboration between healthcare providers and technology experts. We introduce the comparative investigation of domain-specific large language models such as SciBERT with a multi-purpose LLMs BERT. We used cosine similarity to analyze text queries about health disparities in exam rooms when factors such as race are used alone. Using text queries, SciBERT fails when it doesn’t differentiate between queries text: "race" alone and "perpetuates health disparities." We believe clinicians can use generative AI to create a draft response when communicating asynchronously with patients. However, careful attention must be paid to ensure they are developed and implemented ethically and equitably. © 2023, CC BY.

关键词： Health care

Named Entity Recognition in Chinese Judicial Domain Based on Self-attention mechanism and IDCNN 8

学校读者我要写书评

暂无评论

Named Entity Recognition in Chinese Judicial Domain Based on...

8th International Conference on Digital Home, ICDH 2020

作者： Huang, Wenming Zhang, Juan Xiao, Yannan Han, Zheng Deng, Zhenrong Guilin University of Electronic Technology School of Computer Science and Information Security Guilin China Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin China Guilin Bank Guilin China

ISBN: (纸本)9781728192345

Chinese named entity recognition (CNER) in the judicial domain is an important basic task for intelligent analysis and processing of massive documents. This domain entity has more complicated structure than the common named entity, and its entity category is more abundant. However, the general method can not solve the problem of domain specific identification. In this paper, we combine self-attention mechanism and iteration dilated convolution neural network (IDCNN) for CNER in judicial domain. The bidirectional gate recurrent unit (BiGRU) model is used to automatically learn the context semantic information of the text and solve the long-distance dependence of the sequence. The model introduce the IDCNN to extract the key features of context semantic information, and capture finer-grained semantic information in underlying texts. The self-attention mechanism is used to analyze the relationship between characters, and the problem of long sequence semantic dilution is effectively solved by means of dynamic weight, and the optimal tag sequence is calculated by integrating conditional random fields (CRF), which further improves the recognition ability of the model. Finally, by analyzing the characteristics of legal documents, the new data set is annotated and the fine-grained named entity recognition is realized. The experimental results on our corpus show that the proposed method can effectively identify the entities in legal documents, and improve performance in the judicial field. © 2020 IEEE.

关键词： Semantics

In-Hand 3D Object Scanning from an RGB Sequence

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hampali, Shreyas Hodan, Tomas Tran, Luan Ma, Lingni Keskin, Cem Lepetit, Vincent Reality Labs Meta United States LIGM Ecole des Ponts Univ Gustave Eiffel CNRS Marne-la-Vallée France Institute for Computer Graphics and Vision Graz University of Technology Graz Austria

We propose a method for in-hand 3D scanning of an unknown object with a monocular camera. Our method relies on a neural implicit surface representation that captures both the geometry and the appearance of the object, however, by contrast with most NeRF-based methods, we do not assume that the camera-object relative poses are known. Instead, we simultaneously optimize both the object shape and the pose trajectory. As direct optimization over all shape and pose parameters is prone to fail without coarse-level initialization, we propose an incremental approach that starts by splitting the sequence into carefully selected overlapping segments within which the optimization is likely to succeed. We reconstruct the object shape and track its poses independently within each segment, then merge all the segments before performing a global optimization. We show that our method is able to reconstruct the shape and color of both textured and challenging texture-less objects, outperforms classical methods that rely only on appearance features, and that its performance is close to recent methods that assume known camera poses. Copyright © 2022, The Authors. All rights reserved.

关键词： Cameras

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

学校读者我要写书评

暂无评论

Image Forgery Detection Model Analysis using Statistical Spl...

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Shreyas Pagare Surendra Kumar Shukla Priyank Pandey Vishan Kumar Gupta Himanshu Jindal Amit Jain Department of CSE Chameli Devi Group of Institutions Indore MP India Department of Computer Engineering SVKM’S NMIMS MPSTME Shirpur Campus India Department of CSE Graphics Era Deemed to be University Dehradun India Amity School of Engineering and Technology Amity University Punjab Mohali India Department of CSE OP Jindal University Raigarh India

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

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.

关键词： Technological innovation Mood Image color analysis Digital images Splicing Merging Watermarking

SceNDD: A Scenario-based Naturalistic Driving Dataset

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Prabu, Avinash Ranjan, Nitya Li, Lingxi Tian, Renran Chien, Stanley Chen, Yaobin Sherony, Rini United States The Department of Electrical and Computer Engineering Indiana University Purdue University Indianapolis United States The Department of Computer Information and Graphics Technology Indiana University Purdue University Indianapolis United States Toyota Motor North America Ann ArborMI United States

In this paper, we propose SceNDD: a scenario-based naturalistic driving dataset that is built upon data collected from an instrumented vehicle in downtown Indianapolis. The data collection was completed in 68 driving sessions with different drivers, where each session lasted about 20–40 minutes. The main goal of creating this dataset is to provide the research community with real driving scenarios that have diverse trajectories and driving behaviors. The dataset contains ego-vehicle’s waypoints, velocity, yaw angle, as well as non-ego actor’s waypoints, velocity, yaw angle, entry-time, and exit-time. Certain flexibility is provided to users so that actors, sensors, lanes, roads, and obstacles can be added to the existing scenarios. We used a Joint Probabilistic Data Association (JPDA) tracker to detect non-ego vehicles on the road. We present some preliminary results of the proposed dataset and a few applications associated with it. The complete dataset is expected to be released by early 2023. © 2022, CC BY.

关键词： Vehicles