检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ma, Jun Li, Feifei Kim, Sumin Asakereh, Reza Le, Bao-Hiep Nguyen-Vu, Dang-Khoa Pfefferle, Alexander Wei, Muxin Gao, Ruochen Lyu, Donghang Yang, Songxiao Purucker, Lennart Marinov, Zdravko Staring, Marius Lu, Haisheng Dao, Thuy Thanh Ye, Xincheng Li, Zhi Brugnara, Gianluca Vollmuth, Philipp Foltyn-Dumitru, Martha Cho, Jaeyoung Mahmutoglu, Mustafa Ahmed Bendszus, Martin Pflüger, Irada Rastogi, Aditya Ni, Dong Yang, Xin Zhou, Guang-Quan Wang, Kaini Heller, Nicholas Papanikolopoulos, Nikolaos Weight, Christopher Tong, Yubing Udupa, Jayaram K. Patrick, Cahill J. Wang, Yaqi Zhang, Yifan Contijoch, Francisco McVeigh, Elliot Ye, Xin He, Shucheng Haase, Robert Pinetz, Thomas Radbruch, Alexander Krause, Inga Kobler, Erich He, Jian Tang, Yucheng Yang, Haichun Huo, Yuankai Luo, Gongning Kushibar, Kaisar Amankulov, Jandos Toleshbayev, Dias Mukhamejan, Amangeldi Egger, Jan Pepe, Antonio Gsaxner, Christina Luijten, Gijs Fujita, Shohei Kikuchi, Tomohiro Wiestler, Benedikt Kirschke, Jan S. de la Rosa, Ezequiel Bolelli, Federico Lumetti, Luca Grana, Costantino Xie, Kunpeng Wu, Guomin Puladi, Behrus Martín-Isla, Carlos Lekadir, Karim Campello, Victor M. Shao, Wei Brisbane, Wayne Jiang, Hongxu Wei, Hao Yuan, Wu Li, Shuangle Zhou, Yuyin Wang, Bo AI Collaborative Centre University Health Network Department of Laboratory Medicine and Pathobiology University of Toronto Vector Institute Toronto Canada Peter Munk Cardiac Centre University Health Network Toronto Canada Toronto General Hospital Research Institute University Health Network Department of Computer Science University of Toronto University Health Network Vector Institute Toronto Canada University of Science Vietnam National University Ho Chi Minh City Viet Nam Institute of Computer Science University of Freiburg Freiburg Germany School of Medicine and Health Harbin Institute of Technology Harbin China Division of Image Processing Department of Radiology Leiden University Medical Center Leiden Netherlands Department of System and Control Engineering School of Engineering Institute of Science Tokyo Formerly Tokyo Institute of Technology Tokyo Japan Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe Germany School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical Engineering and Computer Science University of Queensland Brisbane Australia School of Cyberspace Hangzhou Dianzi University Hangzhou China Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Division for Computational Radiology and Clinical AI The Department of Neuroradiology University Hospital Bonn Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Division for Computational Radiology and Clinical AI Department of Neuroradiology University Hospital Bonn Germany School of Biomedical Engineering Shenzhen University Shenzhen China School of Biological Science and Medical Engineering Southeast University Nanjing China Department of Urology Cleveland Clinic Cleveland United States Department of Computer Science University of Minnesota Minneapolis United St

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications. © 2024, CC BY-NC-SA.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Learning privacy-enhancing face representations through feature disentanglement

Learning privacy-enhancing face representations through feat...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Blaž Bortolato Marija Ivanovska Peter Rot Janez Križaj Philipp Terhörst Naser Damer Peter Peer Vitomir Štruc Faculty of Electrical Engineering University of Ljubljana Ljubljana Slovenia Faculty of Computer and Information Science University of Ljubljana Ljubljana Slovenia Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany

ISBN: (数字)9781728130798

ISBN: (纸本)9781728130804

Convolutional Neural Networks (CNNs) are today the de-facto standard for extracting compact and discriminative face representations (templates) from images in automatic face recognition systems. Due to the characteristics of CNN models, the generated representations typically encode a multitude of information ranging from identity to soft-biometric attributes, such as age, gender or ethnicity. However, since these representations were computed for the purpose of identity recognition only, the soft-biometric information contained in the templates represents a serious privacy risk. To mitigate this problem, we present in this paper a privacy-enhancing approach capable of suppressing potentially sensitive soft-biometric information in face representations without significantly compromising identity information. Specifically, we introduce a Privacy-Enhancing Face-Representation learning Network (PFRNet) that disentangles identity from attribute information in face representations and consequently allows to efficiently suppress soft-biometrics in face templates. We demonstrate the feasibility of PFRNet on the problem of gender suppression and show through rigorous experiments on the CelebA, Labeled Faces in the Wild (LFW) and Adience datasets that the proposed disentanglement-based approach is highly effective and improves significantly on the existing state-of-the-art.

关键词： Face recognition Privacy Training Neural networks Decoding Training data Task analysis

来源：评论

学校读者我要写书评

暂无评论

The ZTF Source Classification Project: III. A Catalog of Variable Sources

arXiv

引用

arXiv 2023年

作者： Healy, Brian F. Coughlin, Michael W. Mahabal, Ashish A. Laz, Theophile Jegou du Drake, Andrew Graham, Matthew J. Hillenbrand, Lynne A. van Roestel, Jan Szkody, Paula Zielske, LeighAnna Guiga, Mohammed Hassan, Muhammad Yusuf Hughes, Jill L. Nir, Guy Parikh, Saagar Park, Sungmin Purohit, Palak Rebbapragada, Umaa Reed, Draco Warshofsky, Daniel Wold, Avery Bloom, Joshua S. Masci, Frank J. Riddle, Reed Smith, Roger School of Physics and Astronomy University of Minnesota MinneapolisMN55455 United States Division of Physics Mathematics and Astronomy California Institute of Technology PasadenaCA91125 United States Center for Data Driven Discovery California Institute of Technology PasadenaCA91125 United States Department of Astronomy California Institute of Technology PasadenaCA91125 United States Anton Pannekoek Institute for Astronomy University of Amsterdam Amsterdam1090 GE Netherlands Department of Astronomy University of Washington SeattleWA98195 United States Department of Physics Pacific Lutheran University TacomaWA98447 United States Department of Computer Science and Engineering University of Minnesota MinneapolisMN55455 United States Department of Electrical Engineering Indian Institute of Technology Gandhinagar Gujarat 382055 India Department of Astronomy University of California BerkeleyCA94720 United States Lawrence Berkeley National Laboratory 1 Cyclotron Road MS 50B-4206 BerkeleyCA94720 United States Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA15213 United States Computer Vision Imaging and Graphics Lab Indian Institute of Technology Gujarat Gandhinagar382055 India School of Statistics University of Minnesota MinneapolisMN55455 United States Division of Engineering and Applied Science California Institute of Technology PasadenaCA91125 United States Jet Propulsion Laboratory California Institute of Technology PasadenaCA91125 United States IPAC California Institute of Technology 1200 E. California Blvd. PasadenaCA91125 United States Caltech Optical Observatories California Institute of Technology PasadenaCA91125 United States

The classification of variable objects provides insight into a wide variety of astrophysics ranging from stellar interiors to galactic nuclei. The Zwicky Transient Facility (ZTF) provides time-series observations that record the variability of more than a billion sources. The scale of these data necessitates automated approaches to make a thorough analysis. Building on previous work, this paper reports the results of the ZTF Source Classification Project (SCoPe), which trains neural network and XGBoost machine-learning (ML) algorithms to perform dichotomous classification of variable ZTF sources using a manually constructed training set containing 170,632 light curves. We find that several classifiers achieve high precision and recall scores, suggesting the reliability of their predictions for 209,991,147 light curves across 77 ZTF fields. We also identify the most important features for XGB classification and compare the performance of the two ML algorithms, finding a pattern of higher precision among XGB classifiers. The resulting classification catalog is available to the public, and the software developed for SCoPe is open-source and adaptable to future time-domain surveys. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Efficient Recovery of Multi-Camera Motion from Two Affine Correspondences

Efficient Recovery of Multi-Camera Motion from Two Affine Co...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Banglei Guan Ji Zhao Daniel Barath Friedrich Fraundorfer College of Aerospace Science and Engineering National University of Defense Technology China Centre for Machine Perception Czech Technical University Czech Republic Machine Perception Research Laboratory MTA SZTAKI Hungary Institute for Computer Graphics and Vision Graz University of Technology Austria Remote Sensing Technology Institute German Aerospace Center Germany

We propose an efficient method to estimate the relative pose of a multi-camera system from a minimum of two affine correspondences (ACs). Our solution is novel as it computes the 6DOF relative pose by utilizing a first-order rotation approximation. We directly derive a single polynomial based on the constraint between ACs and the generalized camera model. Then a closed-form solution is found analytically and it produces an accurate relative pose estimation efficiently. Benefiting from the low number of exploited correspondences and the speed of the solver, it speeds up robust estimators, e.g. RANSAC, significantly. The proposed method is evaluated both on synthetic data and real-world image sequences from the KITTI benchmark. It is shown that the proposed solver is superior to the state-of-the-art algorithms in terms of accuracy.

关键词： Closed-form solutions Automation Computational modeling Roads Conferences Pose estimation Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Ecological Adaptive Cruise Control for Urban Environments using SPaT Information

Ecological Adaptive Cruise Control for Urban Environments us...

引用

IEEE Conference on Vehicle Power and Propulsion (VPPC)

作者： Sai Krishna Chada Ankith Purbai Daniel Görges Achim Ebert Roman Teutsch Electromobility Research Group University of Kaiserslautern Germany Computer Graphics and HCI Group University of Kaiserslautern Germany Institute for Mechanical and Automotive Engineering University of Kaiserslautern Germany

ISBN: (数字)9781728189598

ISBN: (纸本)9781728189604

This paper proposes an ecological adaptive cruise control (EACC) strategy to minimize the energy consumption of an electric vehicle using two linear model predictive controllers (MPCs). In the absence of a preceding vehicle, the first MPC uses the upcoming traffic light signal phase and timing (SPaT) information to track an optimal green-wave velocity to reach the next traffic light signal during green phase. For the preceding vehicle in range scenario, the second MPC follows the leading vehicle by maintaining a desired inter-vehicle distance and strictly adheres to road speed limits. If the upcoming traffic light signal phase is changing to red, the controller uses the SPaT information to plan an energy-efficient stop near the traffic light signal. To evaluate the performance of the proposed strategy, both controllers are tested in a realistic scenario against a baseline controller and furthermore their energy saving benefits are explored. Finally, investigations on computation time reveal that the proposed strategy is capable for online implementation.

关键词： Energy consumption Green products Urban areas Predictive models Electric vehicles Real-time systems Timing

来源：评论

学校读者我要写书评

暂无评论

A variational method for accurate distance function estimation 9th

A variational method for accurate distance function estimati...

引用

9th International Conference on Numerical Geometry, Grid Generation, and Scientific Computing, celebrating the 150th anniversary of Georgy F. Voronoi, NUMGRID 2018

作者： Belyaev, Alexander G. Fayolle, Pierre-Alain Institute of Sensors Signals and Systems School of Engineering & Physical Sciences Heriot-Watt University Edinburgh United Kingdom Computer Graphics Laboratory University of Aizu Aizu-Wakamatsu Japan

Variational problems for accurate approximation of the distance from the boundary of a domain are studied. It is demonstrated that the problems can be efficiently solved by ADMM. Advantages of the proposed distance fu... 详细信息

ISBN: (纸本)9783030234355

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Minimal Cases for Computing the Generalized Relative Pose using Affine Correspondences

arXiv

引用

arXiv 2020年

作者： Guan, Banglei Zhao, Ji Barath, Daniel Fraundorfer, Friedrich College of Aerospace Science and Engineering National University of Defense Technology China Computer Vision and Geometry Group Department of Computer Science ETH Zürich Institute for Computer Graphics and Vision Graz University of Technology Austria Remote Sensing Technology Institute German Aerospace Center Germany

We propose three novel solvers for estimating the relative pose of a multi-camera system from affine correspondences (ACs). A new constraint is derived interpreting the relationship of ACs and the generalized camera model. Using the constraint, we demonstrate efficient solvers for two types of motions assumed. Considering that the cameras undergo planar motion, we propose a minimal solution using a single AC and a solver with two ACs to overcome the degenerate case. Also, we propose a minimal solution using two ACs with known vertical direction, e.g., from an IMU. Since the proposed methods require significantly fewer correspondences than state-of-the-art algorithms, they can be efficiently used within RANSAC for outlier removal and initial motion estimation. The solvers are tested both on synthetic data and on real-world scenes from the KITTI odometry benchmark. It is shown that the accuracy of the estimated poses is superior to the state-of-the-art techniques. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Assessing users' privacy and security concerns of smart home technologies

引用

i-com 2020年第3期18卷 197-216页

作者： Zimmermann, Verena Gerber, Paul Marky, Karola Böck, Leon Kirchbuchner, Florian Work and Engineering Psychology Technische Universität Darmstadt Darmstadt Germany Telecooperation Lab Technische Universität Darmstadt Darmstadt Germany Keio University Yokohama Japan Fraunhofer Institute for Computer Graphics Darmstadt Germany

Smart Home technologies have the potential to increase the quality of life, home security and facilitate elderly care. Therefore, they require access to a plethora of data about the users' homes and private lives. Resulting security and privacy concerns form a relevant barrier to adopting this promising technology. Aiming to support end users' informed decision-making through addressing the concerns we first conducted semi-structured interviews with 42 potential and little-experienced Smart Home users. Their diverse concerns were clustered into four themes that center around attacks on Smart Home data and devices, the perceived loss of control, the trade-off between functionality and security, and user-centric concerns as compared to concerns on a societal level. Second, we discuss measures to address the four themes from an interdisciplinary perspective. The paper concludes with recommendations for addressing user concerns and for supporting developers in designing user-centered Smart Home technologies. © 2019 Walter de Gruyter GmbH, Berlin/Boston 2019.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Privacy Evaluation Protocols for the Evaluation of Soft-Biometric Privacy-Enhancing Technologies

Privacy Evaluation Protocols for the Evaluation of Soft-Biom...

引用

International Conference of the Biometrics Special Interest Group (BIOSIG)

作者： Philipp Terhörst Marco Huber Naser Damer Peter Rot Florian Kirchbuchner Vitomir Struc Arjan Kuijper Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Mathematical and Applied Visual Computing TU Darmstadt Darmstadt Germany Faculty of Electrical Engineering University of Ljubljana Ljubljana Slovenia

ISBN: (数字)9783885797005

ISBN: (纸本)9781728189277

Biometric data includes privacy-sensitive information, such as soft-biometrics. Soft-biometric privacy enhancing technologies aim at limiting the possibility of deducing such information. Previous works proposed several solutions to this problem using several different evaluation processes, metrics, and attack scenarios. The absence of a standardized evaluation protocol makes a meaningful comparison of these solutions difficult. In this work, we propose privacy evaluation protocols (PEPs) for privacy-enhancing technologies (PETs) dealing with soft-biometric privacy. Our framework evaluates PETs in the most critical scenario of an attacker that knows and adapts to the systems privacy-mechanism. Moreover, our PEPs differentiate between PET of learning-based or training-free nature. To ensure that our protocol meets the highest standards in both cases, it is based on Kerckhoffs`s principle of cryptography.

关键词： Protocols Faces Privacy Training Creep Data privacy Face recognition

来源：评论

学校读者我要写书评

暂无评论

Robust computation of subcortical functional connectivity guided by quantitative susceptibility mapping: An application in Parkinson's disease diagnosis

引用

NeuroImage 2025年 314卷 121256-121256页

作者： Qin, Jianmei Wu, Haoting Wu, Chenqing Guo, Tao Zhou, Cheng Duanmu, Xiaojie Tan, Sijia Wen, Jiaqi Zheng, Qianshi Yuan, Weijin Zhu, Zihao Chen, Jingwen Wu, Jingjing He, Chenyu Ma, Yiran Liu, Chunlei Xu, Xiaojun Guan, Xiaojun Zhang, Minming Department of Radiology the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou China Joint Laboratory of Clinical Radiology the Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou China State Key Laboratory of Computer-aided Design & Computer Graphics Zhejiang University College of Computer Science and technology Hangzhou China State Key Laboratory of Industrial Control Technology Zhejiang University College of Control Science and Engineering Hangzhou China Department of Electrical Engineering and Computer Sciences University of California Berkeley CA United States Helen Wills Neuroscience Institute University of California Berkeley CA United States

Previous resting state functional MRI (rs-fMRI) analyses of the basal ganglia in Parkinson's disease heavily relied on T1-weighted imaging (T1WI) atlases. However, subcortical structures are characterized by subtle contrast differences, making their accurate delineation challenging on T1WI. In this study, we aimed to introduce and validate a method that incorporates quantitative susceptibility mapping (QSM) into the rs-fMRI analytical pipeline to achieve precise subcortical nuclei segmentation and improve the stability of RSFC measurements in Parkinson's disease. A total of 321 participants (148 patients with Parkinson's Disease and 173 normal controls) were enrolled. We performed cross-modal registration at the individual level for rs-fMRI to QSM (FUNC2QSM) and T1WI (FUNC2T1), *** consistency and accuracy of resting state functional connectivity (RSFC) measurements in two registration approaches were assessed by intraclass correlation coefficient and mutual information. Bootstrap analysis was performed to validate the stability of the RSFC differences between Parkinson's disease and normal controls. RSFC-based machine learning models were constructed for Parkinson's disease classification, using optimized hyperparameters (RandomizedSearchCV with 5-fold cross-validation). The consistency of RSFC measurements between the two registration methods was poor, whereas the QSM-guided approach showed better mutual information values, suggesting higher registration accuracy. The disruptions of RSFC identified with the QSM-guided approach were more stable and reliable, as confirmed by bootstrap analysis. In classification models, the QSM-guided method consistently outperformed the T1WI-guided method, achieving higher test-set ROC-AUC values (FUNC2QSM: 0.87–0.90, FUNC2T1: 0.67–0.70). The QSM-guided approach effectively enhanced the accuracy of subcortical segmentation and the stability of RSFC measurement, thus facilitating future biomarker development in Parkinso

关键词： Parkinson's disease Quantitative susceptibility mapping Resting-state functional connectivity Subcortical nuclei

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：