检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Qiao, Xin Ge, Chenyang Zhang, Youmin Zhou, Yanhui Tosi, Fabio Poggi, Matteo Mattoccia, Stefano Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University No.28 West Xianning Road Xi’an710049 China Department of Computer Science and Engineering University of Bologna Viale Risorgimento 2 Bologna40136 Italy

Guided depth super-resolution aims at using a low-resolution depth map and an associated high-resolution RGB image to recover a high-resolution depth map. However, restoring precise and sharp edges near depth discontinuities and fine structures is still challenging for state-of-the-art methods. To alleviate this issue, we propose a novel multi-stage depth super-resolution network, which progressively reconstructs HR depth maps from explicit and implicit high-frequency information. We introduce an efficient transformer to obtain explicit high-frequency information. The shape bias and global context of the transformer allow our model to focus on high-frequency details between objects, i.e., depth discontinuities, rather than texture within objects. Furthermore, we project the input color images into the frequency domain for additional implicit high-frequency cues extraction. Finally, to incorporate the structural details, we develop a fusion strategy that combines depth features and high-frequency information in the multi-stage-scale framework. Exhaustive experiments on the main benchmarks show that our approach establishes a new state-of-the-art. Copyright © 2023, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Dreaming Learning

arXiv

引用

arXiv 2024年

作者： Londei, Alessandro Benati, Matteo Lanzieri, Denise Loreto, Vittorio Sony Computer Science Laboratories - Rome Joint Initiative CREF-SONY Centro Ricerche Enrico Fermi Via Panisperna 89/A Rome00184 Italy Department of Computer Automatic and Management Engineering Sapienza University Via Ariosto 25 Rome Italy Via Panisperna 89/A Rome00184 Italy Sapienza University of Rome Physics Department Piazzale A. Moro 2 Rome00185 Italy Complexity Science Hub Josefstädter Strasse 39 A Vienna1080 Austria

Incorporating novelties into deep learning systems remains a challenging problem. Introducing new information to a machine learning system can interfere with previously stored data and potentially alter the global model paradigm, especially when dealing with non-stationary sources. In such cases, traditional approaches based on validation error minimization offer limited advantages. To address this, we propose a training algorithm inspired by Stuart Kauffman’s notion of the Adjacent Possible. This novel training methodology explores new data spaces during the learning phase. It predisposes the neural network to smoothly accept and integrate data sequences with different statistical characteristics than expected. The maximum distance compatible with such inclusion depends on a specific parameter: the sampling temperature used in the explorative phase of the present method. This algorithm, called Dreaming Learning, anticipates potential regime shifts over time, enhancing the neural network’s responsiveness to non-stationary events that alter statistical properties. To assess the advantages of this approach, we apply this methodology to unexpected statistical changes in Markov chains and non-stationary dynamics in textual sequences. We demonstrated its ability to improve the auto-correlation of generated textual sequences by ∼ 29% and enhance the velocity of loss convergence by ∼ 100% in the case of a paradigm shift in Markov chains. © 2024, CC BY-NC-ND.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Visualized Malware Detection Framework with CNN and Conditional GAN

A Visualized Malware Detection Framework with CNN and Condit...

引用

IEEE International Conference on Big Data

作者： Fang Wang Hussam Al Hamadi Ernesto Damiani C2PS Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates College of Engineering and IT University of Dubai Dubai UAE

ISBN: (纸本)9781665480468

Malware visualization analysis incorporating with Machine Learning (ML) has been proven to be a promising solution for improving security defenses on different platforms. In this work, we propose an integrated framework for addressing common problems experienced by ML utilizers in developing malware detection systems. Namely, a pictorial presentation system with extensions is designed to preserve the identities of benign/malign samples by encoding each variable into binary digits and mapping them into black and white pixels. A conditional Generative Adversarial Network based model is adopted to produce synthetic images and mitigate issues of imbalance classes. Detection models architected by Convolutional Neural Networks are for validating performances while training on datasets with and without artifactual samples. Result demonstrates accuracy rates of 98.51% and 97.26% for these two training scenarios.

关键词： Training Data visualization Machine learning Big Data Generative adversarial networks Malware Encoding

来源：评论

学校读者我要写书评

暂无评论

MiNDesign: Toward a Modeling, Simulation and Evaluation Platform for Human Cognitive Performance

MiNDesign: Toward a Modeling, Simulation and Evaluation Plat...

引用

AHFE Virtual Conference on Human Factors and Simulation and the International Conference on Digital Human Modeling and Applied Optimization, 2020

作者： Tian, Zhiqiang Zhang, Liang Wang, Xin Liu, Yuzhou Li, Junsong Fu, Feng Liao, Zhen Liu, Yanfei China Institute of Marine Technology and Economic No. 70 Xueyuan South Road Haidian District Beijing100081 China Department of Computer Science and Software Engineering Auburn University AuburnAL36849 United States Department of Computer Science and Technology Zhejiang Sci-Tech University No. 928 2nd Avenue Xiasha Hangzhou310018 China

ISBN: (纸本)9783030510633

MiNDesign – an alternative way of human cognitive performance evaluation method is proposed and implemented in this paper. Firstly, the roadmap and whole framework of this solution are illustrated. Then, a cognitive architecture is setup as the basis of cognitive modeling for human behavior of this platform, and functions of each component and its key point are discussed. As an example, cognitive modeling and model-based cognitive performance evaluation for numeric keypad layout operating task are conducted. The results show that the way proposed in this paper is effective, objective and accurate than traditional rating scales and physiological measurement methods, and which has obvious advantages for human performance evaluation. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Virtual reality simulation in training endoscopic skills: A systematic review

引用

Laparoscopic, Endoscopic and Robotic Surgery 2021年第4期4卷 97-104页

作者： Wenlan Zhang Xin Liu Bin Zheng Surgical Simulation Research Laboratory Department of SurgeryUniversity of AlbertaEdmontonT6G 2E1Canada School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China

Objective:Training young physicians in gastrointestinal endoscopy through virtual reality(VR)simulators has become *** is important to evaluate the benefits and usefulness of this technology for teaching endoscopic *** objective of this literature review is to understand the benefits of VR technology through quantitative and qualitative examination of learning ***:A literature search of 7 databases was *** which compared the effects of learning through VR simulation and another method of learning were *** addition,studies were included if they evaluated learning outcomes on clinical *** could be medical residents,fellows,physicians,or *** outcomes measured across studies included subjective overall performance scores,total procedure times,rate of successful procedure completion,error rates,patient pain or discomfort,and measures of ***:A total of 22 studies were ***,VR simulation training was seen to be comparable or significantly better than clinical training,no training,other types of simulation,and another form of VR *** authors reported increasing patient safety,reducing stress and time constraints,and shortening the learning curve as advantages of VR simulation ***,this form of training is also expensive and may result in the learning of bad ***:VR simulation technology can be a valuable form of educating endoscopy novices if properly supervised during training,and if there is also integration of clinical training.

关键词： Gastrointestinal endoscopy Virtual reality simulation Physician Training Endoscopic skill

来源：评论

学校读者我要写书评

暂无评论

Cognitive Modeling and Model-Based Performance Evaluation on Collaborative Decision and Control Task

Cognitive Modeling and Model-Based Performance Evaluation on...

引用

AHFE Virtual Conferences on Neuroergonomics and Cognitive engineering, and Industrial Cognitive Ergonomics and engineering Psychology, 2020

作者： Wang, Xin Zhang, Liang Tian, Zhiqiang Liu, Yuzhou Li, Junsong Fu, Feng Liao, Zhen Liu, Yanfei China Institute of Marine Technology and Economic No. 70 Xueyuan South Road Haidian District Beijing100081 China Department of Computer Science and Software Engineering Auburn University AuburnAL36849 United States Department of Computer Science and Technology Zhejiang Sci-Tech University No. 928 2nd Avenue Xiasha Hangzhou310018 China

ISBN: (纸本)9783030510404

This paper designs a three positions collaborative decision making and control task for the purpose of investigating the collaboration performance. To build cognitive model for the collaborative decision-making task, the model and cognitive parameters are abstracted from realistic control task. Based on cognitive architecture, the cognitive model for the collaborative task are built up and verified by simulation. Depending on the cognitive workload quantifying criteria, the cognitive workload is obtained respectively. Finally, by comparing the cognitive process or tasks, the performance for the collaborative decision making and control tasks is evaluated. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration

arXiv

引用

arXiv 2024年

作者： Luo, Xinzhe Wang, Xin Shapiro, Linda Yuan, Chun Feng, Jianfeng Zhuang, Xiahai The School of Data Science Fudan University Shanghai200433 China The Department of Electrical and Electronic Engineering and I-X Imperial College London LondonSW7 2AZ United Kingdom The Department of Electrical and Computer Engineering University of Washington Seattle98195 United States The Paul G. Allen School of Computer Science and Engineering University of Washington Seattle98195 United States The Department of Radiology and Imaging Sciences University of Utah The Department of Radiology University of Washington Seattle98109 United States The Shanghai Center for Mathematical Sciences The Institute of Science and Technology for Brain-Inspired Intellengence Fudan University Shanghai200433 China National Natural Science Foundation of China China

This article presents a general Bayesian learning framework for multi-modal groupwise image registration. The method builds on probabilistic modelling of the image generative process, where the underlying common anatomy and geometric variations of the observed images are explicitly disentangled as latent variables. Therefore, groupwise image registration is achieved via hierarchical Bayesian inference. We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables, where the registration parameters can be explicitly estimated in a mathematically interpretable fashion. Remarkably, this new paradigm learns groupwise image registration in an unsupervised closed-loop self-reconstruction process, sparing the burden of designing complex image-based similarity measures. The computationally efficient disentangled network architecture is also inherently scalable and flexible, allowing for groupwise registration on large-scale image groups with variable sizes. Furthermore, the inferred structural representations from multi-modal images via disentanglement learning are capable of capturing the latent anatomy of the observations with visual semantics. Extensive experiments were conducted to validate the proposed framework, including four different datasets from cardiac, brain, and abdominal medical images. The results have demonstrated the superiority of our method over conventional similarity-based approaches in terms of accuracy, efficiency, scalability, and interpretability. Copyright © 2024, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Boosted Topological Zero Modes in Elastomer Waveguide Arrays

Boosted Topological Zero Modes in Elastomer Waveguide Arrays

引用

Frontiers in Optics, FiO 2022

作者： Frank, Angelina Leykam, Daniel Smirnova, Daria A. Angelakis, Dimitris G. Ling, Alexander Centre for Quantum Technologies National University of Singapore 3 Science Drive 2 Singapore117543 Singapore Nonlinear Physics Centre Research School of Physics Australian National University CanberraACT2601 Australia Institute of Applied Physics Russian Academy of Science Nizhny Novgorod603950 Russia School of Electrical and Computer Engineering Technical University of Crete Chania73100 Greece Department of Physics National University of Singapore 2 Science Drive 3 Singapore117551 Singapore

We demonstrate boosted topological zero modes in a strain-tuneable photonic polymer waveguide array. Modulating the topological defect speed illustrates the varying localization of the light field. Theoretical predict...

ISBN: (纸本)9781557528209

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secrecy Performance Analysis of Heterogeneous Networks With Unreliable Wireless Backhaul and Imperfect Channel Estimation

Secrecy Performance Analysis of Heterogeneous Networks With ...

引用

作者： Yin, Cheng Garcia-Palacios, Emiliano Xiao, Pei Sharma, Vishal Dobre, Octavia A. Duong, Trung Q. University of Surrey Institute for Communication Systems Home for 5GIC and 6GIC GuildfordGU2 7XH United Kingdom Queen's University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom Memorial University Faculty of Engineering and Applied Science St. John'sNLA1B 3X5 Canada Kyung Hee University Department of Electronic Engineering yeonggi-do Yongin-si17140 Korea Republic of

Wireless backhaul is an economical and flexible alternative to wired backhaul, however, it experiences impairments. This research proposes a new secure heterogeneous system model with unreliable wireless backhaul and imperfect channel estimation over Nakagami-m fading channel. To improve the system secrecy performance, we propose three small-cell transmitter selection schemes under channel estimation imperfections and wireless backhaul impairments, namely Optimum Selection (OS), Sub-optimum Selection (SS) and Minimum-Eavesdropping Selection (MES). Novel closed-form expressions of secrecy outage probability (SOP) are derived for these three selection schemes in both practical and ideal scenarios. The novel theoretical analysis and simulation results show the impact of wireless backhaul uncertainties and channel estimation errors on system secrecy performance. In addition, we investigate how the number of small-cell transmitters affects the system secrecy performance. The asymptotic behaviour is provided to obtain insights into the system performance. The analytical derivations and asymptotic expressions are validated by Monte Carlo simulations. Our novel theoretical analysis can guide different physical layer security (PLS) designs. © 1967-2012 IEEE.

关键词： Transmitters

来源：评论

学校读者我要写书评

暂无评论

Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential

arXiv

引用

arXiv 2025年

作者： Gao, Chenyu Xu, Kaiwen Kim, Michael E. Zuo, Lianrui Li, Zhiyuan Archer, Derek B. Hohman, Timothy J. Moore, Ann Zenobia Ferrucci, Luigi Beason-Held, Lori L. Resnick, Susan M. Davatzikos, Christos Prince, Jerry L. Landman, Bennett A. Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States Department of Computer Science Vanderbilt University NashvilleTN United States Vanderbilt Memory and Alzheimer’s Center Vanderbilt University Medical Center NashvilleTN United States Department of Neurology Vanderbilt University Medical Center NashvilleTN United States Translational Gerontology Branch National Institute on Aging National Institutes of Health BaltimoreMD United States Laboratory of Behavioral Neuroscience National Institute on Aging National Institutes of Health BaltimoreMD United States AI2D Center for AI and Data Science University of Pennsylvania Philadelphia United States Department of Electrical and Computer Engineering Johns Hopkins University BaltimoreMD United States

Defacing is often applied to head magnetic resonance image (MRI) datasets prior to public release to address privacy concerns. The alteration of facial and nearby voxels has provoked discussions about the true capability of these techniques to ensure privacy as well as their impact on downstream tasks. With advancements in deep generative models, the extent to which defacing can protect privacy is uncertain. Additionally, while the altered voxels are known to contain valuable anatomical information, their potential to support research beyond the anatomical regions directly affected by defacing remains uncertain. To evaluate these considerations, we develop a refacing pipeline that recovers faces in defaced head MRIs using cascaded diffusion probabilistic models (DPMs). The DPMs are trained on images from 180 subjects and tested on images from 484 unseen subjects, 469 of whom are from a different dataset. To assess whether the altered voxels in defacing contain universally useful information, we also predict computed tomography (CT)-derived skeletal muscle radiodensity from facial voxels in both defaced and original MRIs. The results show that DPMs can generate high-fidelity faces that resemble the original faces from defaced images, with surface distances to the original faces significantly smaller than those of a population average face (p -4). For shin muscle, the correlation is statistically significant (p 0.05) when any defacing method is applied, suggesting that defacing might not only fail to protect privacy but also eliminate valuable information. We advocate two solutions for data sharing that comply with privacy: 1) share skull-stripped images along with measurements of facial and cranial features extracted before skull-stripping for public access, while acknowledging that this approach inherently compromises many research potentials;or 2) share the unaltered images with privacy enforced through policy restrictions. © 2025, CC BY-NC-ND.

关键词： Magnetic resonance imaging

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：