检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： A.M. Waxman J. Wu F. Bergholm Laboratory for Sensory Robotics College of Engineering Boston University Boston MA USA Computer Vision and Graphics Laboratory Department of Numerical Analysis and Computing Science Royal Institute of Technology Stockholm Sweden

A method is developed for the measurement of short-range visual motion in image sequences, making use of the motion of image features such as edges and points. Each feature generates a Gaussian activation profile in a spatiotemporal neighborhood of specified scale around the feature itself; this profile is then convected with motion of the feature. The authors show that image velocity estimates can be obtained from such dynamic activation profiles using a modification of familiar gradient techniques. The resulting estimators can be formulated in terms of simple ratios of spatiotemporal filters (i.e. receptive fields) convolved with image feature maps. A family of activation profiles of varying scale must be utilized to cover a range of possible image velocities. They suggest a characteristic speed normalization of the estimate obtained from each filter in order to decide which estimate is to be accepted. They formulate the velocity estimators for dynamic edges in 1-D and 2-D image sequences, as well as that for dynamic feature points in 2-D image sequences.< >

关键词： Motion measurement Image sequences Motion analysis Filters Laboratories Computer vision Robot sensing systems Educational institutions Computer graphics numerical analysis

来源：评论

学校读者我要写书评

暂无评论

iLGaCo: Incremental learning of gait covariate factors

arXiv

引用

arXiv 2020年

作者： Mu, Zihao Castro, Francisco M. Marín-Jiménez, Manuel J. Guil, Nicolás Li, Yan-Ran Yu, Shiqi College of Computer Science and Software Engineering Shenzhen University China Department of Computer Architecture University of Málaga Spain Department of Computing and Numerical Analysis University of Córdoba Spain China Department of Computer Science and Engineering Southern University of Science and Technology China

Gait is a popular biometric pattern used for identifying people based on their way of walking. Traditionally, gait recognition approaches based on deep learning are trained using the whole training dataset. In fact, if new data (classes, view-points, walking conditions, etc.) need to be included, it is necessary to re-train again the model with old and new data samples. In this paper, we propose iLGaCo, the first incremental learning approach of covariate factors for gait recognition, where the deep model can be updated with new information without re-training it from scratch by using the whole dataset. Instead, our approach performs a shorter training process with the new data and a small subset of previous samples. This way, our model learns new information while retaining previous knowledge. We evaluate iLGaCo on CASIA-B dataset in two incremental ways: adding new view-points and adding new walking conditions. In both cases, our results are close to the classical ‘training-from-scratch’ approach, obtaining a marginal drop in accuracy ranging from 0.2% to 1.2%, what shows the efficacy of our approach. In addition, the comparison of iLGaCo with other incremental learning methods, such as LwF and iCarl, shows a significant improvement in accuracy, between 6% and 15% depending on the experiment. Copyright © 2020, The Authors. All rights reserved.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

A computational model of depth-based attention

A computational model of depth-based attention

引用

International Conference on Pattern Recognition

作者： A. Maki P. Nordlund J.-O. Eklundh TOSHIBA Kansai Research Laboratory Royal Institute of Technology Motoyama Japan Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science Royal Institute of Technology Stockholm Sweden

We present a computational model for attention. It consists of an early parallel stage with preattentive cues followed by a later serial stage, where the cues are integrated. We base the model on disparity image flow and motion. As one of the several possibilities we choose a depth-based criterion to integrate these cues, in such a way that the attention is maintained to the closest moving object. We demonstrate the technique by experiments in which a moving observer selectively mask our different moving objects in real scenes.

关键词： Computational modeling Computer vision Layout Phase estimation Laboratories numerical analysis Psychology Humans Computational efficiency Stability

来源：评论

学校读者我要写书评

暂无评论

Evaluating associative classification algorithms for Big Data

引用

Big Data Analytics 2019年第1期4卷 1-27页

作者： Padillo, Francisco Luna, José María Ventura, Sebastián Department of Computer Science and Numerical Analysis University of Cordoba Cordoba Spain Knowledge Discovery and Intelligent Systems in Biomedicine Laboratory Maimonides Biomedical Research Institute of Cordoba Cordoba Spain Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

Associative Classification, a combination of two important and different fields (classification and association rule mining), aims at building accurate and interpretable classifiers by means of association rules. A major problem in this field is that existing proposals do not scale well when Big Data are considered. In this regard, the aim of this work is to propose adaptations of well-known associative classification algorithms (CBA and CPAR) by considering different Big Data platforms (Spark and Flink). An experimental study has been performed on 40 datasets (30 classical datasets and 10 Big Data datasets). Classical data have been used to find which algorithms perform better sequentially. Big Data dataset have been used to prove the scalability of Big Data proposals. Results have been analyzed by means of non-parametric tests. Results proved that CBA-Spark and CBA-Flink obtained interpretable classifiers but it was more time consuming than CPAR-Spark or CPAR-Flink. In this study, it was demonstrated that the proposals were able to run on Big Data (file sizes up to 200 GBytes). The analysis of different quality metrics revealed that no statistical difference can be found for these two approaches. Finally, three different metrics (speed-up, scale-up and size-up) have also been analyzed to demonstrate that the proposals scale really well on Big Data. The experimental study has revealed that sequential algorithms cannot be used on large quantities of data and approaches such as CBA-Spark, CBA-Flink, CPAR-Spark or CPAR-Flink are required. CBA has proved to be very useful when the main goal is to obtain highly interpretable results. However, when the runtime has to be minimized CPAR should be used. No statistical difference could be found between the two proposals in terms of quality of the results except for the interpretability of the final classifiers, CBA being statistically better than CPAR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feasibility of Acousto-Electric Tomography

arXiv

引用

arXiv 2019年

作者： Jensen, Bjørn Kirkeby, Adrian Knudsen, Kim Faculty of Information Technology University of Jyväskylä Finland Department of Numerical Analysis and Scientific Computing Simula Research Laboratory Oslo Norway Department of Applied Mathematics and Computer Science Technical University of Denmark Kgs Lyngby Denmark

In acousto-electric tomography the goal is to reconstruct the electric conductivity in a domain from electrostatic boundary measurements of corresponding currents and voltages, while the domain is penetrated by a time-dependent acoustic wave. In this paper we provide an in-silico model of the entire coupled physics scenario and perform computational experiments. We propose a complete inversion framework for acousto-electric tomography in two steps: First the interior power density is obtained from boundary measurements by solving a linear inverse problem;second the interior conductivity is reconstructed from the power density by solving a non-linear, fairly well-posed problem. We develop a numerical model with realistically chosen parameters inspired by medical imaging. The critical signal strength is analyzed and the omnipresent Johnson-Nyquist noise is estimated. With this setup we perform numerical experiments on synthetic data with noise and demonstrate the feasibility of the method. However, our findings are a mix of positive and negative. We reconstruct features even under severe noise conditions, but we also find that the required Signal-to-Noise ratio yet remains infeasible for practical *** Codes 35R30, 65N21 Copyright © 2019, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Trends in Applied Intelligent Systems 1

引用

丛书名： Lecture Notes in Computer science

1000年

作者： Nicolás García-Pedrajas Francisco Herrera Colin Fyfe José Manuel Benítez Moonis Ali

来源：评论

学校读者我要写书评

暂无评论

Trends in Applied Intelligent Systems 1

引用

丛书名： Lecture Notes in Computer science

1000年

作者： Nicolás García-Pedrajas Francisco Herrera Colin Fyfe José Manuel Benítez Moonis Ali

来源：评论

学校读者我要写书评

暂无评论

Trends in Applied Intelligent Systems 1

引用

丛书名： Lecture Notes in Computer science

1000年

作者： Nicolás García-Pedrajas Francisco Herrera Colin Fyfe José Manuel Benítez Moonis Ali

来源：评论

学校读者我要写书评

暂无评论

Complexity and Approximation 1

引用

1000年

作者： Giorgio Ausiello Alberto Marchetti-Spaccamela Pierluigi Crescenzi Giorgio Gambosi Marco Protasi Viggo Kann

ISBN: (数字)9783642584121

ISBN: (纸本)9783540654315;9783642635816

N COMPUTER applications we are used to live with approximation. Var I ious notions of approximation appear, in fact, in many circumstances. One notable example is the type of approximation that arises in numer ical analysis or in computational geometry from the fact that we cannot perform computations with arbitrary precision and we have to truncate the representation of real numbers. In other cases, we use to approximate com plex mathematical objects by simpler ones: for example, we sometimes represent non-linear functions by means of piecewise linear ones. The need to solve difficult optimization problems is another reason that forces us to deal with approximation. In particular, when a problem is computationally hard (i. e. , the only way we know to solve it is by making use of an algorithm that runs in exponential time), it may be practically unfeasible to try to compute the exact solution, because it might require months or years of machine time, even with the help of powerful parallel computers. In such cases, we may decide to restrict ourselves to compute a solution that, though not being an optimal one, nevertheless is close to the optimum and may be determined in polynomial time. We call this type of solution an approximate solution and the corresponding algorithm a polynomial-time approximation algorithm. Most combinatorial optimization problems of great practical relevance are, indeed, computationally intractable in the above sense. In formal terms, they are classified as Np-hard optimization problems.

关键词： Programming Techniques Algorithm analysis and Problem Complexity Computational Mathematics and numerical analysis Discrete Mathematics in Computer science Operations Research/Decision Theory IT in Business

来源：评论

学校读者我要写书评

暂无评论

Finite element simulation of ionic electrodiffusion in cellular geometries

arXiv

引用

arXiv 2019年

作者： Ellingsrud, A.J. Solbrå, A. Einevoll, G.T. Halnes, G. Rognes, M.E. Department for Scientific Computing and Numerical Analysis Simula Research Laboratory Norway Centre for Integrative Neuroplasticity University of Oslo Oslo Norway Department of Physics University of Oslo Oslo Norway Faculty of Science and Technology Norwegian University of Life Sciences Ås Norway

Mathematical models for excitable cells are commonly based on cable theory, which considers a homogenized domain and spatially constant ionic concentrations. Although such models provide valuable insight, the effect of altered ion concentrations or detailed cell morphology on the electrical potentials cannot be captured. In this paper, we discuss an alternative approach to detailed modelling of electrodiffusion in neural tissue. The mathematical model describes the distribution and evolution of ion concentrations in a geometrically-explicit representation of the intra- and extracellular domains. As a combination of the electroneutral Kirchhoff-Nernst-Planck (KNP) model and the Extracellular-Membrane-Intracellular (EMI) framework, we refer to this model as the KNP-EMI model. Here, we introduce and numerically evaluate a new, finite element-based numerical scheme for the KNP-EMI model, capable of efficiently and flexibly handling geometries of arbitrary dimension and arbitrary polynomial degree. Moreover, we compare the electrical potentials predicted by the KNP-EMI and EMI models. Finally, we study ephaptic coupling induced in an unmyelinated axon bundle and demonstrate how the KNP-EMI framework can give new insights in this setting. Copyright © 2019, The Authors. All rights reserved.

关键词： Finite element method

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：