首页期刊导航|计算机科学技术学报（英文版）
期刊信息/Journal information
计算机科学技术学报（英文版）
计算机科学技术学报（英文版）

李国杰

双月刊

1000-9000

jcst@ict.ac.cn

010-62610746

100080

北京中关村科学院南路6号 《计算机科学技术学报（英）》编辑部

计算机科学技术学报（英文版）/Journal Journal of Computer Science and TechnologyCSCDCSTPCD北大核心EISCI
查看更多>>Journal of Computer Science and Technology(JCST)是中国计算机科学技术领域国际性学术期刊。 JCST于1986 年创刊, 双月刊, 国内外公开发行, 由Springer Science + Business Media代理国际出版发行。 JCST是中国计算机学会会刊, 由中国科学院计算技术研究所承办。JCST由数十位国际计算机界的著名专家和学者联袂编审，把握世界计算机科学技术最新发展趋势。JCST荟萃了国内外计算机科学技术领域中有指导性和开拓性的学术论著，定期组织热点专辑或专题栏目，部分文章邀请了世界著名计算机科学专家撰写。
正式出版
收录年代

    Combining KNN with AutoEncoder for Outlier Detection

    刘叔正马帅陈瀚清崔立真...
    1153-1166页
    查看更多>>摘要：K-nearest neighbor(KNN)is one of the most fundamental methods for unsupervised outlier detection be-cause of its various advantages,e.g.,ease of use and relatively high accuracy.Currently,most data analytic tasks need to deal with high-dimensional data,and the KNN-based methods often fail due to"the curse of dimensionality".AutoEn-coder-based methods have recently been introduced to use reconstruction errors for outlier detection on high-dimensional data,but the direct use of AutoEncoder typically does not preserve the data proximity relationships well for outlier detec-tion.In this study,we propose to combine KNN with AutoEncoder for outlier detection.First,we propose the Nearest Neighbor AutoEncoder(NNAE)by persevering the original data proximity in a much lower dimension that is more suit-able for performing KNN.Second,we propose the K-nearest reconstruction neighbors(KNRNs)by incorporating the re-construction errors of NNAE with the K-distances of KNN to detect outliers.Third,we develop a method to automatical-ly choose better parameters for optimizing the structure of NNAE.Finally,using five real-world datasets,we experimen-tally show that our proposed approach NNAE+KNRN is much better than existing methods,i.e.,KNN,Isolation Forest,a traditional AutoEncoder using reconstruction errors(AutoEncoder-RE),and Robust AutoEncoder.
      原文链接:
    • 万方数据
    • 维普

    Point-Voxel Based Geometry-Adaptive Network for 3D Point Cloud Analysis

    赵天孟曾慧张保庆刘红敏...
    1167-1179页
    查看更多>>摘要：Point cloud analysis is challenging because of the unordered and irregular data structure of point clouds.To describe geometric information in point clouds,existing methods mainly use convolution,graph,and attention operations to construct sophisticated local aggregation operators.These operators work well in extracting local information but bring unfavorable inference latency due to high computation complexity.To solve the above problem,this paper presents a nov-el point-voxel based geometry-adaptive network(PVGANet),which combines multiple representations of point and voxel to describe the point cloud from different granularities and can obtain features of different scales effectively.To extract fine-grained geometric features,we design the position-adaptive pooling operator,which uses point pairs'relative position and feature similarity to weight and aggregate the point features at local areas of point clouds.To extract coarse-grained local features,we design a depth-wise convolution operator,which conducts the depth-wise convolution on voxel grids.With an easy addition,fine-grained geometric and coarse-grained local features can be fused,and we can use the geometry-adaptive fused features to complete the efficient shape analysis of point clouds,such as shape classification and part seg-mentation.Extensive experiments on ModelNet40,ScanObjectNN,and ShapeNet Part benchmarks demonstrate that our PVGANet achieves competitive performance compared with the related methods.
      原文链接:
    • 万方数据
    • 维普

    ScenePalette:Contextually Exploring Object Collections Through Multiplex Relations in 3D Scenes

    张少魁谢威宇王琛张松海...
    1180-1192页
    查看更多>>摘要：This paper presents ScenePalette,a modeling tool that allows users to"draw"3D scenes interactively by placing objects on a canvas based on their contextual relationship.ScenePalette is inspired by an important intuition which was often ignored in previous work:a real-world 3D scene consists of the contextually reasonable organization of ob-jects,e.g.people typically place one double bed with several subordinate objects into a bedroom instead of different shapes of beds.ScenePalette,abstracts 3D repositories as multiplex networks and accordingly encodes implicit relations between or among objects.Specifically,basic statistics such as co-occurrence,in combination with advanced relations,are used to tackle object relationships of different levels.Extensive experiments demonstrate that the latent space of ScenePalette has rich contexts that are essential for contextual representation and exploration.
      原文链接:
    • 万方数据
    • 维普

    New Proper Reparameterization of Plane Rational Bézier Curves

    王振飞陈小雕雍俊海
    1193-1206页
    查看更多>>摘要：Coincidence detection of two curves or two surfaces has wide application in computer-aided design(CAD)and computer-aided geometric design(CAGD).Proper reparameterization is the most complicated part in the detection.This paper presents and proves the efficient and necessary coincidence condition for two rational Bezier curves in a new way.It also proposes an effective and efficient proper reparameterization method,Algorithm 1,for detecting a rational Bézier curve which can be degenerated into a new one of a lower degree.A numerical proper reparameterization method,Algorithm 2,and examples are also presented.Algorithm 1 is up to ten times faster than other prevailing methods,and Algorithm 2 is twice as fast and half as close as other prevailing methods.New CAD systems using Algorithm 1 and Algo-rithm 2 will hold accuracy and little computation time.
      原文链接:
    • 万方数据
    • 维普

    The t/s-Diagnosability and Diagnostic Strategy of Balanced Hypercube Under Two Classic Diagnostic Models

    柳晓青周书明Eddie Cheng张红...
    1207-1222页
    查看更多>>摘要：Fault diagnosis plays a crucial role in the fault tolerability assessment of an interconnection network,which is of great value in the design and maintenance of large-scale multiprocessor systems.A t/s-diagnostic strategy,as the generalization of the t/t-diagnostic strategy,refers to the self-diagnosis of a multiprocessor system in which all faulty ver-tices can be identified in a set of size at most s in the presence of at most t faulty vertices.In this work,we show that the balanced hypercube BHn(n ≥ 4)is((2n+1)「g/2(])-「g/2(])2)/((2n+1)「g/2(])-「g/2(])2+(g-2))-diagnosable under both the Preparata,Metze,and Chien(PMC)and MM*models for 4≤「g/2(])≤n.Moreover,we propose two effective t/s-diagnosis algorithms under the PMC and MM*models with time complexity O(NlogN)and O(N(logN)2)(N=22n is the order of BHn),respectively.Finally,comparison results indicate that t/s-diagnosability strengthens the self-diag-nosable capability of the system compared with traditional diagnosabilities.
      原文链接:
    • 万方数据
    • 维普