无需人工干预的关节点提取和三维重建

随着现在人体的运动捕获和行为理解的研究的发展,对这项研究有了越来越高的要求。相对于原来的手动提取人体关节点作为特征点来研究,如何使得提取特征点更加自动化,对以后的运动捕获和行为理解的研究意义重大。提出一种在单目视觉条件下在第一帧自动提取人体关节点位置的方法,来解决传统的以手动标定提取人体关节点的问题,并且利用光流稀疏L_K算法 对提取出的关节点进行运动跟踪,得到运动人体二维坐标信息,结合像机模型通过几何计算获得人体关节点的深度信息。     

连通图中关节点的判定算法

文章提出了一种连通图关节点的矩阵求解算法,该算法数据结构形式简单,求解方便且易于理解,用C语言设计了相应的程序验证了此算法.     

Minimal Structure of Self-Organizing HCMAC Neural Network Classifier

The authors previously proposed a self-organizing Hierarchical Cerebellar Model Articulation Controller (HCMAC) neural network containing a hierarchical GCMAC neural network and a self-organizing input space module to solve high-dimensional pattern classification problems. This novel neural network exhibits fast learning, a low memory requirement, automatic memory parameter determination and highly accurate high-dimensional pattern classification. However, the original architecture needs to be hierarchically expanded using a full binary tree topology to solve pattern classification problems according to the dimension of the input vectors. This approach creates many redundant GCMAC nodes when the dimension of the input vectors in the pattern classification problem does not exactly match that in the self-organizing HCMAC neural network. These redundant GCMAC nodes waste memory units and degrade the learning performance of a self-organizing HCMAC neural network. Therefore, this study presents a minimal structure of self-organizing HCMAC (MHCMAC) neural network with the same dimension of input vectors as the pattern classification problem. Additionally, this study compares the learning performance of this novel learning structure with those of the BP neural network,support vector machine (SVM), and original self-organizing HCMAC neural network in terms of ten benchmark pattern classification data sets from the UCI machine learning repository. In particular, the experimental results reveal that the self-organizing MHCMAC neural network handles high-dimensional pattern classification problems better than the BP, SVM or the original self-organizing HCMAC neural network. Moreover, the proposed self-organizing MHCMAC neural network significantly reduces the memory requirement of the original self-organizing HCMAC neural network, and has a high training speed and higher pattern classification accuracy than the original self-organizing HCMAC neural network in most testing benchmark data sets. The experimental results also show that the MHCMAC neural network learns continuous function well and is suitable for Web page classification.     

Positioning and animating human figures in a task-oriented environment

TEMPUS is an interactive graphics system which enables a user to model the task-oriented activities of several human agents in a three-dimensional environment. The user can create one or more human figures which are correctly scaled according to a specific population, or which meet certain size constraints. These figures may be viewed in any of several graphical modes.     

Negotiating Boundaries. Configuration Management in Software Development Teams

Using case-study material from threesmall software development teams, this paper analysesthe regionalisation of design spaces. Its mainpurpose is to understand problems and practices ofcooperative work in such spaces. Configurationmanagement is used to denote both a practice andsupporting software tools and their relationship. Amajor concern is how to develop practices and toolsthat support cooperation across multipleorganisational and social boundaries whilesimultaneously being respectful of regionalisations.     

改进的模糊CMAC神经网络

提出了一种改进的模糊CMAC神经网络（IFCMAC）,该神经网络是在经典的FCMAC神经网络的模糊后相连层和输出层之间引入了输入矢量的线性加权和来补偿逼近的误差,所以它的逼近精度得到提高,解决了CMAC系列神经网络逼近精度不高的弱点,在颅脑磁共振图像分割仿真实验中,把当前像素点的子图像的纹理特征和该像素点的灰度值作为该像素的特征向量,将该特征向量作为IFCMAC神经网络的输入,实验结果表明其具有较高的分割准确性。     

Taking CSCW seriously

The topic of Computer Supported Cooperative Work (CSCW) has attracted much attention in the last few years. While the field is obviously still in the process of development, there is a marked ambiguity about the exact focus of the field. This lack of focus may hinder its further development and lead to its dissipation. In this paper we set out an approach to CSCW as a field of research which we believe provides a coherent conceptual framework for this area, suggesting that it should be concerned with thesupport requirements of cooperative work arrangements. This provides a more principled, comprehensive, and, in our opinion, more useful conception of the field than that provided by the conception of CSCW as being focused on computer support for groups. We then investigate the consequences of taking this alternative conception seriously, in terms of research directions for the field. As an indication of the fruits of this approach, we discuss the concept of ‘articulation work’ and its relevance to CSCW. This raises a host of interesting problems that are marginalized in the work on small group support but critical to the success of CSCW systems ‘in the large’, i. e., that are designed to meet current work requirements in the everyday world.     

CMAC神经网络结构参数及其结构优化的研究

CMAC神经网络具有学习算法简单、收敛速度快、局域泛化等优点,被广泛应用于机器人控制、信号处理、模式识别以及自适用控制等领域。但是网络的训练过程需要大量的存储单元,最优结构参数的选取是CMAC网络设计中一个重要问题。文中通过对函数逼近问题的研究,说明了量化精度和泛化参数如何影响网络对函数的逼近质量。仿真结果表明,通过对结构参数的调整,可以达到最小的逼近误差。而通过对网络结构的优化不但可以节约网络的训练时间而且可以大幅度减少存储单元的数量。     

An optimal distributed algorithm for finding articulation points in a network

This paper presents a distributed algorithm for finding the articulation points in an n node communication network represented by a connected undirected graph. For a given graph if the deletion of a node splits the graph into two or more components then that node is called an articulation point. The output of the algorithm is available in a distributed manner, i.e., when the algorithm terminates each node knows whether it is an articulation point or not. It is shown that the algorithm requires O(n) messages and O(n) units of time and is optimal in communication complexity to within a constant factor.