结合双语义数据增强与目标定位的细粒度图像分类

细粒度图像分类旨在对属于同一基础类别的图像进行更细致的子类划分,其较大的类内差异和较小的类间差异使得提取局部关键特征成为关键所在。提出一种结合双语义数据增强与目标定位的细粒度图像分类算法。为充分提取具有区分度的局部关键特征,在训练阶段基于双线性注意力池化和卷积块注意模块构建注意力学习模块和信息增益模块,分别获取目标局部细节信息和目标重要轮廓这2类不同语义层次的数据,以双语义数据增强的方式提高模型准确率。同时,在测试阶段构建目标定位模块,使模型聚焦于分类目标整体,从而进一步提高分类准确率。实验结果表明,该算法在CUB-200-2011、FGVC Aircraft和Stanford Cars数据集中分别达到89.5%、93.6%和94.7%的分类准确率,较基准网络Inception-V3、双线性注意力池化特征聚合方式以及B-CNN、RA-CNN、MA-CNN等算法具有更好的分类性能。     

Java Class文件的结构分析及其解析执行

Java Class文件分析及其解析执行是分析JVM的重要部分,通过实例对Class文件的结构进行了详细分析,并初步实现了Class文件的解析执行.     

Analyzing evolution of variability in a software product line: From contexts and requirements to features

Context

In the long run, features of a software product line (SPL) evolve with respect to changes in stakeholder requirements and system contexts. Neither domain engineering nor requirements engineering handles such co-evolution of requirements and contexts explicitly, making it especially hard to reason about the impact of co-changes in complex scenarios.

Objective

In this paper, we propose a problem-oriented and value-based analysis method for variability evolution analysis. The method takes into account both kinds of changes (requirements and contexts) during the life of an evolving software product line.

Method

The proposed method extends the core requirements engineering ontology with the notions to represent variability-intensive problem decomposition and evolution. On the basis of problemorientation, the analysis method identifies candidate changes, detects influenced features, and evaluates their contributions to the value of the SPL.

Results and Conclusion

The process of applying the analysis method is illustrated using a concrete case study of an evolving enterprise software system, which has confirmed that tracing back to requirements and contextual changes is an effective way to understand the evolution of variability in the software product line.     

Illumination robust single sample face recognition based on ESRC

Multimedia Tools and Applications - The extended sparse representation classifier (ESRC) is one of the state-of-the-art solutions for single sample face recognition, but it performs...     

基于ISDN的局域网与INTERET连接方案的设计及分析

ISDN是当前局域网连接Internet的最佳途径之一。根据局域网的具体情况,通过选择一定的接口设备,可取得较好的连接效果。本文通过对ISDN及相关设备技术的分析介绍,给出了一个实用的网络机房连接Internet的技术方案。     

Windows CE．net的AD7854驱动程序开发

介绍基于Windows CE．net的AD7854流接口驱动程序的开发。以AD7854与嵌入式处理器S3C2410接口电路为依据,详细阐述Windows CE．net的中断处理过程,给出驱动开发的具体实现过程、涉及的内核文件以及部分源代码。该驱动程序的实现为基于Windows CE．net的嵌入式系统引进AD7854提供了方便。     

Batch Nearest Neighbor Search for Video Retrieval

To retrieve similar videos to a query clip from a large database, each video is often represented by a sequence of high- dimensional feature vectors. Typically, given a query video containing m feature vectors, an independent nearest neighbor (NN) search for each feature vector is often first performed. After completing all the NN searches, an overall similarity is then computed, i.e., a single content-based video retrieval usually involves m individual NN searches. Since normally nearby feature vectors in a video are similar, a large number of expensive random disk accesses are expected to repeatedly occur, which crucially affects the overall query performance. Batch nearest neighbor (BNN) search is stated as a batch operation that performs a number of individual NN searches. This paper presents a novel approach towards efficient high-dimensional BNN search called dynamic query ordering (DQO) for advanced optimizations of both I/O and CPU costs. Observing the overlapped candidates (or search space) of a pervious query may help to further reduce the candidate sets of subsequent queries, DQO aims at progressively finding a query order such that the common candidates among queries are fully utilized to maximally reduce the total number of candidates. Modelling the candidate set relationship of queries by a candidate overlapping graph (COG), DQO iteratively selects the next query to be executed based on its estimated pruning power to the rest of queries with the dynamically updated COG. Extensive experiments are conducted on real video datasets and show the significance of our BNN query processing strategy.     

基于图象集似然度的人脸识别

根据人的认识规律,提出了基于图象集的似然度人脸识别方法。该方法把图象集中的各幅图象的信息矩阵的奇异值向量作为矩阵中的一列而构成的图象集特征矩阵。然后,把测试样本的图象集特征矩阵与图象集库中的训练样本图象集的特征矩阵相比较找出它们的相似程序－－图象集的似然度,从而进行人睑图象识别。     

图像集的离散度矩阵及其在人脸图像识别中的应用

本文提出了图像集离散度矩阵的基本概念及用于人脸图像识别的方法。该方法把同一类图像集中的各幅图像的信息矩阵的奇异值向量作为矩阵中的一列构成图像集特征矩阵。把这些矩阵组成一图像库,并找出图像集离散度矩阵和图像库离散度矩阵,从而计算出它们的最佳投影系数。然后,把测试样本的图像集特征矩阵与图像集库中的训练样本图像集的特征按投影系数相比较找出它的相似程度,从而进行人脸图像识别。     

基于Agent的智能电子商务支持系统研究

人工智能在近几年得到了迅速的发展,软件Agent在电子商务中越来越重要。该文提出了智能电子商务支持系统（IECSS）的概念,给出了智能电子商务支持系统模型,最后指出了系统支持电子商务的应用及其相关问题。