一种视觉词软直方图的图像表示方法

基于视觉词的统计建模和判别学习,提出一种视觉词软直方图的图像表示方法.假设属于同一视觉词的图像局部特征服从高斯混合分布,利用最大-最小后验伪概率判别学习方法从样本中估计该分布,计算局部特征与视觉词的相似度.累加图像中每个视觉词与对应局部特征的相似度,在全部视觉词集合上进行结果的归一化,得到图像的视觉词软直方图.讨论了两种具体实现方法:一种是基于分类的软直方图方法,该方法根据相似度最大原则建立局部特征与视觉词的对应关系;另一种是完全软直方图方法,该方法将每个局部特征匹配到所有视觉词.在数据库Caltech-4和PASCAL VOC 2006上的实验结果表明,该方法是有效的.     

基于数据场的教育图像可视化表征

读图时代已经来临,如何恰当地表征和展示内涵丰富的教育图像资源是当前亟待解决的科学问题之一。面向右脑潜能开发,从重视可视化结果的形象思维模拟和启发出发,以场论的视角提出一个新的教育图像可视化表征研究框架,在该框架下集成了传统图像可视化表征方法,同时研究了利用教育图像场的新方法。教育图像及其场的实例分析表明了研究的合理性和有效性。     

基于多视觉码本的图像表示

基于词袋模型的图像表示方法的有效性主要受限于局部特征的量化误差。文中提出一种基于多视觉码本的图像表示方法,通过综合考虑码本构建和编码方法这两个方面的因素加以改进。具体包括:1)多视觉码本构建,以迭代方式构建多个紧凑且具有互补性的视觉码本;2)图像表示,首先针对多码本的情况,依次从各码本中选择相应的视觉单词并采用线性回归估计编码系数,然后结合图像的空间金字塔结构形成最终的图像表示。在一些标准测试集合的图像分类结果验证文中方法的有效性。     

Object Bank: An Object-Level Image Representation for High-Level Visual Recognition

It is a remarkable fact that images are related to objects constituting them. In this paper, we propose to represent images by using objects appearing in them. We introduce the novel concept of object bank (OB), a high-level image representation encoding object appearance and spatial location information in images. OB represents an image based on its response to a large number of pre-trained object detectors, or ‘object filters’, blind to the testing dataset and visual recognition task. Our OB representation demonstrates promising potential in high level image recognition tasks. It significantly outperforms traditional low level image representations in image classification on various benchmark image datasets by using simple, off-the-shelf classification algorithms such as linear SVM and logistic regression. In this paper, we analyze OB in detail, explaining our design choice of OB for achieving its best potential on different types of datasets. We demonstrate that object bank is a high level representation, from which we can easily discover semantic information of unknown images. We provide guidelines for effectively applying OB to high level image recognition tasks where it could be easily compressed for efficient computation in practice and is very robust to various classifiers.     

基于词语关系的词向量模型

词向量能够以向量的形式表示词的意义,近来许多自然语言处理应用中已经融入词向量,将其作为额外特征或者直接输入以提升系统性能。然而,目前的词向量训练模型大多基于浅层的文本信息,没有充分挖掘深层的依存关系。词的词义体现在该词与其他词产生的关系中,而词语关系包含关联单位、关系类型和关系方向三个属性,因此,该文提出了一种新的基于神经网络的词向量训练模型,它具有三个顶层,分别对应关系的三个属性,更合理地利用词语关系对词向量进行训练,借助大规模未标记文本,利用依存关系和上下文关系来训练词向量。将训练得到的词向量在类比任务和蛋白质关系抽取任务上进行评价,以验证关系模型的有效性。实验表明,与skip-gram模型和CBOW模型相比,由关系模型训练得到的词向量能够更准确地表达词语的语义信息。     

基于词频统计特征和 GVP 的大规模图像检索算法研究

针对传统的GVP(Geometry-Preserving Visual Phrases)图像检索算法计算量大、时间复杂度高且不适合处理大规模图像检索等缺点,文章提出了FSF-GVP(Frequency Statistics Feature-Geometry-Preserving Visual Phrases)算法,该方法将词频统计特征和GVP算法相结合,使用GVP排序算法对词频特征统计后的相似结果集进行排序,忽略不相似结果集,极大地提高了检索效率。实验结果表明,FSF-GVP在保证检索准确性的前提下,提高了检索效率,适用于实时大规模图像检索。     

基于支持区域探测的视觉短语的图像表示方法

近年来,基于bag-of-words模型的图像表示方法由于丢弃了视觉词汇之间的空间位置关系,且存在冗余信息,从而不能有效地表示该类图像。针对传统词袋模型视觉词汇之间相对位置关系利用不足,以及语义信息不明确的问题,提出采用基于支持区域的视觉短语来表示图像。通过支持区域探测得到图像中对分类起重要作用的支持区域,然后对支持区域上的视觉词进行空间建模得到视觉短语用于分类。最后在标准数据集UIUC-Sports8图像库和Scene-15图像库上进行对比实验,实验结果表明该算法具有良好的图像分类性能。     

一种改进的GloVe词向量表示学习方法

GloVe模型是一种广泛使用的词向量表示学习的模型.许多研究发现,学习得到的词向量维数越大,性能越好;但维数越大,模型学习耗时越长.事实上,GloVe模型中,耗时主要表现在两方面,一是统计词对共现矩阵,二是训练学习词向量表示.该文在利用GloVe模型统计语料中词对共现时,基于对称或非对称窗口得到两个共现矩阵,然后分别学...     

基于位平面分解的三角形NAM图像表示

位平面分解是一种能够有效地降低图像的复杂性的方法,而三角形Packing 问题是一类特殊的Packing 问题,在许多领域里得到了广泛的应用,有着巨大理论价值和实际意义.因此,借助于位平面分解和三角形Packing问题的思想,以提高多值图像的表示效率为目标,提出了一种基于位平面分解的的三角形NAM(非对称逆布局模式表示模型)的图像表示方法.给出并实现了基于位平面分解的三角形NAM的图像表示算法,理论分析和实验结果表明:与流行的线性四元树表示方法相比,基于位平面分解的三角形NAM表示方法能更有效地减少数据存储空间,是多值图像模式的一种良好的表示方法.     

Fractional-order Sparse Representation for Image Denoising

Sparse representation models have been shown promising results for image denoising. However, conventional sparse representation-based models cannot obtain satisfactory estimations for sparse coefficients and the dictionary. To address this weakness, in this paper, we propose a novel fractional-order sparse representation (FSR) model. Specifically, we cluster the image patches into K groups, and calculate the singular values for each clean/noisy patch pair in the wavelet domain. Then the uniform fractional-order parameters are learned for each cluster. Then a novel fractional-order sample space is constructed using adaptive fractional-order parameters in the wavelet domain to obtain more accurate sparse coefficients and dictionary for image denoising. Extensive experimental results show that the proposed model outperforms state-of-the-art sparse representation-based models and the block-matching and 3D filtering algorithm in terms of denoising performance and the computational efficiency.      

A Vector-based Representation for Image Warping

A method for image analysis, representation and re-synthesis is introduced. Unlike other schemes it is not pixel based but rather represents a picture as vector data, from which an altered version of the original image can be rendered. Representing an image as vector data allows performing operations such as zooming, retouching or colourising, avoiding common problems associated with pixel image manipulation. This paper brings together methods from the areas of computer vision, image compositing and image based rendering to prove that this type of image representation is a step towards accurate and efficient image manipulation.     

三维人体重建中的服装视觉信息表示

针对三维人体重建中服装视觉信息表示模糊的问题,提出一种多阶段优化的三维人体重建方法.首先对输入的人体图像进行预处理,分别提取其语义特征、明暗特征和高频特征;然后基于局部深度特征构建有向距离场,隐式表征三维人体的几何形状;再构建着装层次表示模块,通过定义着装层次损失函数感知服装语义上下文信息,并优化有向距离场,生成粗糙的...     

基于GloVe模型的词向量改进方法

使用词向量表示方法能够很好的捕捉词语的语法和语义信息,为了能够提高词向量语义信息表示的准确性,本文通过分析GloVe模型共现矩阵的特点,利用分布式假设,提出了一种基于GloVe词向量训练模型的改进方法.该方法主要通过对维基百科统计词频分析,总结出过滤共现矩阵中无关词和噪声词的一般规律,最后给出了词向量在词语类比数据集和词语相关性数据集的评估结果.实验表明,在相同的实验环境中,本文的方法能够有效的缩短词向量的训练时间,并且在词语语义类比实验中准确率得到提高.     

A Single Image Representation Model for Efficient Stereoscopic Image Creation

Computer graphics is one of the most efficient ways to create a stereoscopic image. The process of stereoscopic CG generation is, however, still very inefficient compared to that of monoscopic CG generation. Despite that stereo images are very similar to each other, they are rendered and manipulated independently. Additional requirements for disparity control specific to stereo images lead to even greater inefficiency. This paper proposes a method to reduce the inefficiency accompanied in the creation of a stereoscopic image. The system automatically generates an optimized single image representation of the entire visible area from both cameras. The single image can be easily manipulated with conventional techniques, as it is spatially smooth and maintains the original shapes of scene objects. In addition, a stereo image pair can be easily generated with an arbitrary disparity setting. These convenient and efficient features are achieved by the automatic generation of a stereo camera pair, robust occlusion detection with a pair of Z‐buffers, an optimization method for spatial smoothness, and stereo image pair generation with a non‐linear disparity adjustment. Experiments show that our technique dramatically improves the efficiency of stereoscopic image creation while preserving the quality of the results.     

融合单词贡献度与Word2Vec词向量的文档表示

针对现有文档向量表示方法受噪声词语影响和重要词语语义不完整的问题,通过融合单词贡献度与Word2Vec词向量提出一种新的文档表示方法.应用数据集训练Word2Vec模型,计算数据集中词语的贡献度,同时设置贡献度阈值,提取贡献度大于该阈值的单词构建单词集合.在此基础上,寻找文档与集合中共同存在的单词,获取其词向量并融合单...     

基于模型的运动表示用于图像序列的处理

该文讨论了图像序列中运动物体的姿态描述问题。以姿态向量作为刻画运动序列的统一参数,建立了由姿态向量计算外部特征点运动轨迹的关系式,讨论了逆向映射的计算方法。     

Group Collaborative Representation for Image Set Classification

International Journal of Computer Vision - With significant advances in imaging technology, multiple images of a person or an object are becoming readily available in a number of real-life...     

A Hierarchical Representation for Content-based Image Retrieval

In this paper, we present a hierarchical entropy-based representation (HER) for one-dimensional signals. Any signal can be effectively represented by means of a vector containing the energy values related to its most important points, i.e. the maxima, together with their relative locations along the time axis. Such a representation has been applied to a database containing several shapes represented by their closed contour in curvilinear coordinates in order to perform content-based retrieval for time series. K-d-trees have been used as a spatial access method in order to improve the search performance. The results obtained from our experiments show that HER for indexing (HERI) achieves very good performance with few false alarms and false dismissals.     

Class-Driven Non-Negative Matrix Factorization for Image Representation

Non-negative matrix factorization (NMF) is a useful technique to learn a parts-based representation by decomposing the original data matrix into a basis set and coefficients with non-negative constraints. However, as an unsupervised method, the original NMF cannot utilize the discriminative class information. In this paper, we propose a semi-supervised class-driven NMF method to associate a class label with each basis vector by introducing an inhomogeneous representation cost constraint. This constraint forces the learned basis vectors to represent better for their own classes but worse for the others. Therefore, data samples in the same class will have similar representations, and consequently the discriminability in new representations could be boosted. Some experiments carried out on several standard databases validate the effectiveness of our method in comparison with the state-of-the-art approaches.