-
公开(公告)号:US20090290802A1
公开(公告)日:2009-11-26
申请号:US12125057
申请日:2008-05-22
申请人: Xian-Sheng Hua , Guo-Jun Qi , Yong Rui , Tao Mei , Hong-Jiang Zhang
发明人: Xian-Sheng Hua , Guo-Jun Qi , Yong Rui , Tao Mei , Hong-Jiang Zhang
IPC分类号: G06K9/62
CPC分类号: G06K9/34
摘要: The concurrent multiple instance learning technique described encodes the inter-dependency between instances (e.g. regions in an image) in order to predict a label for a future instance, and, if desired the label for an image determined from the label of these instances. The technique, in one embodiment, uses a concurrent tensor to model the semantic linkage between instances in a set of images. Based on the concurrent tensor, rank-1 supersymmetric non-negative tensor factorization (SNTF) can be applied to estimate the probability of each instance being relevant to a target category. In one embodiment, the technique formulates the label prediction processes in a regularization framework, which avoids overfitting, and significantly improves a learning machine's generalization capability, similar to that in SVMs. The technique, in one embodiment, uses Reproducing Kernel Hilbert Space (RKHS) to extend predicted labels to the whole feature space based on the generalized representer theorem.
摘要翻译: 所描述的并发多实例学习技术编码实例(例如,图像中的区域)之间的相互依赖性,以便预测将来实例的标签,以及如果需要,从这些实例的标签确定的图像的标签。 在一个实施例中,该技术使用并发张量来对一组图像中的实例之间的语义联系进行建模。 基于并发张量,可以应用秩1超对称非负张量因子分解(SNTF)来估计每个实例与目标类别相关的概率。 在一个实施例中,该技术在正则化框架中制定标签预测过程,其避免过拟合,并且显着地提高学习机器的泛化能力,类似于SVM中的标准预测过程。 在一个实施例中,该技术使用再生核希尔伯特空间(RKHS)来基于广义代表定理将预测标签扩展到整个特征空间。
-
公开(公告)号:US20090125461A1
公开(公告)日:2009-05-14
申请号:US11958050
申请日:2007-12-17
申请人: Guo-Jun Qi , Xian-Sheng Hua , Yong Rui , Hong-Jiang Zhang , Shipeng Li
发明人: Guo-Jun Qi , Xian-Sheng Hua , Yong Rui , Hong-Jiang Zhang , Shipeng Li
IPC分类号: G06F15/18
CPC分类号: G06N99/005
摘要: Multi-label active learning may entail training a classifier with a set of training samples having multiple labels per sample. In an example embodiment, a method includes accepting a set of training samples, with the set of training samples having multiple respective samples that are each respectively associated with multiple labels. The set of training samples is analyzed to select a sample-label pair responsive to at least one error parameter. The selected sample-label pair is then submitted to an oracle for labeling.
摘要翻译: 多标签主动学习可能需要对分类器训练一组具有每个样本的多个标签的训练样本。 在示例实施例中,一种方法包括接受一组训练样本,其中该组训练样本具有多个相应样本,每个样本分别与多个标签相关联。 分析该组训练样本以响应于至少一个误差参数来选择样本标签对。 然后将选定的样品标签对提交给oracle进行标记。
-
公开(公告)号:US08422802B2
公开(公告)日:2013-04-16
申请号:US13077735
申请日:2011-03-31
申请人: Linjun Yang , Darui Li , Xian-Sheng Hua , Hong-Jiang Zhang
发明人: Linjun Yang , Darui Li , Xian-Sheng Hua , Hong-Jiang Zhang
IPC分类号: G06K9/36
CPC分类号: G06K9/6223
摘要: Techniques for construction of a visual codebook are described herein. Feature points may be extracted from large numbers of images. In one example, images providing N feature points may be used to construct a codebook of K words. The centers of each of K clusters of feature points may be initialized. In a looping or iterative manner, an assignment step assigns each feature point to a cluster and an update step locates a center of each cluster. The feature points may be assigned to a cluster based on a lesser of a distance to a center of a previously assigned cluster and a distance to a center derived by operation of an approximate nearest neighbor algorithm having aspects of randomization. The loop terminates when the feature points have sufficiently converged to their respective clusters. Centers of the clusters represent visual words, which may be used to construct the visual codebook.
摘要翻译: 本文描述了构建视觉码本的技术。 特征点可以从大量图像中提取出来。 在一个示例中,提供N个特征点的图像可以用于构造K个字的码本。 可以初始化K个特征点中的每一个的中心。 以循环或迭代的方式,分配步骤将每个特征点分配给集群,并且更新步骤定位每个集群的中心。 可以基于距先前分配的簇的中心的距离中较小的一个特征点来分配特征点,以及通过具有随机化方面的近似最近邻算法的操作导出的到中心的距离。 当特征点已经充分收敛到它们各自的簇时,环路终止。 集群的中心表示视觉词,可用于构建视觉码本。
-
公开(公告)号:US20120158686A1
公开(公告)日:2012-06-21
申请号:US12971880
申请日:2010-12-17
申请人: Xian-Sheng Hua , Dong Liu , Meng Wang , Hong-Jiang Zhang
发明人: Xian-Sheng Hua , Dong Liu , Meng Wang , Hong-Jiang Zhang
IPC分类号: G06F17/30
CPC分类号: G06F16/5866
摘要: A computing device configured to determine a subset of the tags associated with at least one image of a plurality of received, tagged images is described herein. The computing device performs the determining based on one or more measures of consistency of visual similarity between ones of the images with semantic similarity between tags of the ones of the images.
摘要翻译: 被配置为确定与多个接收到的标记图像中的至少一个图像相关联的标签的子集的计算设备在此被描述。 计算装置基于图像中的一个图像之间的视觉相似性的一致性的测量来执行确定,其中图像的标签之间具有语义相似性。
-
公开(公告)号:US08131086B2
公开(公告)日:2012-03-06
申请号:US12237298
申请日:2008-09-24
申请人: Xian-Sheng Hua , Guo-Jun Qi , Yong Rui , Hong-Jiang Zhang
发明人: Xian-Sheng Hua , Guo-Jun Qi , Yong Rui , Hong-Jiang Zhang
IPC分类号: G06K9/68
CPC分类号: G06K9/469 , G06K9/6297
摘要: Kernelized spatial-contextual image classification is disclosed. One embodiment comprises generating a first spatial-contextual model to represent a first image, the first spatial-contextual model having a plurality of interconnected nodes arranged in a first pattern of connections with each node connected to at least one other node, generating a second spatial-contextual model to represent a second image using the first pattern of connections, and estimating the distance between corresponding nodes in the first spatial-contextual model and the second spatial-contextual model based on a relationship with adjacent connected nodes to determine a distance between the first image and the second image.
摘要翻译: 公开了内核空间上下文图像分类。 一个实施例包括生成第一空间上下文模型以表示第一图像,第一空间上下文模型具有以与连接到至少一个其他节点的每个节点连接的第一连接方式布置的多个互连节点,产生第二空间 - 使用所述第一连接模式来表示第二图像,以及基于与相邻连接节点的关系来估计所述第一空间 - 上下文模型中的对应节点与所述第二空间 - 上下文模型之间的距离,以确定所述第二图像之间的距离 第一个图像和第二个图像。
-
公开(公告)号:US07996762B2
公开(公告)日:2011-08-09
申请号:US12030616
申请日:2008-02-13
申请人: Guo-Jun Qi , Xian-Sheng Hua , Yong Rui , Hong-Jiang Zhang , Shipeng Li
发明人: Guo-Jun Qi , Xian-Sheng Hua , Yong Rui , Hong-Jiang Zhang , Shipeng Li
IPC分类号: G06F17/00
CPC分类号: G06F17/30799 , G06K9/00711
摘要: Correlative multi-label image annotation may entail annotating an image by indicating respective labels for respective concepts. In an example embodiment, a classifier is to annotate an image by implementing a labeling function that maps an input feature space and a label space to a combination feature vector. The combination feature vector models both features of individual ones of the concepts and correlations among the concepts.
摘要翻译: 相关多标签图像注释可能需要通过针对相应概念指示相应的标签来注释图像。 在示例实施例中,分类器是通过实现将输入特征空间和标签空间映射到组合特征向量的标记功能来注释图像。 组合特征向量模拟各个概念的特征和概念之间的相关性。
-
公开(公告)号:US08175847B2
公开(公告)日:2012-05-08
申请号:US12415722
申请日:2009-03-31
申请人: Hong-Jiang Zhang , Dong Liu , Meng Wang , Linjun Yang , Xian-Sheng Hua
发明人: Hong-Jiang Zhang , Dong Liu , Meng Wang , Linjun Yang , Xian-Sheng Hua
IPC分类号: G06F17/18
CPC分类号: G06F17/30038
摘要: Technologies for generating a boosted tag ranking for a media instance, the boosted tag ranking based on probabilistic relevance estimation computed by a probabilistic relevance estimator and tag correlation refining performed by a tag correlation refiner. Such boosted tag rankings may be used for search result ranking, tag recommendation, and group recommendation.
摘要翻译: 用于生成用于媒体实例的提升的标签排名的技术,基于由概率相关性估计器计算的概率相关性估计的增强的标签排名以及由标签相关性精炼器执行的标签相关性精炼。 这种提升的标签排名可以用于搜索结果排名,标签推荐和组推荐。
-
公开(公告)号:US08086549B2
公开(公告)日:2011-12-27
申请号:US11958050
申请日:2007-12-17
申请人: Guo-Jun Qi , Xian-Sheng Hua , Yong Rui , Hong-Jiang Zhang , Shipeng Li
发明人: Guo-Jun Qi , Xian-Sheng Hua , Yong Rui , Hong-Jiang Zhang , Shipeng Li
IPC分类号: G06F15/18
CPC分类号: G06N99/005
摘要: Multi-label active learning may entail training a classifier with a set of training samples having multiple labels per sample. In an example embodiment, a method includes accepting a set of training samples, with the set of training samples having multiple respective samples that are each respectively associated with multiple labels. The set of training samples is analyzed to select a sample-label pair responsive to at least one error parameter. The selected sample-label pair is then submitted to an oracle for labeling.
摘要翻译: 多标签主动学习可能需要对分类器训练一组具有每个样本的多个标签的训练样本。 在示例实施例中,一种方法包括接受一组训练样本,其中该组训练样本具有多个相应样本,每个样本分别与多个标签相关联。 分析该组训练样本以响应于至少一个误差参数来选择样本标签对。 然后将选定的样品标签对提交给oracle进行标记。
-
公开(公告)号:US20100074537A1
公开(公告)日:2010-03-25
申请号:US12237298
申请日:2008-09-24
申请人: Xian-Sheng Hua , Guo-Jun Qi , Yong Rui , Hong-Jiang Zhang
发明人: Xian-Sheng Hua , Guo-Jun Qi , Yong Rui , Hong-Jiang Zhang
IPC分类号: G06K9/62
CPC分类号: G06K9/469 , G06K9/6297
摘要: Kernelized spatial-contextual image classification is disclosed. One embodiment comprises generating a first spatial-contextual model to represent a first image, the first spatial-contextual model having a plurality of interconnected nodes arranged in a first pattern of connections with each node connected to at least one other node, generating a second spatial-contextual model to represent a second image using the first pattern of connections, and estimating the distance between corresponding nodes in the first spatial-contextual model and the second spatial-contextual model based on a relationship with adjacent connected nodes to determine a distance between the first image and the second image.
摘要翻译: 公开了内核空间上下文图像分类。 一个实施例包括生成第一空间上下文模型以表示第一图像,第一空间上下文模型具有以与连接到至少一个其他节点的每个节点连接的第一连接方式布置的多个互连节点,产生第二空间 - 使用所述第一连接模式来表示第二图像,以及基于与相邻连接节点的关系来估计所述第一空间 - 上下文模型中的对应节点与所述第二空间 - 上下文模型之间的距离,以确定所述第二图像之间的距离 第一个图像和第二个图像。
-
公开(公告)号:US20090083010A1
公开(公告)日:2009-03-26
申请号:US12030616
申请日:2008-02-13
申请人: Guo-Jun Qi , Xian-Sheng Hua , Yong Rui , Hong-Jiang Zhang , Shipeng Li
发明人: Guo-Jun Qi , Xian-Sheng Hua , Yong Rui , Hong-Jiang Zhang , Shipeng Li
IPC分类号: G06F17/10
CPC分类号: G06F17/30799 , G06K9/00711
摘要: Correlative multi-label image annotation may entail annotating an image by indicating respective labels for respective concepts. In an example embodiment, a classifier is to annotate an image by implementing a labeling function that maps an input feature space and a label space to a combination feature vector. The combination feature vector models both features of individual ones of the concepts and correlations among the concepts.
摘要翻译: 相关多标签图像注释可能需要通过针对相应概念指示相应的标签来注释图像。 在示例实施例中,分类器是通过实现将输入特征空间和标签空间映射到组合特征向量的标记功能来注释图像。 组合特征向量模拟各个概念的特征和概念之间的相关性。
-
-
-
-
-
-
-
-
-