-
公开(公告)号：US20130290222A1
公开(公告)日：2013-10-31
申请号：US13458183
申请日：2012-04-27
CPC分类号： G06F17/30247 , G06K9/6247 , G06K9/6259
摘要： An instance-level retrieval method and system are provided. A representation of a query image is embedded in a multi-dimensional space using a learned projection. The projection is learned using category-labeled training data to optimize a classification rate on the training data. The joint learning of the projection and the classifiers improves the computation of similarity/distance between images by embedding them in a subspace where the similarity computation outputs more accurate results. An input query image can thus be used to retrieve similar instances in a database by computing the comparison measure in the embedding space.
摘要翻译： 提供实例级检索方法和系统。 使用学习投影将查询图像的表示嵌入到多维空间中。 使用类别标记的训练数据学习投影，以优化训练数据的分类率。 投影和分类器的联合学习通过将图像嵌入到相似度计算输出更准确的结果的子空间来改善图像之间的相似度/距离的计算。 因此，输入查询图像可以用于通过计算嵌入空间中的比较度量来检索数据库中的类似实例。
-
公开(公告)号：US09075824B2
公开(公告)日：2015-07-07
申请号：US13458183
申请日：2012-04-27
CPC分类号： G06F17/30247 , G06K9/6247 , G06K9/6259
摘要： An instance-level retrieval method and system are provided. A representation of a query image is embedded in a multi-dimensional space using a learned projection. The projection is learned using category-labeled training data to optimize a classification rate on the training data. The joint learning of the projection and the classifiers improves the computation of similarity/distance between images by embedding them in a subspace where the similarity computation outputs more accurate results. An input query image can thus be used to retrieve similar instances in a database by computing the comparison measure in the embedding space.
摘要翻译： 提供实例级检索方法和系统。 使用学习投影将查询图像的表示嵌入到多维空间中。 使用类别标记的训练数据学习投影，以优化训练数据的分类率。 投影和分类器的联合学习通过将图像嵌入到相似度计算输出更准确的结果的子空间来改善图像之间的相似度/距离的计算。 因此，输入查询图像可以用于通过计算嵌入空间中的比较度量来检索数据库中的类似实例。
-
公开(公告)号：US20120143853A1
公开(公告)日：2012-06-07
申请号：US12960018
申请日：2010-12-03
申请人： Albert Gordo , Florent Perronnin
发明人： Albert Gordo , Florent Perronnin
IPC分类号： G06F17/30
CPC分类号： G06F17/30247
摘要： A system and method for comparing a query object and one or more of a set of database objects are provided. The method includes providing quantized representations of database objects. The database objects have each been transformed with a quantized embedding function which is the composition of a real-valued embedding function and a quantization function. The query object is transformed to a representation of the query object in a real-valued embedding space using the real-valued embedding function. Query-dependent estimated distance values are computed for the query object, based on the transformed query object and stored. A comparison (e.g., distance or similarity) measure between the query object and each of the quantized database object representations is computed based on the stored query-dependent estimated distance values. Data is output based on the comparison computation.
摘要翻译： 提供了一种用于比较查询对象与一组数据库对象中的一个或多个的系统和方法。 该方法包括提供数据库对象的量化表示。 数据库对象每个都已经用量化嵌入函数进行了变换，该嵌入函数是实值嵌入函数和量化函数的组合。 使用实值嵌入函数将查询对象转换为实值嵌入空间中的查询对象的表示。 基于所转换的查询对象并存储查询对象，计算与查询相关的估计距离值。 基于存储的查询相关估计距离值来计算查询对象和每个量化数据库对象表示之间的比较（例如距离或相似度）度量。 基于比较计算输出数据。
-
公开(公告)号：US08370338B2
公开(公告)日：2013-02-05
申请号：US12960018
申请日：2010-12-03
申请人： Albert Gordo , Florent Perronnin
发明人： Albert Gordo , Florent Perronnin
IPC分类号： G06F17/30
CPC分类号： G06F17/30247
摘要： A system and method for comparing a query object and one or more of a set of database objects are provided. The method includes providing quantized representations of database objects. The database objects have each been transformed with a quantized embedding function which is the composition of a real-valued embedding function and a quantization function. The query object is transformed to a representation of the query object in a real-valued embedding space using the real-valued embedding function. Query-dependent estimated distance values are computed for the query object, based on the transformed query object and stored. A comparison (e.g., distance or similarity) measure between the query object and each of the quantized database object representations is computed based on the stored query-dependent estimated distance values. Data is output based on the comparison computation.
摘要翻译： 提供了一种用于比较查询对象与一组数据库对象中的一个或多个的系统和方法。 该方法包括提供数据库对象的量化表示。 数据库对象每个都已经用量化嵌入函数进行了变换，该量化嵌入函数是实值嵌入函数和量化函数的组合。 使用实值嵌入函数将查询对象转换为实值嵌入空间中的查询对象的表示。 基于所转换的查询对象并存储查询对象，计算与查询相关的估计距离值。 基于存储的与查询相关的估计距离值来计算查询对象和每个量化数据库对象表示之间的比较（例如，距离或相似性）度量。 基于比较计算输出数据。
-
公开(公告)号：US20110137898A1
公开(公告)日：2011-06-09
申请号：US12632135
申请日：2009-12-07
申请人： Albert Gordo , Florent Perronnin , Francois Ragnet
发明人： Albert Gordo , Florent Perronnin , Francois Ragnet
IPC分类号： G06F17/30
摘要： A document classification method comprises: (i) classifying pages of an input document to generate page classifications; (ii) aggregating the page classifications to generate an input document representation, the aggregating not being based on ordering of the pages; and (iii) classifying the input document based on the input document representation. A page classifier for use in the page classifying operation (i) is trained based on pages of a set of labeled training documents having document classification labels. In some such embodiments, the pages of the set of labeled training documents are not labeled, and the page classifier training comprises: clustering pages of the set of labeled training documents to generate page clusters; and generating the page classifier based on the page clusters.
摘要翻译： 文档分类方法包括：（i）分类输入文档的页面以生成页面分类; （ii）聚合页面分类以生成输入文档表示，聚合不是基于页面的排序; 和（iii）基于输入文档表示对输入文档进行分类。 用于页面分类操作（i）中的页面分类器基于具有文档分类标签的一组标记的训练文档的页面进行训练。 在一些这样的实施例中，标记的训练文档集合的页面没有被标记，并且页面分类器训练包括：聚集所标识的训练文档集合的页面以生成页面簇; 以及基于页面集群生成页面分类器。
-
公开(公告)号：US08699789B2
公开(公告)日：2014-04-15
申请号：US13230253
申请日：2011-09-12
申请人： Albert Gordo , Florent C. Perronnin
发明人： Albert Gordo , Florent C. Perronnin
CPC分类号： G06K9/6247 , G06K9/6256
摘要： A training system, training method, and a system and method of use of a trained classification system are provided. A classifier may be trained with a first “cheap” view but not using a second “costly” view of each of the training samples, which is not available at test time. The two views of samples are each defined in a respective original feature space. An embedding function is learned for embedding at least the first view of the training samples into a common feature space in which the second view can also be embedded or is the same as the second view original feature space. Labeled training samples (first view only) for training the classifier are embedded into the common feature space using the learned embedding function. The trained classifier can be used to predict labels for test samples for which the first view has been embedded in the common feature space with the embedding function.
摘要翻译： 提供了训练系统，训练方法，以及训练有素的分类系统的使用系统和方法。 分类器可以用第一“便宜”视图进行训练，但不使用每个训练样本的第二个“昂贵”视图，这在测试时间不可用。 样本的两个视图各自在相应的原始特征空间中定义。 学习嵌入功能，至少将训练样本的第一视图嵌入到第二视图也可以被嵌入或与第二视图原始特征空间相同的公共特征空间中。 用于训练分类器的标记训练样本（仅第一视图）使用学习的嵌入函数嵌入到公共特征空间中。 经过训练的分类器可用于预测第一视图已嵌入到具有嵌入功能的公共特征空间中的测试样本的标签。
-
公开(公告)号：US20130064444A1
公开(公告)日：2013-03-14
申请号：US13230253
申请日：2011-09-12
申请人： Albert Gordo , Florent C. Perronnin
发明人： Albert Gordo , Florent C. Perronnin
IPC分类号： G06K9/62
CPC分类号： G06K9/6247 , G06K9/6256
摘要： A training system, training method, and a system and method of use of a trained classification system are provided. A classifier may be trained with a first “cheap” view but not using a second “costly” view of each of the training samples, which is not available at test time. The two views of samples are each defined in a respective original feature space. An embedding function is learned for embedding at least the first view of the training samples into a common feature space in which the second view can also be embedded or is the same as the second view original feature space. Labeled training samples (first view only) for training the classifier are embedded into the common feature space using the learned embedding function. The trained classifier can be used to predict labels for test samples for which the first view has been embedded in the common feature space with the embedding function.
摘要翻译： 提供了训练系统，训练方法，以及训练有素的分类系统的使用系统和方法。 分类器可以用第一便宜视图进行训练，但是不使用每个训练样本的第二代价视图，这在测试时间不可用。 样本的两个视图各自在相应的原始特征空间中定义。 学习嵌入功能，至少将训练样本的第一视图嵌入到第二视图也可以被嵌入或与第二视图原始特征空间相同的公共特征空间中。 用于训练分类器的标记训练样本（仅第一视图）使用学习的嵌入函数嵌入到公共特征空间中。 经过训练的分类器可用于预测第一视图已嵌入到具有嵌入功能的公共特征空间中的测试样本的标签。
-
-
-
-
-
-
搜索结果
7 条记录 (耗时 0.02 秒)