中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.022 seconds)

    LARGE-SCALE STRONGLY SUPERVISED ENSEMBLE METRIC LEARNING
    1.
    发明申请
    LARGE-SCALE STRONGLY SUPERVISED ENSEMBLE METRIC LEARNING 有权
    大规模强有力的可控制度学习

    公开(公告)号：US20130129202A1

    公开(公告)日：2013-05-23

    申请号：US13682780

    申请日：2012-11-21

    Applicant: NEC Laboratories America, Inc.

    Inventor： Chang Huang ,  Shenghuo Zhu ,  Kai Yu

    IPC: G06K9/62

    CPC classification number: G06K9/6256 ,  G06K9/6232

    Abstract: Systems and methods for metric learning include iteratively determining feature groups of images based on its derivative norm. Corresponding metrics of the feature groups are learned by gradient descent based on an expected loss. The corresponding metrics are combined to provide an intermediate metric matrix as a sparse representation of the images. A loss function of all metric parameters corresponding to features of the intermediate metric matrix are optimized, using a processor, to learn a final metric matrix. Eigenvalues of the final metric matrix are projected onto a simplex.

    Abstract translation: 度量学习的系统和方法包括基于其导数规范迭代确定图像的特征组。 通过基于预期损失的梯度下降来学习特征组的相应度量。 相应的度量被组合以提供作为图像的稀疏表示的中间度量矩阵。 使用处理器来优化对应于中间度量矩阵的特征的所有度量参数的损失函数来学习最终的度量矩阵。 最终公制矩阵的特征值被投影到单纯形上。

    Window dependent feature regions and strict spatial layout for object detection
    2.
    发明授权
    Window dependent feature regions and strict spatial layout for object detection 有权
    窗口依赖特征区域和严格的物体检测空间布局

    公开(公告)号：US09020248B2

    公开(公告)日：2015-04-28

    申请号：US14108280

    申请日：2013-12-16

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xiaoyu Wang ,  Ming Yang ,  Yuanqing Lin ,  Shenghuo Zhu

    IPC: G06K9/00 ,  G06K9/62 ,  G06K9/46

    CPC classification number: G06K9/6257 ,  G06K9/4642 ,  G06K9/6202 ,  G06K9/6211 ,  G06K9/6212

    Abstract: Systems and methods for object detection by receiving an image; segmenting the image and identifying candidate bounding boxes which may contain an object; for each candidate bounding box, dividing the box into overlapped small patches, and extracting dense features from the patches; during a training phase, applying a learning process to learn one or more discriminative classification models to classify negative boxes and positive boxes; and during an operational phase, for a new box generated from the image, applying the learned classification model to classify whether the box contains an object.

    Abstract translation: 通过接收图像进行物体检测的系统和方法; 分割图像并识别可能包含对象的候选边界框; 对于每个候选边界框，将框分成重叠的小块，并从补丁中提取密集特征; 在培训阶段，应用学习过程学习一个或多个歧视性分类模型，以对负面框和正面框进行分类; 并且在操作阶段期间，对于从图像生成的新框，应用所学习的分类模型来分类所述框是否包含对象。

    Predicting query execution time
    3.
    发明授权
    Predicting query execution time 有权
    预测查询执行时间

    公开(公告)号：US08874548B2

    公开(公告)日：2014-10-28

    申请号：US13711023

    申请日：2012-12-11

    Applicant: NEC Laboratories America, Inc.

    Inventor： Wentao Wu ,  Yun Chi ,  Shenghuo Zhu ,  Junichi Tatemura ,  Vahit Hakan Hacigumus

    IPC: G06F17/30 ,  G06F7/00

    CPC classification number: G06F17/30474 ,  G06F17/30463

    Abstract: There are provided a system and method for predicting query execution time in a database system. A cost model determination device determines a cost model of a database query optimizer for the database system. The cost model models costs of queries applied to the database system. A profiling device determines profiling queries for profiling input/output cost units and processor cost units relating to the database system, and profiles the cost units using the profiling queries to output profiled cost units. A calibrating device calibrates cost units in the cost model responsive to the profiled cost units to output calibrated cost units. A sampling re-estimator samples and re-estimates a cardinality estimation of a final query plan to output an updated cardinality estimation. A predictor applies the calibrated cost units and the updated cardinality estimation in the cost model to generate a prediction of an execution time of a given query.

    Abstract translation: 提供了一种用于在数据库系统中预测查询执行时间的系统和方法。 成本模型确定装置确定数据库系统的数据库查询优化器的成本模型。 成本模型建模应用于数据库系统的查询成本。 分析设备确定用于分析与数据库系统相关的输入/输出成本单位和处理器成本单元的分析查询，并使用分析查询对成本单位进行概要分析以输出分析成本单位。 校准装置根据成型单位对成本模型中的成本单位进行校准，以输出校准成本单位。 抽样重新估计器对最终查询计划的基数估计进行采样并重新估计，以输出更新的基数估计。 预测器将成本模型中的校准成本单元和更新的基数估计值应用于生成给定查询的执行时间的预测。

    Efficient distance metric learning for fine-grained visual categorization
    4.
    发明授权
    Efficient distance metric learning for fine-grained visual categorization 有权
    高效的距离度量学习，用于细粒度视觉分类

    公开(公告)号：US09471847B2

    公开(公告)日：2016-10-18

    申请号：US14524441

    申请日：2014-10-27

    Applicant: NEC Laboratories America, Inc.

    Inventor： Shenghuo Zhu ,  Yuanqing Lin ,  Qi Qian

    IPC: G06K9/62

    CPC classification number: G06K9/6201 ,  G06K9/6232 ,  G06K9/6251

    Abstract: Methods and systems for distance metric learning include generating two random projection matrices of a dataset from a d-dimensional space into an m-dimensional sub-space, where m is smaller than d. An optimization problem is solved in the m-dimensional subspace to learn a distance metric based on the random projection matrices. The distance metric is recovered in the d-dimensional space.

    Abstract translation: 用于距离度量学习的方法和系统包括从d维空间向m维子空间生成数据集的两个随机投影矩阵，其中m小于d。 在m维子空间中解决了优化问题，以便基于随机投影矩阵来学习距离度量。 距离度量在d维空间中被恢复。

    EFFICIENT DISTANCE METRIC LEARNING FOR FINE-GRAINED VISUAL CATEGORIZATION
    8.
    发明申请
    EFFICIENT DISTANCE METRIC LEARNING FOR FINE-GRAINED VISUAL CATEGORIZATION 有权
    有效的距离度量学习，细致的视觉分类

    公开(公告)号：US20150117764A1

    公开(公告)日：2015-04-30

    申请号：US14524441

    申请日：2014-10-27

    Applicant: NEC Laboratories America, Inc.

    Inventor： Shenghuo Zhu ,  Yuanqing Lin ,  Qi Qian

    IPC: G06K9/62

    CPC classification number: G06K9/6201 ,  G06K9/6232 ,  G06K9/6251

    Abstract: Methods and systems for distance metric learning include generating two random projection matrices of a dataset from a d-dimensional space into an m-dimensional sub-space, where m is smaller than d. An optimization problem is solved in the m-dimensional subspace to learn a distance metric based on the random projection matrices. The distance metric is recovered in the d-dimensional space.

    Abstract translation: 用于距离度量学习的方法和系统包括从d维空间向m维子空间生成数据集的两个随机投影矩阵，其中m小于d。 在m维子空间中解决了优化问题，以便基于随机投影矩阵来学习距离度量。 距离度量在d维空间中被恢复。

    Large-scale strongly supervised ensemble metric learning
    9.
    发明授权
    Large-scale strongly supervised ensemble metric learning 有权
    大规模强有力的监督综合度量学习

    公开(公告)号：US08873844B2

    公开(公告)日：2014-10-28

    申请号：US13682780

    申请日：2012-11-21

    Applicant: NEC Laboratories America, Inc.

    Inventor： Chang Huang ,  Shenghuo Zhu ,  Kai Yu

    IPC: G06K9/62

    CPC classification number: G06K9/6256 ,  G06K9/6232

    Abstract: Systems and methods for metric learning include iteratively determining feature groups of images based on its derivative norm. Corresponding metrics of the feature groups are learned by gradient descent based on an expected loss. The corresponding metrics are combined to provide an intermediate metric matrix as a sparse representation of the images. A loss function of all metric parameters corresponding to features of the intermediate metric matrix are optimized, using a processor, to learn a final metric matrix. Eigenvalues of the final metric matrix are projected onto a simplex.

    Abstract translation: 度量学习的系统和方法包括基于其导数规范迭代确定图像的特征组。 通过基于预期损失的梯度下降来学习特征组的相应度量。 相应的度量被组合以提供作为图像的稀疏表示的中间度量矩阵。 使用处理器来优化对应于中间度量矩阵的特征的所有度量参数的损失函数来学习最终的度量矩阵。 最终公制矩阵的特征值被投影到单纯形上。

    Window Dependent Feature Regions and Strict Spatial Layout for Object Detection
    10.
    发明申请
    Window Dependent Feature Regions and Strict Spatial Layout for Object Detection 有权
    窗口相关特征区域和对象检测的严格空间布局

    公开(公告)号：US20140241623A1

    公开(公告)日：2014-08-28

    申请号：US14108280

    申请日：2013-12-16

    Applicant: NEC Laboratories America, Inc.

    Inventor： Xiaoyu Wang ,  Ming Yang ,  Yuanqing Lin ,  Shenghuo Zhu

    IPC: G06K9/62

    CPC classification number: G06K9/6257 ,  G06K9/4642 ,  G06K9/6202 ,  G06K9/6211 ,  G06K9/6212

    Abstract: Systems and methods for object detection by receiving an image; segmenting the image and identifying candidate bounding boxes which may contain an object; for each candidate bounding box, dividing the box into overlapped small patches, and extracting dense features from the patches; during a training phase, applying a learning process to learn one or more discriminative classification models to classify negative boxes and positive boxes; and during an operational phase, for a new box generated from the image, applying the learned classification model to classify whether the box contains an object.

    Abstract translation: 通过接收图像进行物体检测的系统和方法; 分割图像并识别可能包含对象的候选边界框; 对于每个候选边界框，将框分成重叠的小块，并从补丁中提取密集特征; 在培训阶段，应用学习过程学习一个或多个歧视性分类模型，以对负面框和正面框进行分类; 并且在操作阶段期间，对于从图像生成的新框，应用所学习的分类模型来分类所述框是否包含对象。

Patent Agency Ranking