Probabilistic retrospective event detection
    21.
    发明申请
    Probabilistic retrospective event detection 有权
    概率回顾事件检测

    公开(公告)号:US20070038653A1

    公开(公告)日:2007-02-15

    申请号:US11256353

    申请日:2005-10-21

    IPC分类号: G06F7/00

    CPC分类号: G06F17/30684 G06F17/30687

    摘要: Probabilistic retrospective event detection is described. In one aspect, event parameters are initialized to identify a number of events from a corpus of documents. Using a generative model, documents are determined to be associated with an event to detect representative events from the identified number of events.

    摘要翻译: 描述概率回顾事件检测。 在一个方面,事件参数被初始化以从文档语料库中识别多个事件。 使用生成模型,文档被确定为与事件相关联以从所识别的事件数量检测代表事件。

    Efficient propagation for face annotation
    22.
    发明授权
    Efficient propagation for face annotation 有权
    面部注释的高效传播

    公开(公告)号:US07403642B2

    公开(公告)日:2008-07-22

    申请号:US11111696

    申请日:2005-04-21

    IPC分类号: G06K9/00

    摘要: Systems, engines, user interfaces, and methods allow a user to select a group of images, such as digital photographs, and assign to the group of images the name of a person who is represented in each of the images. The name is automatically propagated to the face of the person, each time the person's face occurs in an image. In one implementation, names and associations are shared between a browsing mode for viewing multiple images at once and a viewer mode, for viewing one image at a time. The browsing mode can provide a menu of candidate names for annotating a face in a single image of the viewer mode. Likewise, the viewer mode can provide annotated face information to the browser mode for facilitating name propagation. Identification of a person's face in multiple images can be accomplished not only by finding similarities in facial features but also by finding similarities in contextual features near the face in different images.

    摘要翻译: 系统,引擎,用户界面和方法允许用户选择一组图像,例如数字照片,并且在图像组中分配在每个图像中表示的人的姓名。 每当人的脸发生在图像中时,名称将自动传播到人的脸部。 在一个实现中,名称和关联在用于一次查看多个图像的浏览模式和观看者模式之间共享,以便一次查看一个图像。 浏览模式可以提供用于在观看者模式的单个图像中注释脸部的候选名称的菜单。 类似地,观看者模式可以向浏览器模式提供注释的面部信息,以便于名称传播。 可以通过在面部特征中发现相似性,而且通过在不同图像中的脸部附近的上下文特征中找到相似性来实现多个图像中的人脸识别。

    Generating clusters of images for search results
    23.
    发明授权
    Generating clusters of images for search results 失效
    为搜索结果生成图像群集

    公开(公告)号:US07725451B2

    公开(公告)日:2010-05-25

    申请号:US11337825

    申请日:2006-01-23

    IPC分类号: G06F7/00 G06F17/30

    CPC分类号: G06F17/30265

    摘要: A method and system for generating clusters of images for a search result of an image query is provided. When an original image query is received, the search system identifies text associated with the original image query by submitting the original image query to a search engine. The search system identifies phrases from the text of the web page containing the search result. The search system uses each of the identified phrases as an image query and submits the image queries to an image search engine. The search system considers the image search result for each image query to represent a cluster of related images. The search system then presents the clusters of images as the images of the image search result of the original image query.

    摘要翻译: 提供了一种用于生成用于图像查询的搜索结果的图像群集的方法和系统。 当接收到原始图像查询时,搜索系统通过将原始图像查询提交给搜索引擎来识别与原始图像查询相关联的文本。 搜索系统从包含搜索结果的网页的文本中识别短语。 搜索系统使用每个识别的短语作为图像查询,并将图像查询提交给图像搜索引擎。 搜索系统考虑每个图像查询的图像搜索结果来表示相关图像的集群。 然后,搜索系统将图像集合呈现为原始图像查询的图像搜索结果的图像。

    Generating clusters of images for search results
    24.
    发明申请
    Generating clusters of images for search results 失效
    为搜索结果生成图像群集

    公开(公告)号:US20070174269A1

    公开(公告)日:2007-07-26

    申请号:US11337825

    申请日:2006-01-23

    IPC分类号: G06F17/30

    CPC分类号: G06F17/30265

    摘要: A method and system for generating clusters of images for a search result of an image query is provided. When an original image query is received, the search system identifies text associated with the original image query by submitting the original image query to a search engine. The search system identifies phrases from the text of the web page containing the search result. The search system uses each of the identified phrases as an image query and submits the image queries to an image search engine. The search system considers the image search result for each image query to represent a cluster of related images. The search system then presents the clusters of images as the images of the image search result of the original image query.

    摘要翻译: 提供了一种用于生成用于图像查询的搜索结果的图像群集的方法和系统。 当接收到原始图像查询时,搜索系统通过将原始图像查询提交给搜索引擎来识别与原始图像查询相关联的文本。 搜索系统从包含搜索结果的网页的文本中识别短语。 搜索系统使用每个识别的短语作为图像查询,并将图像查询提交给图像搜索引擎。 搜索系统考虑每个图像查询的图像搜索结果来表示相关图像的集群。 然后,搜索系统将图像集合呈现为原始图像查询的图像搜索结果的图像。

    Efficient Propagation for Face Annotation
    25.
    发明申请
    Efficient Propagation for Face Annotation 审中-公开
    面部注释的有效传播

    公开(公告)号:US20080152201A1

    公开(公告)日:2008-06-26

    申请号:US12047247

    申请日:2008-03-12

    IPC分类号: G06K9/46 G06K9/00

    摘要: Systems, engines, user interfaces, and methods allow a user to select a group of images, such as digital photographs, and assign to the group of images the name of a person who is represented in each of the images. The name is automatically propagated to the face of the person, each time the person's face occurs in an image. In one implementation, names and associations are shared between a browsing mode for viewing multiple images at once and a viewer mode, for viewing one image at a time. The browsing mode can provide a menu of candidate names for annotating a face in a single image of the viewer mode. Likewise, the viewer mode can provide annotated face information to the browser mode for facilitating name propagation. Identification of a person's face in multiple images can be accomplished not only by finding similarities in facial features but also by finding similarities in contextual features near the face in different images.

    摘要翻译: 系统,引擎,用户界面和方法允许用户选择一组图像,例如数字照片,并且在图像组中分配在每个图像中表示的人的姓名。 每当人的脸发生在图像中时,名称将自动传播到人的脸部。 在一个实现中,名称和关联在用于一次查看多个图像的浏览模式和观看者模式之间共享,以便一次查看一个图像。 浏览模式可以提供用于在观看者模式的单个图像中注释脸部的候选名称的菜单。 类似地,观看者模式可以向浏览器模式提供注释的面部信息,以便于名称传播。 可以通过在面部特征中发现相似性,而且通过在不同图像中的脸部附近的上下文特征中找到相似性来实现多个图像中的人脸识别。

    Efficient propagation for face annotation
    26.
    发明申请
    Efficient propagation for face annotation 有权
    面部注释的高效传播

    公开(公告)号:US20060239515A1

    公开(公告)日:2006-10-26

    申请号:US11111696

    申请日:2005-04-21

    IPC分类号: G06F17/00 G06K9/00 G06K9/54

    摘要: Systems, engines, user interfaces, and methods allow a user to select a group of images, such as digital photographs, and assign to the group of images the name of a person who is represented in each of the images. The name is automatically propagated to the face of the person, each time the person's face occurs in an image. In one implementation, names and associations are shared between a browsing mode for viewing multiple images at once and a viewer mode, for viewing one image at a time. The browsing mode can provide a menu of candidate names for annotating a face in a single image of the viewer mode. Likewise, the viewer mode can provide annotated face information to the browser mode for facilitating name propagation. Identification of a person's face in multiple images can be accomplished not only by finding similarities in facial features but also by finding similarities in contextual features near the face in different images.

    摘要翻译: 系统,引擎,用户界面和方法允许用户选择一组图像,例如数字照片,并且在图像组中分配在每个图像中表示的人的姓名。 每当人的脸发生在图像中时,名称将自动传播到人的脸部。 在一个实现中,名称和关联在用于一次查看多个图像的浏览模式和观看者模式之间共享,以便一次查看一个图像。 浏览模式可以提供用于在观看者模式的单个图像中注释脸部的候选名称的菜单。 类似地,观看者模式可以向浏览器模式提供注释的面部信息,以便于名称传播。 可以通过在面部特征中发现相似性,而且通过在不同图像中的脸部附近的上下文特征中找到相似性来实现多个图像中的人脸识别。

    CLASSIFICATION OF IMAGES AS ADVERTISEMENT IMAGES OR NON-ADVERTISEMENT IMAGES
    27.
    发明申请
    CLASSIFICATION OF IMAGES AS ADVERTISEMENT IMAGES OR NON-ADVERTISEMENT IMAGES 有权
    图像分类作为广告图像或非广告图像

    公开(公告)号:US20110058734A1

    公开(公告)日:2011-03-10

    申请号:US12945635

    申请日:2010-11-12

    IPC分类号: G06K9/62

    CPC分类号: G06Q30/02 G06Q30/0277

    摘要: An advertisement image classification system trains a binary classifier to classify images as advertisement images or non-advertisement images and then uses the binary classifier to classify images of web pages as advertisement images or non-advertisement images. During a training phase, the classification system generates training data of feature vectors representing the images and labels indicating whether an image is an advertisement image or a non-advertisement Image. The classification system trains a binary classifier to classify Images using training data. During a classification phase, the classification system inputs a web page with an image and generates a feature vector for the image. The classification system then applies the trained binary classifier to the feature vector to generate a score indicating whether the image is an advertisement image or a non-advertisement image.

    摘要翻译: 广告图像分类系统训练二进制分类器将图像分类为广告图像或非广告图像,然后使用二进制分类器将网页的图像分类为广告图像或非广告图像。 在训练阶段,分类系统生成表示图像的特征向量的训练数据,以及指示图像是广告图像还是非广告图像的标签。 分类系统训练二进制分类器,以使用训练数据对图像进行分类。 在分类阶段,分类系统输入具有图像的网页,并生成图像的特征向量。 然后,分类系统将经过训练的二进制分类器应用于特征向量,以生成指示图像是广告图像还是非广告图像的分数。

    Classification of images as advertisement images or non-advertisement images
    28.
    发明授权
    Classification of images as advertisement images or non-advertisement images 有权
    图像分类为广告图像或非广告图像

    公开(公告)号:US08027940B2

    公开(公告)日:2011-09-27

    申请号:US12945635

    申请日:2010-11-12

    IPC分类号: G06F15/18

    CPC分类号: G06Q30/02 G06Q30/0277

    摘要: An advertisement image classification system trains a binary classifier to classify images as advertisement images or non-advertisement images and then uses the binary classifier to classify images of web pages as advertisement images or non-advertisement images. During a training phase, the classification system generates training data of feature vectors representing the images and labels indicating whether an image is an advertisement image or a non-advertisement image. The classification system trains a binary classifier to classify images using training data. During a classification phase, the classification system inputs a web page with an image and generates a feature vector for the image. The classification system then applies the trained binary classifier to the feature vector to generate a score indicating whether the image is an advertisement image or a non-advertisement image.

    摘要翻译: 广告图像分类系统训练二进制分类器将图像分类为广告图像或非广告图像,然后使用二进制分类器将网页的图像分类为广告图像或非广告图像。 在训练阶段,分类系统生成表示图像的特征向量的训练数据,以及指示图像是广告图像还是非广告图像的标签。 分类系统训练二进制分类器,以使用训练数据对图像进行分类。 在分类阶段,分类系统输入具有图像的网页,并生成图像的特征向量。 然后,分类系统将经过训练的二进制分类器应用于特征向量,以生成指示图像是广告图像还是非广告图像的分数。

    Classification of images as advertisement images or non-advertisement images of web pages
    29.
    发明授权
    Classification of images as advertisement images or non-advertisement images of web pages 有权
    将图像分类为网页的广告图像或非广告图像

    公开(公告)号:US07840502B2

    公开(公告)日:2010-11-23

    申请号:US11762553

    申请日:2007-06-13

    IPC分类号: G06F15/18

    CPC分类号: G06Q30/02 G06Q30/0277

    摘要: An advertisement image classification system trains a binary classifier to classify images as advertisement images or non-advertisement images and then uses the binary classifier to classify images of web pages as advertisement images or non-advertisement images. During a training phase, the classification system generates training data of feature vectors representing the images and labels indicating whether an image is an advertisement image or a non-advertisement image. The classification system trains a binary classifier to classify images using training data. During a classification phase, the classification system inputs a web page with an image and generates a feature vector for the image. The classification system then applies the trained binary classifier to the feature vector to generate a score indicating whether the image is an advertisement image or a non-advertisement image.

    摘要翻译: 广告图像分类系统训练二进制分类器将图像分类为广告图像或非广告图像,然后使用二进制分类器将网页的图像分类为广告图像或非广告图像。 在训练阶段,分类系统生成表示图像的特征向量的训练数据,以及指示图像是广告图像还是非广告图像的标签。 分类系统训练二进制分类器,以使用训练数据对图像进行分类。 在分类阶段,分类系统输入具有图像的网页,并生成图像的特征向量。 然后,分类系统将经过训练的二进制分类器应用于特征向量,以生成指示图像是广告图像还是非广告图像的分数。

    CLASSIFICATION OF IMAGES AS ADVERTISEMENT IMAGES OR NON-ADVERTISEMENT IMAGES
    30.
    发明申请
    CLASSIFICATION OF IMAGES AS ADVERTISEMENT IMAGES OR NON-ADVERTISEMENT IMAGES 有权
    图像分类作为广告图像或非广告图像

    公开(公告)号:US20080313031A1

    公开(公告)日:2008-12-18

    申请号:US11762553

    申请日:2007-06-13

    IPC分类号: G06Q30/00

    CPC分类号: G06Q30/02 G06Q30/0277

    摘要: An advertisement image classification system trains a binary classifier to classify images as advertisement images or non-advertisement images and then uses the binary classifier to classify images of web pages as advertisement images or non-advertisement images. During a training phase, the classification system generates training data of feature vectors representing the images and labels indicating whether an image is an advertisement image or a non-advertisement image. The classification system trains a binary classifier to classify images using training data. During a classification phase, the classification system inputs a web page with an image and generates a feature vector for the image. The classification system then applies the trained binary classifier to the feature vector to generate a score indicating whether the image is an advertisement image or a non-advertisement image.

    摘要翻译: 广告图像分类系统训练二进制分类器将图像分类为广告图像或非广告图像,然后使用二进制分类器将网页的图像分类为广告图像或非广告图像。 在训练阶段,分类系统生成表示图像的特征向量的训练数据,以及指示图像是广告图像还是非广告图像的标签。 分类系统训练二进制分类器,以使用训练数据对图像进行分类。 在分类阶段,分类系统输入具有图像的网页,并生成图像的特征向量。 然后,分类系统将经过训练的二进制分类器应用于特征向量,以生成指示图像是广告图像还是非广告图像的分数。