-
公开(公告)号:US20120128239A1
公开(公告)日:2012-05-24
申请号:US13300305
申请日:2011-11-18
申请人: Anjan Goswami , Naren Chittar , Ali Dasdan , Sanjay Pundlkrao Ghatare , Sandip Namdeo Gaikwad , Sung Hwan Chung
发明人: Anjan Goswami , Naren Chittar , Ali Dasdan , Sanjay Pundlkrao Ghatare , Sandip Namdeo Gaikwad , Sung Hwan Chung
CPC分类号: G06Q30/0276 , G06F17/3025 , G06F17/30256 , G06F17/30259 , G06F17/30265 , G06F17/3053 , G06Q30/0243 , G06T7/0002 , G06T2207/30168
摘要: Image-based features may be significantly correlated with click-through rates of images that depict a product, which may provide a more formal basis for the informal notion that good quality images will result in better click-through rates, as compared to poor quality images. Accordingly, an image assessment machine is configured to analyze image-based features to improve click-through rates for shopping search applications (e.g., a product search engine). Moreover, the image assessment machine may rank search results based on image quality factors and may notify sellers about low quality images. This may have the effect of improving the brand value for an online shopping website and accordingly have a positive long-term impact on the online shopping website.
摘要翻译: 基于图像的特征可能与描绘产品的图像的点击率显着相关,这可能为非正式概念提供更正式的基础,即与质量差的图像相比,高质量的图像将导致更好的点击率 。 因此,图像评估机被配置为分析基于图像的特征以提高购物搜索应用(例如,产品搜索引擎)的点击率。 此外,图像评估机可以基于图像质量因素对搜索结果进行排序,并且可以通知卖方关于低质量图像。 这可能会影响网上购物网站的品牌价值,从而对网络购物网站产生积极的长期影响。
-
公开(公告)号:US08675957B2
公开(公告)日:2014-03-18
申请号:US13300305
申请日:2011-11-18
申请人: Anjan Goswami , Naren Chittar , Ali Dasdan , Sanjay Pundlkrao Ghatare , Sandip Namdeo Gaikwad , Sung Hwan Chung
发明人: Anjan Goswami , Naren Chittar , Ali Dasdan , Sanjay Pundlkrao Ghatare , Sandip Namdeo Gaikwad , Sung Hwan Chung
IPC分类号: G06K9/00
CPC分类号: G06Q30/0276 , G06F17/3025 , G06F17/30256 , G06F17/30259 , G06F17/30265 , G06F17/3053 , G06Q30/0243 , G06T7/0002 , G06T2207/30168
摘要: Image-based features may be significantly correlated with click-through rates of images that depict a product, which may provide a more formal basis for the informal notion that good quality images will result in better click-through rates, as compared to poor quality images. Accordingly, an image assessment machine is configured to analyze image-based features to improve click-through rates for shopping search applications (e.g., a product search engine). Moreover, the image assessment machine may rank search results based on image quality factors and may notify sellers about low quality images. This may have the effect of improving the brand value for an online shopping website and accordingly have a positive long-term impact on the online shopping website.
摘要翻译: 基于图像的特征可能与描绘产品的图像的点击率显着相关,这可能为非正式概念提供更正式的基础,即与质量差的图像相比,高质量的图像将导致更好的点击率 。 因此,图像评估机被配置为分析基于图像的特征以提高购物搜索应用(例如,产品搜索引擎)的点击率。 此外,图像评估机可以基于图像质量因素对搜索结果进行排序,并且可以通知卖方关于低质量图像。 这可能会影响网上购物网站的品牌价值,从而对网络购物网站产生积极的长期影响。
-
公开(公告)号:US20120303615A1
公开(公告)日:2012-11-29
申请号:US13462179
申请日:2012-05-02
申请人: Anjan Goswami , Sung Hwan Chung
发明人: Anjan Goswami , Sung Hwan Chung
IPC分类号: G06F17/30
CPC分类号: G06N5/048 , G06F17/00 , G06F17/30 , G06F17/30247 , G06F17/3025 , G06F17/30268 , G06F17/3053 , G06F17/30536 , G06F17/30539 , G06F17/30545 , G06F17/30864 , G06K9/00 , G06K9/0014 , G06K9/20 , G06K9/46 , G06K9/4647 , G06K9/6201 , G06K9/6231 , G06K9/68 , G06Q30/02
摘要: A machine may be configured to access an image of an item described by a description of the item. The machine may determine an image quality score of the image based on an analysis of the image. A request for search results that pertain to the description may be received by the machine, and the machine may present a search result that references the item's image, based on its image quality score. Also, the machine may access images of items and descriptions of items and generate a set of most frequent text tokens included in the item descriptions. The machine may identify an image feature exhibited by an item's image and determine that a text token from the corresponding item description matches one of the most frequent text tokens. A data structure may be generated by the machine to correlate the identified image feature with the text token.
摘要翻译: 机器可以被配置为访问由项目的描述描述的项目的图像。 该机器可以基于图像的分析来确定图像的图像质量得分。 针对描述的搜索结果的请求可以由机器接收,并且机器可以基于其图像质量得分来呈现引用该项目的图像的搜索结果。 此外,机器可以访问项目的图像和项目的描述,并且生成包括在项目描述中的一组最常见的文本令牌。 机器可以识别由项目的图像展示的图像特征,并且确定来自相应项目描述的文本标记与最常见的文本标记之一匹配。 可以由机器生成数据结构以将所识别的图像特征与文本标记相关联。
-
公开(公告)号:US08977629B2
公开(公告)日:2015-03-10
申请号:US13462179
申请日:2012-05-02
申请人: Anjan Goswami , Sung Hwan Chung
发明人: Anjan Goswami , Sung Hwan Chung
CPC分类号: G06N5/048 , G06F17/00 , G06F17/30 , G06F17/30247 , G06F17/3025 , G06F17/30268 , G06F17/3053 , G06F17/30536 , G06F17/30539 , G06F17/30545 , G06F17/30864 , G06K9/00 , G06K9/0014 , G06K9/20 , G06K9/46 , G06K9/4647 , G06K9/6201 , G06K9/6231 , G06K9/68 , G06Q30/02
摘要: A machine may be configured to access an image of an item described by a description of the item. The machine may determine an image quality score of the image based on an analysis of the image. A request for search results that pertain to the description may be received by the machine, and the machine may present a search result that references the item's image, based on its image quality score. Also, the machine may access images of items and descriptions of items and generate a set of most frequent text tokens included in the item descriptions. The machine may identify an image feature exhibited by an item's image and determine that a text token from the corresponding item description matches one of the most frequent text tokens. A data structure may be generated by the machine to correlate the identified image feature with the text token.
摘要翻译: 机器可以被配置为访问由项目的描述描述的项目的图像。 该机器可以基于图像的分析来确定图像的图像质量得分。 针对描述的搜索结果的请求可以由机器接收,并且机器可以基于其图像质量得分来呈现引用该项目的图像的搜索结果。 此外,机器可以访问项目的图像和项目的描述,并且生成包括在项目描述中的一组最常见的文本令牌。 机器可以识别由项目的图像展示的图像特征,并且确定来自相应项目描述的文本标记与最常见的文本标记之一匹配。 可以由机器生成数据结构以将所识别的图像特征与文本标记相关联。
-
5.
公开(公告)号:US20080137989A1
公开(公告)日:2008-06-12
申请号:US11944017
申请日:2007-11-21
申请人: Andrew Y. Ng , Ashutosh Saxena , Sung Hwan Chung , Min Sun
发明人: Andrew Y. Ng , Ashutosh Saxena , Sung Hwan Chung , Min Sun
IPC分类号: G06K9/36
CPC分类号: G06K9/20 , G06K2209/40 , G06T7/593 , G06T2207/10012
摘要: Three-dimensional image data is generated. According to an example embodiment, three-dimensional depth information is estimated from a still image. A set of monocular images and their corresponding ground-truth depth maps are used to determine a relationship between monocular image features and the depth of image points. For different points in a particular image, the determined relationship is used together with local and global image features including monocular cues to determine relative depths of the points.
摘要翻译: 生成三维图像数据。 根据示例性实施例,从静止图像估计三维深度信息。 使用一组单目图像及其对应的地面真相深度图来确定单目图像特征与图像点深度之间的关系。 对于特定图像中的不同点,所确定的关系与本地和全局图像特征一起使用,包括单眼线索以确定点的相对深度。
-
公开(公告)号:US20070094325A1
公开(公告)日:2007-04-26
申请号:US11255624
申请日:2005-10-21
申请人: Ronald Ih , William Sumerlin , Derek Gaw , Sung Hwan Chung
发明人: Ronald Ih , William Sumerlin , Derek Gaw , Sung Hwan Chung
IPC分类号: G06F15/16
CPC分类号: A63F13/358 , A63F13/12 , A63F13/352 , A63F2300/534 , A63F2300/5533 , H04L41/00 , H04L41/0677 , H04L41/0896 , H04L67/1002 , H04L67/1008 , H04L67/1017 , H04L67/1019 , H04L67/1021 , H04L67/104 , H04L67/1091
摘要: Hybrid peer-to-peer data communication and management is described, including querying a plurality of elements in an environment for state data, the state data describes a state of the environment and an activity occurring in the environment, receiving the state data from one or more of the plurality of elements in response to the querying, analyzing the state data to determine an environmental change, the updated state data is generated describing the environmental change, and using the updated state data to modify the environment by dynamically allocating the plurality of elements to process a simulation, the plurality of elements being dynamically allocated based on available processing capacity provided by the plurality of elements.
摘要翻译: 描述了混合对等数据通信和管理,包括在状态数据的环境中查询多个元素,状态数据描述环境的状态和环境中发生的活动,从一个或多个 更多的元素响应于查询,分析状态数据以确定环境变化,生成描述环境变化的更新状态数据,并且通过动态地分配多个元素来使用更新的状态数据来修改环境 为了处理模拟,基于由所述多个元素提供的可用处理能力来动态地分配所述多个元素。
-
公开(公告)号:US08472699B2
公开(公告)日:2013-06-25
申请号:US11944017
申请日:2007-11-21
申请人: Andrew Y. Ng , Ashutosh Saxena , Sung Hwan Chung , Min Sun
发明人: Andrew Y. Ng , Ashutosh Saxena , Sung Hwan Chung , Min Sun
IPC分类号: G06K9/00
CPC分类号: G06K9/20 , G06K2209/40 , G06T7/593 , G06T2207/10012
摘要: Three-dimensional image data is generated. According to an example embodiment, three-dimensional depth information is estimated from a still image. A set of monocular images and their corresponding ground-truth depth maps are used to determine a relationship between monocular image features and the depth of image points. For different points in a particular image, the determined relationship is used together with local and global image features including monocular cues to determine relative depths of the points.
摘要翻译: 生成三维图像数据。 根据示例性实施例,从静止图像估计三维深度信息。 使用一组单目图像及其对应的地面真相深度图来确定单目图像特征与图像点深度之间的关系。 对于特定图像中的不同点,所确定的关系与本地和全局图像特征一起使用,包括单眼线索以确定点的相对深度。
-
-
-
-
-
-