-
公开(公告)号：US09710447B2
公开(公告)日：2017-07-18
申请号：US14215925
申请日：2014-03-17
Applicant: YAHOO! INC.
Inventor： Jia Li , Xiangnan Kong
CPC classification number: G06F17/241 , G06F17/30598 , G06K9/00677 , G06K9/6296
Abstract: System, method and architecture for providing improved visual recognition by modeling visual content, semantic content and an implicit social network representing individuals depicted in a collection of content, such as visual images, photographs, etc. which network may be determined based on co-occurrences of individuals represented by the content, and/or other data linking the individuals. In accordance with one or more embodiments, using images as an example, a relationship structure may comprise an implicit structure, or network, determined from co-occurrences of individuals in the images. A kernel jointly modeling content, semantic and social network information may be built and used in automatic image annotation and/or determination of relationships between individuals, for example.
-
Patent Agency Ranking
公开(公告)号：US09607217B2
公开(公告)日：2017-03-28
申请号：US14579998
申请日：2014-12-22
Applicant: Yahoo! Inc.
Inventor： Suleyman Cetintas , Kuang-chih Lee , Jia Li
IPC: G06K9/00 , G06F3/0484 , G06F17/30 , G06K9/62
CPC classification number: G06K9/6267 , G06F3/04842 , G06F17/30265 , G06K9/00456 , G06K9/00664 , G06K9/4628 , G06K9/6201 , G06K9/626 , G06K9/627 , G06N3/08
Abstract: Briefly, embodiments of methods and/or systems of generating preference indices for contiguous portions of digital images are disclosed. For one embodiment, as an example, parameters of a neural network may be developed to generate object labels for digital images. The developed parameters may be transferred to a neural network utilized to generate signal sample value levels corresponding to preference indices for contiguous portions of digital images.
-
公开(公告)号：US20170083752A1
公开(公告)日：2017-03-23
申请号：US14859040
申请日：2015-09-18
Applicant: Yahoo! Inc.
Inventor： Mohammad Saberian , Sachin Sudhakar Farfade , Jia Li
CPC classification number: G06T3/40 , G06K9/00248 , G06K9/4628 , G06K9/6272 , G06N3/0454
Abstract: Briefly, embodiments of methods and/or systems of detecting and image of a human face in a digital image are disclosed. For one embodiment, as an example, parameters of a neural network may be developed to generate object labels for digital images. The developed parameters may be refined by a neural network to generate signal sample value levels corresponding to probability that a human face may be depicted at a localized region of a digital image.
-
公开(公告)号：US09411829B2
公开(公告)日：2016-08-09
申请号：US13913943
申请日：2013-06-10
Applicant: YAHOO! INC.
Inventor： Jia Li , Nadav Golbandi , XianXing Zhang
IPC: G06F17/30
CPC classification number: G06F17/30274 , G06F17/30253 , G06F17/30256 , G06F17/30687 , G06F17/30713 , G06K9/4642 , G06K9/6223 , G06K9/6226 , G06K9/6262
Abstract: Disclosed herein is a system and method that facilitate searching and/or browsing of images by clustering, or grouping, the images into a set of image clusters using facets, such as without limitation visual properties or visual characteristics, of the images, and representing each image cluster by a representative image selected for the image cluster. A map-reduce based probabilistic topic model may be used to identify one or more images belonging to each image cluster and update model parameters.
Abstract translation: 本文公开了一种系统和方法，其通过使用小平面（例如但不限于图像的视觉特性或视觉特征）将图像聚类或分组成一组图像群集来促进搜索和/或浏览图像，并且表示每个图像 通过为图像集群选择的代表图像进行图像聚类。 可以使用基于地图缩减的概率主题模型来识别属于每个图像簇的一个或多个图像和更新模型参数。
-
公开(公告)号：US20160180162A1
公开(公告)日：2016-06-23
申请号：US14579998
申请日：2014-12-22
Applicant: Yahoo! Inc.
Inventor： Suleyman Cetintas , Kuang-chih Lee , Jia Li
IPC: G06K9/00 , G06K9/62 , G06F3/0484 , G06N3/08 , G06F17/30
CPC classification number: G06K9/6267 , G06F3/04842 , G06F17/30265 , G06K9/00456 , G06K9/00664 , G06K9/4628 , G06K9/6201 , G06K9/626 , G06K9/627 , G06N3/08
Abstract: Briefly, embodiments of methods and/or systems of generating preference indices for contiguous portions of digital images are disclosed. For one embodiment, as an example, parameters of a neural network may be developed to generate object labels for digital images. The developed parameters may be transferred to a neural network utilized to generate signal sample value levels corresponding to preference indices for contiguous portions of digital images.
Abstract translation: 简而言之，公开了为数字图像的连续部分生成偏好索引的方法和/或系统的实施例。 对于一个实施例，作为示例，可以开发神经网络的参数以生成数字图像的对象标签。 所开发的参数可以被传送到用于产生对应于数字图像的连续部分的偏好索引的信号样本值级别的神经网络。
-
公开(公告)号：US20140363075A1
公开(公告)日：2014-12-11
申请号：US13913943
申请日：2013-06-10
Applicant: YAHOO! INC.
Inventor： Jia Li , Nadav Golbandi , XianXing Zhang
IPC: G06K9/62
CPC classification number: G06F17/30274 , G06F17/30253 , G06F17/30256 , G06F17/30687 , G06F17/30713 , G06K9/4642 , G06K9/6223 , G06K9/6226 , G06K9/6262
Abstract: Disclosed herein is a system and method that facilitate searching and/or browsing of images by clustering, or grouping, the images into a set of image clusters using facets, such as without limitation visual properties or visual characteristics, of the images, and representing each image cluster by a representative image selected for the image cluster. A map-reduce based probabilistic topic model may be used to identify one or more images belonging to each image cluster and update model parameters.
Abstract translation: 本文公开了一种系统和方法，其通过使用小平面（例如但不限于图像的视觉特性或视觉特征）将图像聚类或分组成一组图像群集来促进搜索和/或浏览图像，并且表示每个图像 通过为图像集群选择的代表图像进行图像聚类。 可以使用基于地图缩减的概率主题模型来识别属于每个图像簇的一个或多个图像和更新模型参数。
-
-
-
-
-
Search Results
26
records
(took 0.019 seconds)
