会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 5. 发明申请
    • GEODESIC SALIENCY USING BACKGROUND PRIORS
    • 使用背景技术的地球物理学
    • US20160163058A1
    • 2016-06-09
    • US14890884
    • 2013-07-31
    • Yichen WEIFang WENJian SUNMICROSOFT TECHNOLOGY LICENSING, LLC
    • Yichen WeiFang WenJian Sun
    • G06T7/00
    • G06T7/162G06K9/3233G06T7/11G06T7/136G06T7/194G06T2207/20164
    • Disclosed herein are techniques and systems for computing geodesic saliency of images using background priors. An input image may be segmented into a plurality of patches, and a graph associated with the image may be generated, the graph comprising nodes and edges. The nodes of the graph include nodes that correspond to the plurality of patches of the image plus an additional virtual background node that is added to the graph. The graph further includes edges that connect the nodes to each other, including internal edges between adjacent patches and boundary edges between those patches at the boundary of the image and the virtual background node. Using this graph, a saliency value, called the “geodesic” saliency, for each patch of the image is determined as a length of a shortest path from a respective patch to the virtual background node.
    • 这里公开了用于使用背景先验计算图像的测地学显着性的技术和系统。 可以将输入图像分割成多个片段,并且可以生成与图像相关联的图形,该图形包括节点和边缘。 图形的节点包括与图像的多个补丁相对应的节点以及添加到图形的附加虚拟背景节点。 该图进一步包括将节点彼此连接的边缘,包括相邻补丁之间的内部边缘和图像边界处的虚拟背景节点之间的这些补丁之间的边界边缘。 使用该图,对于图像的每个补丁,显着值(称为“测地线”)显着性被确定为从相应补丁到虚拟背景节点的最短路径的长度。
    • 7. 发明授权
    • Dynamic keyword suggestion and image-search re-ranking
    • 动态关键字建议和图像搜索重新排序
    • US08185526B2
    • 2012-05-22
    • US12691181
    • 2010-01-21
    • Fang WenJian Sun
    • Fang WenJian Sun
    • G06F7/04G06F17/30
    • G06F17/30256G06F17/30265
    • A content-based re-ranking (CBR) process may be performed on query results based on a selected keyword that is extracted from previous query results, and thereby increase a relevancy of search results. A search engine may perform the CBR process using a target image that is selected from a plurality of image search results, the CBR to identify re-ranked image search results. Keywords may be extracted from the re-ranked image search results. A portion of the keywords may be outputted as suggested keywords and made selectable by a user. Finally, a refined CBR process may be performed based on the target image and a received selection a suggested keyword, the refined CBR to output the refined image search results.
    • 可以基于从先前查询结果提取的所选择的关键字对查询结果执行基于内容的重新排序(CBR)处理,从而增加搜索结果的相关性。 搜索引擎可以使用从多个图像搜索结果中选择的目标图像来执行CBR处理,CBR用于识别重新排序的图像搜索结果。 可以从重新排序的图像搜索结果中提取关键字。 关键字的一部分可以作为建议的关键字输出,并且可由用户选择。 最后,可以基于目标图像和接收到的选择一个建议的关键字,精炼的CBR来输出精细图像搜索结果来执行精细的CBR处理。
    • 8. 发明申请
    • DYNAMIC KEYWORD SUGGESTION AND IMAGE-SEARCH RE-RANKING
    • 动态关键词建议和图像搜索重新排序
    • US20110179021A1
    • 2011-07-21
    • US12691181
    • 2010-01-21
    • Fang WenJian Sun
    • Fang WenJian Sun
    • G06F17/30
    • G06F17/30256G06F17/30265
    • A content-based re-ranking (CBR) process may be performed on query results based on a selected keyword that is extracted from previous query results, and thereby increase a relevancy of search results. A search engine may perform the CBR process using a target image that is selected from a plurality of image search results, the CBR to identify re-ranked image search results. Keywords may be extracted from the re-ranked image search results. A portion of the keywords may be outputted as suggested keywords and made selectable by a user. Finally, a refined CBR process may be performed based on the target image and a received selection a suggested keyword, the refined CBR to output the refined image search results.
    • 可以基于从先前查询结果提取的所选择的关键字对查询结果执行基于内容的重新排序(CBR)处理,从而增加搜索结果的相关性。 搜索引擎可以使用从多个图像搜索结果中选择的目标图像来执行CBR处理,CBR用于识别重新排序的图像搜索结果。 可以从重新排序的图像搜索结果中提取关键字。 关键字的一部分可以作为建议的关键字输出,并且可由用户选择。 最后,可以基于目标图像和接收到的选择一个建议的关键字,精炼的CBR来输出精细图像搜索结果来执行精细的CBR处理。
    • 9. 发明授权
    • Real time head pose estimation
    • 实时头部姿态估计
    • US08687880B2
    • 2014-04-01
    • US13425188
    • 2012-03-20
    • Yichen WeiFang WenJian SunTommer LeyvandJinyu LiCasey MeekhofTim Keosababian
    • Yichen WeiFang WenJian SunTommer LeyvandJinyu LiCasey MeekhofTim Keosababian
    • G06K9/62
    • G06K9/00281G06K9/00362G06K2009/4666
    • Methods are provided for generating a low dimension pose space and using the pose space to estimate one or more head rotation angles of a user head. In one example, training image frames including a test subject head are captured under a plurality of conditions. For each frame an actual head rotation angle about a rotation axis is recorded. In each frame a face image is detected and converted to an LBP feature vector. Using principal component analysis a PCA feature vector is generated. Pose classes related to rotation angles about a rotation axis are defined. The PCA feature vectors are grouped into a pose class that corresponds to the actual rotation angle associated with the PCA feature vector. Linear discriminant analysis is applied to the pose classes to generate the low dimension pose space.
    • 提供了用于产生低维度姿态空间并且使用姿态空间来估计用户头部的一个或多个头部旋转角度的方法。 在一个示例中,在多个条件下捕获包括测试对象头的训练图像帧。 对于每个帧,记录关于旋转轴的实际头部旋转角度。 在每帧中,检测到脸部图像并将其转换为LBP特征向量。 使用主成分分析生成PCA特征向量。 定义与旋转轴相关的旋转角度的姿态类。 PCA特征向量被分组为与PCA特征向量相关联的实际旋转角度对应的姿态类别。 将线性判别分析应用于姿态类以生成低维姿态空间。
    • 10. 发明授权
    • Learning object cutout from a single example
    • 从一个例子学习对象剪切
    • US08644600B2
    • 2014-02-04
    • US11810595
    • 2007-06-05
    • Qiong YangFang WenXiaoou Tang
    • Qiong YangFang WenXiaoou Tang
    • G06K9/00
    • G06K9/621G06T7/11G06T7/12G06T7/162G06T7/174G06T7/194G06T7/90G06T2207/10024G06T2207/20072G06T2207/20081G06T2207/20121
    • Systems and methods are described for learning visual object cutout from a single example. In one implementation, an exemplary system determines the color context near each block in a model image to create an appearance model. The system also learns color sequences that occur across visual edges in the model image to create an edge profile model. The exemplary system then infers segmentation boundaries in unknown images based on the appearance model and edge profile model. In one implementation, the exemplary system minimizes the energy in a graph-cut model where the appearance model is used for data energy and the edge profile is used to modulate edges. The system is not limited to images with nearly identical foregrounds or backgrounds. Some variations in scale, rotation, and viewpoint are allowed.
    • 描述了从单个示例中学习视觉对象切割的系统和方法。 在一个实现中,示例性系统确定模型图像中每个块附近的颜色上下文以创建外观模型。 该系统还学习在模型图像中跨视觉边缘发生的颜色序列,以创建边缘轮廓模型。 然后,示例性系统基于外观模型和边缘轮廓模型来推断未知图像中的分割边界。 在一个实现中,示例性系统最小化图形切割模型中的能量,其中外观模型用于数据能量,并且边缘轮廓用于调制边缘。 该系统不限于具有几乎相同的前景或背景的图像。 允许在比例尺,旋转角度和视角上有一些变化。