专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US07750903B2 Modeling reflections within an image sequence 有权
标题翻译：建模图像序列中的反射
公开(公告)号：US07750903B2
公开(公告)日：2010-07-06
申请号：US11534647
申请日：2006-09-23
申请人： Nebojsa Jojic , Brendan J. Frey
发明人： Nebojsa Jojic , Brendan J. Frey
IPC分类号： G06T17/00
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.
摘要翻译：提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，视频序列中的图像或帧被表示为随时间改变其外观和形状的平坦移动对象的集合，并且可以随着时间而彼此闭塞。定义了统计生成模型，用于生成这样的视觉数据，其中诸如出现位图和噪声，形状位图和形状变异等参数是已知的。此外，当未知时，这些参数是通过使用最大化算法从视觉数据估计而没有预先预处理的。通过模型中的参数估计和推理，视觉数据被分割成有助于视频或图像编辑中的复杂应用的组件，例如对象去除或插入，跟踪和视觉监视，视频浏览，照片组织，视频合成，等等

52. 发明授权

US07729999B2 Program verification and discovery using probabilistic inference 有权
标题翻译：使用概率推理的程序验证和发现
公开(公告)号：US07729999B2
公开(公告)日：2010-06-01
申请号：US11622904
申请日：2007-01-12
申请人： Sumit Gulwani , Vladimir Jojic , Nebojsa Jojic
发明人： Sumit Gulwani , Vladimir Jojic , Nebojsa Jojic
IPC分类号： G06F15/18
CPC分类号： G06F11/3608
摘要： In one embodiment, a computer system performs a method for verifying the validity or invalidity of a software routine by learning appropriate invariants at each program point. A computer system chooses an abstract domain that is sufficiently precise to express the appropriate invariants. The computer system associates an inconsistency measure with any two abstract elements of the abstract domain. The computer system searches for a set of local invariants configured to optimize a total inconsistency measure which includes a sum of local inconsistency measures. The computer system optimizes the total inconsistency measure for all input/output pairs of the software routine. In one embodiment, the optimization of total inconsistency is achieved by the computer system which repeatedly replaces a locally inconsistent invariant with a new invariant, randomly selected among the possible invariants which are locally less inconsistent with the current invariants at the neighboring program points.
摘要翻译：在一个实施例中，计算机系统通过在每个程序点学习适当的不变量来执行用于验证软件例程的有效性或无效性的方法。计算机系统选择足够精确的表示适当不变量的抽象域。计算机系统将不一致性度量与抽象域的任意两个抽象元素相关联。计算机系统搜索一组局部不变量，其被配置为优化包括本地不一致性度量的总和的总不一致性度量。计算机系统优化软件程序的所有输入/输出对的总不一致性测量。在一个实施例中，总体不一致性的优化是通过计算机系统实现的，该计算机系统在局部地与邻近程序点的当前不变量局部较不一致的可能不变量中随机选择新的不变量来重复地替换局部不一致的不变量。

53. 发明申请

US20080282108A1 PROGRAM SYNTHESIS AND DEBUGGING USING MACHINE LEARNING TECHNIQUES 有权
标题翻译：使用机器学习技术的程序合成和调试
公开(公告)号：US20080282108A1
公开(公告)日：2008-11-13
申请号：US11745295
申请日：2007-05-07
申请人： Vladimir Jojic , Nebojsa Jojic , Sumit Gulwani
发明人： Vladimir Jojic , Nebojsa Jojic , Sumit Gulwani
IPC分类号： G06F9/44 , G06F11/00 , G06F15/18
CPC分类号： G06F11/3624 , G06F8/436
摘要： One embodiment is directed to synthesizing code fragments in a software routine using known inputs and corresponding expected outputs. A computer system provides a software routine with known inputs and corresponding expected outputs, infers software routine instructions based on the known inputs and corresponding expected outputs, and synthesizes a correctly functioning code fragment based on the inferred instructions. Another embodiment is directed to automatically resolving semantic errors in a software routine. A computer system provides the software routine with known inputs and corresponding expected outputs for portions of a program fragment where an error has been localized. The computer system learns a correctly functioning program fragment from pairs of input-output descriptions of the program fragment, determines the program statements that can transform given input states into given output states after execution of those program statements, and alters portions of the software routine with the learned program fragments.
摘要翻译：一个实施例涉及使用已知输入和相应的预期输出来合成软件例程中的代码片段。计算机系统提供具有已知输入和对应的预期输出的软件例程，基于已知输入和相应的预期输出推断软件程序指令，并且基于推断的指令来合成正确运行的代码片段。另一个实施例涉及自动解决软件程序中的语义错误。计算机系统向软件例程提供已知输入和对于已经本地化错误的程序片段的部分的相应的预期输出。计算机系统从程序片段的输入输出描述中学习正确运行的程序片段，确定在执行这些程序语句之后将给定的输入状态转换为给定的输出状态的程序语句，并且改变软件程序的一部分学习的程序片段。

54. 发明授权

US07274821B2 System and method to facilitate pattern recognition by deformable matching 失效
标题翻译：通过可变形匹配促进模式识别的系统和方法
公开(公告)号：US07274821B2
公开(公告)日：2007-09-25
申请号：US11302004
申请日：2005-12-13
申请人： Nebojsa Jojic , Patrice Simard
发明人： Nebojsa Jojic , Patrice Simard
IPC分类号： G06K9/62
CPC分类号： G06K9/6206 , Y10S707/99936
摘要： A system and method to facilitate pattern recognition or matching between patterns are disclosed that is substantially invariant to small transformations. A substantially smooth deformation field is applied to a derivative of a first pattern and a resulting deformation component is added to the first pattern to derive a first deformed pattern. An indication of similarity between the first pattern and a second pattern may be determined by minimizing the distance between the first deformed pattern and the second pattern with respect to deformation coefficients associated with each deformed pattern. The foregoing minimization provides a system (e.g., linear) that may be solved with standard methods.
摘要翻译：公开了一种促进模式识别或模式匹配的系统和方法，其基本上不变形为小变换。将基本平滑的变形场施加到第一图案的导数，并将所得到的变形分量添加到第一图案以导出第一变形图案。第一图案和第二图案之间的相似度的指示可以通过相对于与每个变形图案相关联的变形系数最小化第一变形图案和第二图案之间的距离来确定。上述最小化提供了可以用标准方法解决的系统（例如，线性）。

55. 发明授权

US07269560B2 Speech detection and enhancement using audio/video fusion 有权
标题翻译：使用音频/视频融合的语音检测和增强
公开(公告)号：US07269560B2
公开(公告)日：2007-09-11
申请号：US10608988
申请日：2003-06-27
申请人： John R. Hershey , Trausti Thor Kristjansson , Hagai Attias , Nebojsa Jojic
发明人： John R. Hershey , Trausti Thor Kristjansson , Hagai Attias , Nebojsa Jojic
IPC分类号： G10L21/00
CPC分类号： G10L15/065 , G10L15/20 , G10L15/25 , G10L25/78
摘要： A system and method facilitating speech detection and/or enhancement utilizing audio/video fusion is provided. The present invention fuses audio and video in a probabilistic generative model that implements cross-model, self-supervised learning, enabling rapid adaptation to audio visual data. The system can learn to detect and enhance speech in noise given only a short (e.g., 30 second) sequence of audio-visual data. In addition, it automatically learns to track the lips as they move around in the video.
摘要翻译：提供了利用音频/视频融合的促进语音检测和/或增强的系统和方法。本发明将音频和视频融合在实现跨模型，自我监督学习的概率生成模型中，使得能够快速适应视听数据。该系统可以学习仅在短（例如，30秒）的视听数据序列中检测和增强噪声中的语音。此外，它会自动学习在视频中移动时跟踪嘴唇。

56. 发明申请

US20070192039A1 SHIFT-INVARIANT PREDICTIONS 有权
标题翻译：移位不变预测
公开(公告)号：US20070192039A1
公开(公告)日：2007-08-16
申请号：US11738411
申请日：2007-04-20
申请人： Nebojsa Jojic , David Heckerman , Noah Zaitlen , Manuel Gomez
发明人： Nebojsa Jojic , David Heckerman , Noah Zaitlen , Manuel Gomez
IPC分类号： G06F19/00
CPC分类号： G06F19/18 , G06F19/16 , G06F19/24
摘要： Shift invariant predictors are described herein. By way of example, a system for predicting binding information relating to a binding of a protein and a ligand can include a trained binding model and a prediction component. The trained binding model can include a hidden variable representing an unknown alignment of the ligand at a binding site of the protein. The prediction component can be configured to predict the binding information by employing information about the protein's sequence, the ligand's sequence and the trained binding model.
摘要翻译：这里描述了移位不变量预测器。作为示例，用于预测与蛋白质和配体的结合相关的结合信息的系统可以包括训练的结合模型和预测组分。经训练的结合模型可以包括表示蛋白质结合位点处配体的未知比对的隐藏变量。预测组件可以被配置为通过使用关于蛋白质序列，配体序列和训练的结合模型的信息来预测结合信息。

57. 发明授权

US07243239B2 Click passwords 有权
标题翻译：点击密码
公开(公告)号：US07243239B2
公开(公告)日：2007-07-10
申请号：US10187311
申请日：2002-06-28
申请人： Darko Kirovski , Nebojsa Jojic , Paul Roberts
发明人： Darko Kirovski , Nebojsa Jojic , Paul Roberts
IPC分类号： H04K1/00 , H04L9/00
CPC分类号： G06F21/36
摘要： Methods, systems, devices and/or storage media for passwords. An exemplary method tiles an image, associates an index with each tile and optionally determines offsets for select tiles. Further, the tiling optionally relies on probability and/or entropy. An exemplary password system includes an image; a grid associated with the image, the grid composed of polygons; an index associated with each polygon; and an offset associated with each polygon wherein password identification relies on one or more indices and one or more offsets.
摘要翻译：用于密码的方法，系统，设备和/或存储介质。贴图图像的示例性方法，将索引与每个瓦片相关联，并且可选地确定选择瓦片的偏移量。此外，平铺可选地依赖于概率和/或熵。示例性密码系统包括图像; 与图像相关联的网格，网格由多边形组成; 与每个多边形相关联的索引; 以及与每个多边形相关联的偏移量，其中密码识别依赖于一个或多个索引和一个或多个偏移量。

58. 发明申请

US20070106626A1 Large-scale information collection and mining 有权
标题翻译：大型信息采集和挖掘
公开(公告)号：US20070106626A1
公开(公告)日：2007-05-10
申请号：US11266974
申请日：2005-11-04
申请人： Craig Mundie , David Heckerman , Nebojsa Jojic , Randy Hinrichs
发明人： Craig Mundie , David Heckerman , Nebojsa Jojic , Randy Hinrichs
IPC分类号： G06N3/02
CPC分类号： G06N99/005 , G06F19/00 , G06Q10/10 , G06Q50/24 , G16H50/20
摘要： The methods/systems described herein facilitate large-scale data collection and aggregation. One exemplary system that facilitates large-scale reporting of health-related data comprises a data collection component, a database and an aggregation component. The data collection component can collect health-related data on a large-scale from a non-selected population. The database can store at least some of the health-related data. The aggregation component can facilitate automatically ascertaining at least one pattern from the health-related data at least in part by applying one or more statistical, data-mining or machine-learning techniques to the database. One exemplary method of extracting health observations from information obtained on a macro-scale comprises receiving information about a plurality of self-selected subjects, pooling the information, mining the pooled information at least in part by employing a data-mining algorithm to infer one or more health observations from the pooled information, and monetizing the one or more health observations.
摘要翻译：这里描述的方法/系统有助于大规模数据收集和聚合。促进健康相关数据的大规模报告的一个示例性系统包括数据收集组件，数据库和聚合组件。数据收集组件可以从非选定人群大规模收集健康相关数据。数据库可以存储至少一些健康相关数据。聚合组件可以至少部分地通过将一个或多个统计，数据挖掘或机器学习技术应用于数据库来自动地从健康相关数据确定至少一个模式。从在宏观尺度上获得的信息中提取健康观测的一个示例性方法包括：接收关于多个自选择对象的信息，汇集信息，至少部分地通过采用数据挖掘算法推断出一个或多个从汇集的信息中获得更多的健康意见，并通过一个或多个健康观察获利。

59. 发明申请

US20070019884A1 MODELING REFLECTIONS WITHIN AN IMAGE SEQUENCE 有权
标题翻译：在图像序列中建模反射
公开(公告)号：US20070019884A1
公开(公告)日：2007-01-25
申请号：US11534647
申请日：2006-09-23
申请人： Nebojsa Jojic , Brendan Frey
发明人： Nebojsa Jojic , Brendan Frey
IPC分类号： G06K9/36 , G06T17/00
CPC分类号： G06T7/215 , G06T2207/10016 , G06T2207/30196
摘要： A simplified general model and an associated estimation algorithm is provided for modeling visual data such as a video sequence. Specifically, images or frames in a video sequence are represented as collections of flat moving objects that change their appearance and shape over time, and can occlude each other over time. A statistical generative model is defined for generating such visual data where parameters such as appearance bit maps and noise, shape bit-maps and variability in shape, etc., are known. Further, when unknown, these parameters are estimated from visual data without prior pre-processing by using a maximization algorithm. By parameter estimation and inference in the model, visual data is segmented into components which facilitates sophisticated applications in video or image editing, such as, for example, object removal or insertion, tracking and visual surveillance, video browsing, photo organization, video compositing, etc.
摘要翻译：提供了简化的一般模型和相关联的估计算法用于对诸如视频序列的视觉数据进行建模。具体来说，视频序列中的图像或帧被表示为随时间改变其外观和形状的平坦移动对象的集合，并且可以随着时间而彼此闭塞。定义了统计生成模型，用于生成这样的视觉数据，其中诸如出现位图和噪声，形状位图和形状变异等参数是已知的。此外，当未知时，这些参数是通过使用最大化算法从视觉数据估计而没有预先预处理的。通过模型中的参数估计和推理，视觉数据被分割成有助于视频或图像编辑中的复杂应用的组件，例如对象去除或插入，跟踪和视觉监视，视频浏览，照片组织，视频合成，等等

60. 发明授权

US06785419B1 System and method to facilitate pattern recognition by deformable matching 失效
公开(公告)号：US06785419B1
公开(公告)日：2004-08-31
申请号：US09748564
申请日：2000-12-22
申请人： Nebojsa Jojic , Patrice Simard
发明人： Nebojsa Jojic , Patrice Simard
IPC分类号： G06K948
CPC分类号： G06K9/6206 , Y10S707/99936
摘要： A system and method to facilitate pattern recognition or matching between patterns are disclosed that is substantially invariant to small transformations. A substantially smooth deformation field is applied to a derivative of a first pattern and a resulting deformation component is added to the first pattern to derive a first deformed pattern. An indication of similarity between the first pattern and a second pattern may be determined by minimizing the distance between the first deformed pattern and the second pattern with respect to deformation coefficients associated with each deformed pattern. The foregoing minimization provides a system (e.g., linear) that may be solved with standard methods.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式