公开(公告)号：US06446060B1

公开(公告)日：2002-09-03

申请号：US09237734

申请日：1999-01-26

申请人： Lawerence D. Bergman ,  Vittorio Castelli ,  Chung-Sheng Li ,  John R. Smith

发明人： Lawerence D. Bergman ,  Vittorio Castelli ,  Chung-Sheng Li ,  John R. Smith

IPC分类号： G06F1730

CPC分类号： G06F17/30262 ,  G06F17/3025 ,  G06F17/30259 ,  G06F17/30265 ,  Y10S707/915 ,  Y10S707/956 ,  Y10S707/99933 ,  Y10S707/99945

摘要： Similarity measure has been one of the critical issues for successful content-based retrieval. Simple quadratic forms of distance is inadequate as it does not necessary correspond to perceived similarity nor is it adaptive to different applications. This patent application describes a new sequential query processing algorith for evaluating content-based composite object queries. The composite objects consist of spatial and temporal arrangements of simple objects. The simple objects are defined in terms of spatial, temporal, feature and semantic attributes. The query method defines a process for executing a best-first search for the matches to the query, while providing a flexible framework for broadening the search space as required. The query method guarantees that there are no false dismissals of the candidate composite objects.

摘要翻译： 相似性度量一直是成功基于内容检索的关键问题之一。 距离的简单二次形式是不充分的，因为它不需要对应于感知的相似性，也不适用于不同的应用。 该专利申请描述了用于评估基于内容的复合对象查询的新的顺序查询处理算法。 复合对象由简单对象的空间和时间排列组成。 简单的对象是根据空间，时间，特征和语义属性来定义的。 查询方法定义了一种用于执行对查询的匹配的最佳搜索的过程，同时提供了一种灵活的框架，用于根据需要扩展搜索空间。 查询方法保证对候选复合对象没有虚假的解雇。

公开(公告)号：US07272593B1

公开(公告)日：2007-09-18

申请号：US09237646

申请日：1999-01-26

申请人： Vittorio Castelli ,  Chung-Sheng Li ,  John R. Smith

发明人： Vittorio Castelli ,  Chung-Sheng Li ,  John R. Smith

IPC分类号： G06F17/30

CPC分类号： G06F17/30648 ,  G06F17/3069 ,  G06K9/6251 ,  G06K9/6254 ,  Y10S707/957 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99937 ,  Y10S707/99945

摘要： An iterative refinement algorithm for content-based retrieval of images based on low-level features such as textures, color histograms, and shapes that can be described by feature vectors. This technique adjusts the original feature space to the new application by performing nonlinear multidimensional scaling. Consequently, the transformed distance of those feature vectors which are considered to be similar is minimized in the new feature space. Meanwhile, the distance among clusters are maintained. User feedback is utilized to refine the query, by dynamically adjusting the similarity measure and modifying the linear transform of features, along with revising the feature vectors.

摘要翻译： 一种基于内容的图像检索的迭代细化算法，其基于诸如纹理，颜色直方图和可由特征向量描述的形状的低级特征。 该技术通过执行非线性多维缩放来调整新应用程序的原始特征空间。 因此，被认为是相似的那些特征向量的变换距离在新特征空间中被最小化。 同时，保持簇之间的距离。 用户反馈用于通过动态调整相似性度量和修改特征的线性变换以及修改特征向量来优化查询。

公开(公告)号：US06535872B1

公开(公告)日：2003-03-18

申请号：US09288580

申请日：1999-04-08

申请人： Vittorio Castelli ,  Chung-Sheng Li ,  John R. Smith

发明人： Vittorio Castelli ,  Chung-Sheng Li ,  John R. Smith

IPC分类号： G06F1730

CPC分类号： G06F17/30592 ,  G06F17/30554 ,  Y10S707/99933 ,  Y10S707/99936

摘要： Apparatus and method for generating a view element representation of multiple-attribute tabular data are provided, including converting tabular data into a multidimensional lattice form whereby each functional attribute of the relational data is mapped to a dimension in the lattice, and each cell in the lattice corresponds to an aggregation over records in the data table. The mechanism further provides for generating a view element representation of multidimensional lattice data comprising decomposing the multidimensional data into view elements such that the view elements retain sufficient information to reconstruct the original lattice data. Alternatively, the mechanism for generating a view element data representation including iterative decomposition of the lattice data into aggregated and residual view elements or by spatially partitioning the lattice data. Further taught are an apparatus and a method for generating a view element data representation including the decomposition of the lattice data by iteratively and jointly aggregating and spatially partitioning the lattice data. Under the system for representing the data using view element sets, costs and benefits are assigned to the view elements and the view element sets are formed on the bases of the costs and benefits. A view of the data from a set of view elements is synthesized by selecting view elements from the view element sets and assembling the view elements together to construct the views.

摘要翻译： 提供了用于生成多属性表格数据的视图元素表示的装置和方法，包括将表格数据转换为多维格子形式，由此将关系数据的每个功能属性映射到格子中的维度，并且格子中的每个单元格 对应于数据表中的记录上的聚合。 该机制进一步提供用于生成多维网格数据的视图元素表示，包括将多维数据分解为视图元素，使得视图元素保留足够的信息以重构原始格点数据。 或者，用于生成视图元素数据表示的机制，包括将格点数据迭代分解为聚合和残留视图元素或通过空间分割格点数据。 进一步教导的是用于生成视图元素数据表示的装置和方法，该视图元素数据表示包括通过迭代地并且共同地聚集和空间分割格点数据来分解格点数据。 在使用视图元素集合表示数据的系统下，成本和收益被分配给视图元素，并且视图元素集是基于成本和收益而形成的。 通过从视图元素集合中选择视图元素并将视图元素组合在一起以构建视图来合成来自一组视图元素的数据的视图。

公开(公告)号：US07818329B2

公开(公告)日：2010-10-19

申请号：US11759654

申请日：2007-06-07

申请人： Murray S. Campbell ,  Shahram Ebadollahi ,  Matthew L. Hill ,  Brian Michael Landry ,  Chung-Sheng Li ,  Apostol Ivanov Natsev ,  Milind R. Naphade ,  John R. Smith ,  Jelena Tesic ,  Lexing Xie

发明人： Murray S. Campbell ,  Shahram Ebadollahi ,  Matthew L. Hill ,  Brian Michael Landry ,  Chung-Sheng Li ,  Apostol Ivanov Natsev ,  Milind R. Naphade ,  John R. Smith ,  Jelena Tesic ,  Lexing Xie

IPC分类号： G06F17/30

CPC分类号： G06F17/30056 ,  G06F17/30038 ,  Y10S707/99934

摘要： A method and apparatus is disclosed that receives an input narrative in a particular media format, and produces therefrom a multimedia enriched version of the input narrative. In one embodiment, a method is provided for enriching an input narrative with multimedia content, wherein the method includes the step of selectively segmenting the input narrative to form queries pertaining to different portions or elements of the input narrative. The method further comprises retrieving multimedia artifacts from one or more multimedia repositories, wherein each retrieved multimedia artifact is associated with one of the queries, and selecting a subset of the retrieved multimedia artifacts, wherein the subset includes artifacts comprising different types of multimedia content. The input narrative is then combined with respective multimedia artifacts of the subset, in order to provide an enriched and enhanced narrative.

摘要翻译： 公开了一种以特定媒体格式接收输入叙述的方法和装置，并从其产生输入叙述的多媒体增强版本。 在一个实施例中，提供了一种用于利用多媒体内容丰富输入叙事的方法，其中所述方法包括选择性地分割输入叙述以形成关于输入叙述的不同部分或元素的查询的步骤。 该方法还包括从一个或多个多媒体存储库检索多媒体伪影，其中每个检索到的多媒体伪影与查询中的一个相关联，并且选择检索到的多媒体伪影的子集，其中该子集包括包含不同类型的多媒体内容的伪影。 然后将输入叙述与该子集的相应多媒体工件组合，以便提供丰富和增强的叙事。

公开(公告)号：US07401062B2

公开(公告)日：2008-07-15

申请号：US11451972

申请日：2006-06-13

申请人： Chung-Sheng Li ,  Ching-Yung Lin ,  Milind R. Naphade ,  John R. Smith

发明人： Chung-Sheng Li ,  Ching-Yung Lin ,  Milind R. Naphade ,  John R. Smith

IPC分类号： G06F17/00 ,  G06F15/18 ,  G06N5/02

CPC分类号： G06F9/50 ,  G06N99/005

摘要： Methods and apparatus for optimizing resource allocation among data analysis functions in a classification system are provided. Each of the data analysis functions is characterized as a set of operating points in accordance with at least one of resource requirements and analysis quality. An operating point for each of the data analysis functions is selected in accordance with one or more constraints. The analysis functions are applied at selected operating points to optimize resource allocation among the data analysis functions in the classification system.

摘要翻译： 提供了一种用于优化分类系统中数据分析功能之间的资源分配的方法和装置。 根据资源需求和分析质量中的至少一个，每个数据分析功能被表征为一组操作点。 根据一个或多个约束来选择每个数据分析功能的操作点。 分析功能应用于所选择的操作点，以优化分类系统中数据分析功能之间的资源分配。

公开(公告)号：US20080168462A1

公开(公告)日：2008-07-10

申请号：US12054955

申请日：2008-03-25

申请人： Chung-Sheng Li ,  Ching-Yung Lin ,  Milind R. Naphade ,  John R. Smith

发明人： Chung-Sheng Li ,  Ching-Yung Lin ,  Milind R. Naphade ,  John R. Smith

IPC分类号： G06F9/46

CPC分类号： G06F9/50 ,  G06N99/005

摘要： Methods and apparatus for optimizing resource allocation among data analysis functions in a classification system are provided. Each of the data analysis functions is characterized as a set of operating points in accordance with at least one of resource requirements and analysis quality. An operating point for each of the data analysis functions is selected in accordance with one or more constraints. The analysis functions are applied at selected operating points to optimize resource allocation among the data analysis functions in the classification system.

摘要翻译： 提供了一种用于优化分类系统中数据分析功能之间的资源分配的方法和装置。 根据资源需求和分析质量中的至少一个，每个数据分析功能被表征为一组操作点。 根据一个或多个约束来选择每个数据分析功能的操作点。 分析功能应用于所选择的操作点，以优化分类系统中数据分析功能之间的资源分配。

公开(公告)号：US06819797B1

公开(公告)日：2004-11-16

申请号：US09493879

申请日：2000-01-28

申请人： John R. Smith ,  Chung-Sheng Li

发明人： John R. Smith ,  Chung-Sheng Li

IPC分类号： G06K900

CPC分类号： G06K9/00744 ,  G06F17/30802 ,  G06F17/30811 ,  G06F17/30825 ,  G06F17/30831 ,  G06F17/30858 ,  G06K9/4685 ,  Y10S707/99933 ,  Y10S707/99945

摘要： A method and apparatus for classifying or annotating image and video content by assigning each class of event, action, region or object a unique symbol and then building symbol strings to represent sequences in space or time. The symbol strings can be decoded using a library of annotated PT descriptors to automatically label the image and video content. Furthermore, the PT descriptors can be used for searching by sketch or searching by example where the search query input is converted to symbol strings, which are efficiently compared based on the presence and relative counts of PT descriptors mapped into a PT matrices. The Precedence Template (PT) descriptor can be used for classifying and querying video based on the spatial and temporal orderings of regions, objects, actions or events. Applied to video, the PT descriptors provide a way to compare the temporal order of events, actions, or objects such as those represented in a scene transition graph, key-frame list, or event string. Applied to images, the PT descriptors provide a way to compare the spatial arrangement of image regions or objects. By capturing the spatial and temporal relationships statistically, the PT descriptors provide a robust way to measure similarity in the presence of insertions, deletions, substitutions, replications and relocations of events, actions, regions or objects.

摘要翻译： 一种分类或注释图像和视频内容的方法和装置，通过将每个类别的事件，动作，区域或对象分配给唯一符号，然后构建符号串来表示空间或时间中的序列。 可以使用带注释的PT描述符的库对符号串进行解码，以自动标记图像和视频内容。 此外，PT描述符可以用于通过草图搜索或通过示例搜索，其中搜索查询输入被转换为符号串，其基于映射到PT矩阵的PT描述符的存在和相对计数被有效地比较。 优先级模板（PT）描述符可以用于基于区域，对象，动作或事件的空间和时间顺序对视频进行分类和查询。 适用于视频的PT描述符提供了一种比较场景转换图，关键帧列表或事件串中表示的事件，动作或对象的时间顺序的方法。 应用于图像，PT描述符提供了一种比较图像区域或对象的空间排列的方法。 通过统计地捕获空间和时间关系，PT描述符提供了在事件，动作，区域或对象的插入，删除，替换，复制和重新定位的情况下测量相似性的可靠方式。

公开(公告)号：US08165983B2

公开(公告)日：2012-04-24

申请号：US12054955

申请日：2008-03-25

申请人： Chung-Sheng Li ,  Ching-Yung Lin ,  Milind R. Naphade ,  John R. Smith

发明人： Chung-Sheng Li ,  Ching-Yung Lin ,  Milind R. Naphade ,  John R. Smith

IPC分类号： G06F17/00 ,  G06F15/18 ,  G06N5/02

CPC分类号： G06F9/50 ,  G06N99/005

摘要： Methods and apparatus for optimizing resource allocation among data analysis functions in a classification system are provided. Each of the data analysis functions is characterized as a set of operating points in accordance with at least one of resource requirements and analysis quality. An operating point for each of the data analysis functions is selected in accordance with one or more constraints. The analysis functions are applied at selected operating points to optimize resource allocation among the data analysis functions in the classification system.

摘要翻译： 提供了一种用于优化分类系统中数据分析功能之间的资源分配的方法和装置。 根据资源需求和分析质量中的至少一个，每个数据分析功能被表征为一组操作点。 根据一个或多个约束来选择每个数据分析功能的操作点。 分析功能应用于所选择的操作点，以优化分类系统中数据分析功能之间的资源分配。

公开(公告)号：US06847980B1

公开(公告)日：2005-01-25

申请号：US09607974

申请日：2000-06-30

申请人： Ana B. Benitez ,  Alejandro Jaimes ,  Shih-Fu Chang ,  John R. Smith ,  Chung-sheng Li

发明人： Ana B. Benitez ,  Alejandro Jaimes ,  Shih-Fu Chang ,  John R. Smith ,  Chung-sheng Li

IPC分类号： G06F17/30

CPC分类号： G06F17/30604 ,  G06F17/30017 ,  G06F17/30858 ,  Y10S707/913 ,  Y10S707/914 ,  Y10S707/916 ,  Y10S707/99945

摘要： An invention for generating standard description records from multimedia information. The invention utilizes fundamental entity-relation models for the Generic AV DS that classify the entities, the entity attributes, and the relationships in relevant types to describe visual data. It also involves classification of entity attributes into syntactic and semantic attributes. Syntactic attributes can be categorized into different levels: type/technique, global distribution, local structure, and global composition. Semantic attributes can be likewise discretely categorized: generic object, generic scene, specific object, specific scene, abstract object, and abstract scene. The invention further classifies entity relationships into syntactic/semantic categories. Syntactic relationship categories include spatial, temporal, and visual categories. Semantic relationship categories include lexical and predicative categories. Spatial and temporal relationships can be topological or directional; visual relationships can be global, local, or composition; lexical relationships can be synonymy, antonymy, hyponymy/hypernymy, or meronymy/holonymy; and predicative relationships can be actions (events) or states.

摘要翻译： 一种用于从多媒体信息生成标准描述记录的发明。 本发明为通用AV DS使用基本实体关系模型，对实体进行分类，实体属性以及相关类型的关系来描述视觉数据。 它还涉及将实体属性分类为语法和语义属性。 语法属性可以分为不同的层次：类型/技术，全局分布，局部结构和全局组成。 语义属性可以同样地离散分类：通用对象，通用场景，特定对象，特定场景，抽象对象和抽象场景。 本发明进一步将实体关系分类为语义/语义类别。 句法关系类别包括空间，时间和视觉类别。 语义关系类别包括词汇和谓词类别。 空间和时间关系可以是拓扑或方向性; 视觉关系可以是全局，本地或组合; 词汇关系可以是同义词，antonymy，hyponymy / hypernymy，或meronymy / holonymy; 而谓词关系可以是行为（事件）或状态。

公开(公告)号：US06223183B1

公开(公告)日：2001-04-24

申请号：US09493435

申请日：2000-01-29

申请人： John R. Smith ,  Chung-Sheng Li

发明人： John R. Smith ,  Chung-Sheng Li

IPC分类号： G06F1730

CPC分类号： G06F17/30256 ,  G06F17/30017 ,  Y10S707/99942 ,  Y10S707/99943

摘要： A system and method for uniformly describing space and frequency views of multi-dimensional lattice data, including regions, tilings and hierarchical decompositions of image, video, audio content, and time series data in space, time, frequency and resolution. The space and frequency view description scheme provides a way to specify regions in space, time, frequency and resolution in term of space and frequency views. This allows specification of concepts such as “half resolution”, “upper right quadrant” or “high pass band”, such as when referring to views of an image. The space and frequency view description scheme also provides for SFTilings comprising non-redundant sets of views and SFPartitionings which are SFTilings which completely cover the space, as well as SFHierarchical decompositions comprising hierarchies of SFViews where there are processing dependencies among views. The inventive system and method also provide a way to index these view, which is important in applications of progressive retrieval in which a client application can send requests for views of images stored at a server in terms of an index value. The space and frequency view description scheme handles the details concerning the access and relationship of views with different resolutions, spatial locations and sizes.

摘要翻译： 用于统一描述多维格点数据的空间和频率视图的系统和方法，包括空间，时间，频率和分辨率的图像，视频，音频内容和时间序列数据的区域，方向和分层分解。 空间和频率视图描述方案提供了一种在空间和频率视图方面指定空间，时间，频率和分辨率的区域的方法。 这允许指定诸如“半分辨率”，“右上象限”或“高通频带”之类的概念，诸如当提及图像的视图时。 空间和频率视图描述方案还提供了包括非冗余视图组和SFP分区的SFT，其中SFP分区是完全覆盖该空间的SFT，以及包括在视图之间具有处理依赖性的SFView的层次结构的SF层级分解。 本发明的系统和方法还提供了一种索引这些视图的方法，这在逐行检索的应用中是重要的，其中客户端应用可以根据索引值发送存储在服务器上的图像的视图的请求。 空间和频率视图描述方案处理关于不同分辨率，空间位置和大小的视图的访问和关系的细节。