-
公开(公告)号：EP1125245A4
公开(公告)日：2004-04-14
申请号：EP99971950
申请日：1999-11-05
Applicant: UNIV COLUMBIA , AT & T CORP , IBM , EASTMAN KODAK CO
Inventor： PAEK SEUNGYUP , BENITEZ ANA , CHANG SHIH-FU , LI CHUNG-SHENG , SMITH JOHN R , BERGMAN LAWRENCE D , PURI ATUL , HUANG QIAN , JUDICE CHARLIE
IPC: G06T1/00 , G06F17/30 , G06T7/00 , G11B27/00 , H04N5/76 , H04N5/91 , H04N5/92 , H04N7/08 , H04N7/081 , H04N7/26
CPC classification number: G06F17/30011 , G06F17/3028 , G06F17/3079 , G06F17/30796 , G06F17/30858 , G06K9/00677 , G06K9/46
Abstract: Systems and methods for describing image content establish image description records which include an object set (24), an object hierarchy (26) and entity relation graphs (28). For image content, image objects can include global objects (O0 8) and local objects (O1 2 and O2 6). The image objects are further defined by a number of features of different classes (36, 38 and 40), which in turn are further defined by a number of feature descriptors. The relationships between and among the objects in the object set are defined by the object hierarchy (26) and entity relation graphs (28). The image description records provide a standard vehicle for describing the content and context of image information for subsequent access and processing by computer applications such as search engines, filters, and archive systems.
Abstract translation: 用于描述图像内容的系统和方法建立包括对象集（24），对象分层结构（26）和实体关系图（28）的图像描述记录。 对于图像内容，图像对象可以包括全局对象（O0 8）和本地对象（O1 2和O2 6）。 图像对象进一步由不同类别（36,38和40）的许多特征定义，而这些特征又由许多特征描述符进一步定义。 对象集合中对象之间的关系由对象层次结构（26）和实体关系图（28）定义。 图像描述记录为描述图像信息的内容和上下文提供了一个标准工具，以供计算机应用程序（如搜索引擎，过滤器和存档系统）随后访问和处理。
-
2.发明公开FUNDAMENTAL ENTITY-RELATIONSHIP MODELS FOR THE GENERIC AUDIO VISUAL DATA SIGNAL DESCRIPTION 审中-公开基本单位关系模型描述一般视听数据信号
公开(公告)号：EP1194870A4
公开(公告)日：2008-03-26
申请号：EP00946974
申请日：2000-06-30
Applicant: UNIV COLUMBIA , IBM
Inventor： BENITEZ ANA , JAIMES ALEJANDRO , CHANG SHIH-FU , SMITH JOHN R , LI CHUNG-SHENG
CPC classification number: G06F17/30604 , G06F17/30017 , G06F17/30858
Abstract: Systems and methods for generating standard description records from multimedia information are provided. 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 describing visual data. It 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 categorized into different levels: generic object, generic scene, specific object, specific scene, abstract object, and abstract scene. The invention further utilizes classification of entity relationships into syntactic and semantic categories. Syntactic relationships can be categorized into spatial, temporal, and visual categories. Semantic relationships can be categorized into lexical and predicative categories.
-
公开(公告)号：EP1151398A4
公开(公告)日：2004-04-14
申请号：EP00915716
申请日：2000-02-01
Applicant: UNIV COLUMBIA , IBM
Inventor： BENITEZ ANA B , JAIMES ALEJANDRO , PAEK SEUNGYUP , CHANG SHIH-FU , LI CHUNG-SHENG , SMITH JOHN R
CPC classification number: G06F17/30017 , G06F17/3028
Abstract: A multimedia archive description scheme is provided for characterizing a multimedia archive having records and associated record descriptions. The multimedia archive description scheme provides a data structure which relates records by similarity measures. The principle data structure in the multimedia archive description scheme is a cluster (100). A cluster includes one or more attributes of the records in the archive and can include one or more cluster relationships (110). Cluster attributes (105) can include feature space attributes, semantic attributes, media attributes and meta attributes of the records in the archive. The cluster relationships (110) can relate records to clusters or clusters to clusters. Cluster relationships can include feature space (syntactic) relationships, sematic relationships, media relationships and meta relationships. The multimedia archive description scheme provides an efficient form for describing a collection of records.
-
4.发明专利
公开(公告)号：JP2003099320A
公开(公告)日：2003-04-04
申请号：JP2002161305
申请日：2002-06-03
Applicant: IBM
Inventor： LI CHUNG-SHENG , SMITH JOHN R , CHANG YUAN-CHI , JHINGRAN ANANT D , PADMANABHAN SRIRAM K , HSIAO HUI-I , CHOY DAVID MUN-HIEN , LIN JY-JINE JAMES , FUH GENE Y C , WILLIAMS ROBIN , BERGMAN LAWRENCE D
Abstract: PROBLEM TO BE SOLVED: To provide a method and an apparatus for constructing and implementing a universal extension module for processing objects in a database. SOLUTION: A multi-tier database architecture comprises an object-relational database engine as a top tier, one or more domain-specific extension modules as a bottom tier, and one or more universal extension modules as a middle tier. The individual extension modules of the bottom tier operationally connect with the one or more universal extension modules which, themselves operationally connect with the database engine. The domain-specific extension modules preferably provide such functions as searching, indexing, and retrieval services of images, video, audio, time series, web pages, text, XML, spatial data, etc.
-
5.发明公开TEMPORAL SEGMENT BASED EXTRACTION AND ROBUST MATCHING OF VIDEO FINGERPRINTS 审中-公开ON时段提取物为基础及稳健比较视频指纹
公开(公告)号：EP2240871A4
公开(公告)日：2014-04-09
申请号：EP08861964
申请日：2008-11-24
Applicant: IBM
Inventor： CHANG JANE WEN , NATSEV APOSTOL IVANOV , SMITH JOHN R
CPC classification number: G06K9/00758 , G06F17/30781 , G06K9/00744 , H04H60/37 , H04H60/59 , H04H2201/90
Abstract: A computer implemented method, apparatus, and computer program product code for temporal, event-based video fingerprinting. In one embodiment, events in video content are detected. The video content comprises a plurality of video frames. An event represents discrete points of interest in the video content. A set of temporal, event-based segments are generated using the events. Each temporal, event-based segment is a segment of the video content covering a set of events. A time series signal is derived from each temporal, event-based segment using temporal tracking of content-based features of a set of frames associated with the each temporal, event-based segment. A temporal segment based fingerprint is extracted based on the time series signal for the each temporal, event-based segment to form a set of temporal segment based fingerprints associated with the video content.
-
Patent Agency Ranking
公开(公告)号：JP2000222276A
公开(公告)日：2000-08-11
申请号：JP2000019357
申请日：2000-01-27
Applicant: IBM
Inventor： SAMUEL S ADAMS , HILD STEFAN G , LA MAIRE RICHARD O , HIROSHI MARUYAMA , RAKESHU MOOHAN , SANDEEPU SHINHARU , SMITH JOHN R
Abstract: PROBLEM TO BE SOLVED: To make it easy for a general computing device to display web contents by changing elements in an HTML file by using information included in a retrieved content modification file. SOLUTION: When the general computing device requests an HTML file (B100), the HTML file is analyzed and a link to a content-modified file including information regarding the modification of elements in the HTML file is discriminated so that the file can be displayed by the general computing device (B200). Then the link is used to retrieve the discriminated content-modified file (B300). The information in the retrieved content-modified file is used to change selected elements of the HTML file so that the file is displayed by the reqeust-side general computing device (B600).
-
7.发明申请METHOD AND APPARATUS FOR CLASSIFYING MULTIMEDIA ARTIFACTS USING ONTOLOGY SELECTION AND SEMANTIC CLASSIFICATION 审中-公开使用本体选择和语义分类来分类多媒体伪影的方法和设备
公开(公告)号：WO2008086032A3
公开(公告)日：2008-08-21
申请号：PCT/US2008000364
申请日：2008-01-10
Applicant: IBM
Inventor： NAPHADE MILIND R , SMITH JOHN R , TESIC JELENA
IPC: G06F17/30
CPC classification number: G06F17/30707 , G06F17/30038 , Y10S707/99944
Abstract: A method and apparatus is provided for automatically classifying a multimedia artifact (204) based on scoring, and selecting the appropriate set of ontologies from among all possible sets of ontologies (206), preferably using a recursive routing selection technique (202). The semantic tagging of the multimedia artifact (204) is enhanced by applying only classifiers (208) from the selected ontology (206), for use in classifying the multimedia artifact (204), wherein the classifiers are selected based on the context of the multimedia artifact (204). One embodiment of the invention, directed to a method for classifying a multimedia artifact (204), uses a specified criteria to select one or more ontologies (206), wherein the specified criteria indicates the comparative similarity between specified characteristics of the multimedia artifact (204) and each ontology (206). The method further comprises scoring and selecting one or more classifiers (208) from a plurality of classifiers (208) that respectively correspond to semantic element of the selected ontologies (206), and evaluating the multimedia artifact (204) using the selected classifiers (208) to determine a classification for the multimedia artifact (204).
Abstract translation: 提供了一种方法和装置，用于基于评分自动分类多媒体人工产物（204），并且优选地使用递归路由选择技术（202）从所有可能的本体集合（206）中选择适当的本体集合。 通过仅应用来自所选本体（206）的分类器（208）来增强多媒体伪像（204）的语义标签以用于分类多媒体伪像（204），其中基于多媒体的上下文来选择分类器 神器（204）。 涉及用于分类多媒体人工产物（204）的方法的本发明的一个实施例使用指定的标准来选择一个或多个本体论（206），其中指定的标准指示多媒体人工产物（204）的指定特征之间的比较相似性 ）和每个本体（206）。 该方法进一步包括从分别对应于所选本体（206）的语义元素的多个分类器（208）中评分和选择一个或多个分类器（208），并且使用所选择的分类器（208）评估多媒体工件（204） ）来确定多媒体伪像的分类（204）。
-
公开(公告)号：WO0045307A9
公开(公告)日：2001-12-27
申请号：PCT/US0002488
申请日：2000-02-01
Applicant: UNIV COLUMBIA , IBM , BENITEZ ANA B , JAIMES ALEJANDRO , PAEK SEUNGYUP , CHANG SHIH FU , LI CHUNG SHENG , SMITH JOHN R
Inventor： BENITEZ ANA B , JAIMES ALEJANDRO , PAEK SEUNGYUP , CHANG SHIH-FU , LI CHUNG-SHENG , SMITH JOHN R
CPC classification number: G06F17/30017 , G06F17/3028
Abstract: A multimedia archive description scheme is provided for characterizing a multimedia archive having records and associated record descriptions. The multimedia archive description scheme provides a data structure which relates records by similarity measures. The principle data structure in the multimedia archive description scheme is a cluster (100). A cluster includes one or more attributes of the records in the archive and can include one or more cluster relationships (110). Cluster attributes (105) can include feature space attributes, semantic attributes, media attributes and meta attributes of the records in the archive. The cluster relationships (110) can relate records to clusters or clusters to clusters. Cluster relationships can include feature space (syntactic) relationships, sematic relationships, media relationships and meta relationships. The multimedia archive description scheme provides an efficient form for describing a collection of records.
Abstract translation: 提供了多媒体档案描述方案，用于表征具有记录和相关联的记录描述的多媒体档案。 多媒体档案描述方案提供了一种通过相似度测量来记录记录的数据结构。 多媒体档案描述方案中的原理数据结构是集群（100）。 集群包括归档中的记录的一个或多个属性，并且可以包括一个或多个集群关系（110）。 集群属性（105）可以包括归档中的记录的特征空间属性，语义属性，媒体属性和元属性。 集群关系（110）可以将记录与集群或集群关联到集群。 集群关系可以包括特征空间（句法）关系，语义关系，媒体关系和元关系。 多媒体档案描述方案提供了一种用于描述记录集合的有效形式。
-
9.发明申请SYSTEM AND METHOD FOR ANNOTATING MULTI-MODAL CHARACTERISTICS IN MULTIMEDIA DOCUMENTS 审中-公开多媒体文件中提供多模式特征的系统与方法
公开(公告)号：WO2004059536A3
公开(公告)日：2004-12-29
申请号：PCT/US0340726
申请日：2003-12-19
Applicant: IBM , ADAMS HUGH W JR , IYENGAR GIRIDHAREN , LIN CHING-YUNG , NETI CHALAPATHY V , SMITH JOHN R , TSENG BELLE L
Inventor： ADAMS HUGH W JR , IYENGAR GIRIDHAREN , LIN CHING-YUNG , NETI CHALAPATHY V , SMITH JOHN R , TSENG BELLE L
CPC classification number: G06F17/30038 , G06F17/241
Abstract: A manual annotation system of multi-modal characteristics in multimedia files. There is provided an arrangement for selection an observation modality of video with audio, video without audio, audio with video, or audio without video, to be used to annotate multimedia content. While annotating video or audio features is isolation results in less confidence in the identification of features, observing both audio and video simultaneously and annotating that observation results in a higher confidence level.
-
10.发明申请METHOD AND APPARATUS FOR CLASSIFYING MULTIMEDIA ARTIFACTS USING ONTOLOGY SELECTION AND SEMANTIC CLASSIFICATION 审中-公开使用本体选择和语义分类分类多媒体手段的方法和装置
公开(公告)号：WO2008086032A2
公开(公告)日：2008-07-17
申请号：PCT/US2008000364
申请日：2008-01-10
Applicant: IBM
Inventor： NAPHADE MILIND R , SMITH JOHN R , TESIC JELENA
IPC: G06F17/30
CPC classification number: G06F17/30707 , G06F17/30038 , Y10S707/99944
Abstract: A method and apparatus is provided for automatically classifying a multimedia artifact (204) based on scoring, and selecting the appropriate set of ontologies from among all possible sets of ontologies (206), preferably using a recursive routing selection technique (202). The semantic tagging of the multimedia artifact (204) is enhanced by applying only classifiers (208) from the selected ontology (206), for use in classifying the multimedia artifact (204), wherein the classifiers are selected based on the context of the multimedia artifact (204). One embodiment of the invention, directed to a method for classifying a multimedia artifact (204), uses a specified criteria to select one or more ontologies (206), wherein the specified criteria indicates the comparative similarity between specified characteristics of the multimedia artifact (204) and each ontology (206). The method further comprises scoring and selecting one or more classifiers (208) from a plurality of classifiers (208) that respectively correspond to semantic element of the selected ontologies (206), and evaluating the multimedia artifact (204) using the selected classifiers (208) to determine a classification for the multimedia artifact (204).
Abstract translation: 提供了一种方法和装置，用于基于评分来自动分类多媒体伪影（204），并且优选地使用递归路由选择技术（202）从所有可能的本体集合（206）中选择适当的本体集合。 通过仅从所选择的本体（206）应用分类器（208）来增强多媒体伪像（204）的语义标记，以用于分类多媒体伪像（204），其中基于多媒体的上下文来选择分类器 神器（204）。 本发明的一个实施例涉及用于分类多媒体伪影（204）的方法，使用指定的标准来选择一个或多个本体（206），其中指定的标准表示多媒体伪影（204）的特定特征之间的比较相似度 ）和每个本体（206）。 该方法还包括从分别对应于所选本体（206）的语义元素的多个分类器（208）中对一个或多个分类器（208）进行评分和选择，以及使用所选择的分类器（208）评估多媒体伪像（204） ）来确定多媒体伪像的分类（204）。
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.02 seconds)
