-
公开(公告)号：US20140056432A1
公开(公告)日：2014-02-27
申请号：US13591489
申请日：2012-08-22
IPC分类号： H04R29/00
CPC分类号： G10L25/51
摘要： A method for determining a semantic concept associated with an audio signal captured using an audio sensor. A data processor is used to automatically analyze the audio signal using a plurality of semantic concept detectors to determine corresponding preliminary semantic concept detection values, each semantic concept detector being adapted to detect a particular semantic concept. The preliminary semantic concept detection values are analyzed using a joint likelihood model based on predetermined pair-wise likelihoods that particular pairs of semantic concepts co-occur to determine updated semantic concept detection values. One or more semantic concepts are determined based on the updated semantic concept detection values. The semantic concept detectors and the joint likelihood model are trained together with a joint training process using training audio signals, at least some of which are known to be associated with a plurality of semantic concepts.
摘要翻译： 一种用于确定与使用音频传感器捕获的音频信号相关联的语义概念的方法。 数据处理器用于使用多个语义概念检测器自动分析音频信号，以确定对应的初步语义概念检测值，每个语义概念检测器适于检测特定的语义概念。 基于预定的成对似然性，使用联合似然模型来分析初步语义概念检测值，特定的语义概念对共同出现以确定更新的语义概念检测值。 基于更新的语义概念检测值来确定一个或多个语义概念。 语义概念检测器和联合似然模型与使用训练音频信号的联合训练过程一起训练，其中至少一些已知与多个语义概念相关联。
-
公开(公告)号：US20140037269A1
公开(公告)日：2014-02-06
申请号：US13565926
申请日：2012-08-03
IPC分类号： G11B27/00
CPC分类号： G06K9/00765 , G06K9/6249 , G11B27/034 , G11B27/28
摘要： A method for identifying a set of key video frames from a video sequence comprising extracting feature vectors for each video frame and applying a group sparsity algorithm to represent the feature vector for a particular video frame as a group sparse combination of the feature vectors for the other video frames. Weighting coefficients associated with the group sparse combination are analyzed to determine video frame clusters of temporally-contiguous, similar video frames. A summary is formed based on the determined video frame clusters.
摘要翻译： 一种用于从视频序列中识别一组关键视频帧的方法，包括提取每个视频帧的特征向量，并且应用组稀疏算法来表示特定视频帧的特征向量作为另一个的特征向量的组稀疏组合 视频帧。 分析与组稀疏组合相关联的加权系数，以确定时间上相邻的类似视频帧的视频帧聚类。 基于确定的视频帧聚类形成摘要。
-
公开(公告)号：US20140037215A1
公开(公告)日：2014-02-06
申请号：US13565911
申请日：2012-08-03
IPC分类号： G06K9/48
CPC分类号： G06K9/48 , G06K9/00718 , G06K9/00744 , G06K9/00751 , G06K9/00765 , G06K9/6224
摘要： A method for identifying a set of key video frames from a video sequence comprising extracting feature vectors for each video frame and applying a group sparsity algorithm to represent the feature vector for a particular video frame as a group sparse combination of the feature vectors for the other video frames. Weighting coefficients associated with the group sparse combination are analyzed to determine video frame clusters of temporally-contiguous, similar video frames. A set of key video frames are selected based on the determined video frame clusters.
摘要翻译： 一种用于从视频序列中识别一组关键视频帧的方法，包括提取每个视频帧的特征向量，并且应用组稀疏算法来表示特定视频帧的特征向量作为另一个的特征向量的组稀疏组合 视频帧。 分析与组稀疏组合相关联的加权系数，以确定时间上相邻的类似视频帧的视频帧聚类。 基于所确定的视频帧集群来选择一组关键视频帧。
-
公开(公告)号：US08612441B2
公开(公告)日：2013-12-17
申请号：US13021188
申请日：2011-02-04
申请人： Mark D. Wood , Alexander C. Loui
发明人： Mark D. Wood , Alexander C. Loui
CPC分类号： G06F17/30867 , G06F17/30244 , G06F17/30247 , G06F17/30268 , G06F17/30525 , G06F17/3074 , G06F17/30781 , G06F17/30997
摘要： A method of identifying one or more particular images from an image collection, includes indexing the image collection to provide image descriptors for each image in the image collection such that each image is described by one or more of the image descriptors; receiving a query from a user specifying at least one keyword for an image search; and using the keyword(s) to search a second collection of tagged images to identify co-occurrence keywords. The method further includes using the identified co-occurrence keywords to provide an expanded list of keywords; using the expanded list of keywords to search the image descriptors to identify a set of candidate images satisfying the keywords; grouping the set of candidate images according to at least one of the image descriptors, and selecting one or more representative images from each grouping; and displaying the representative images to the user.
-
公开(公告)号：US08386490B2
公开(公告)日：2013-02-26
申请号：US12912820
申请日：2010-10-27
申请人： Wei Jiang , Alexander C. Loui
发明人： Wei Jiang , Alexander C. Loui
IPC分类号： G06F7/00
CPC分类号： G06F17/30038
摘要： A method of classifying a set of semantic concepts on a second multimedia collection based upon adapting a set of semantic concept classifiers and updating concept affinity relations that were developed to classify the set of semantic concepts for a first multimedia collection. The method comprises providing the second multimedia collection from a different domain and a processor automatically classifying the semantic concepts from the second multimedia collection by adapting the semantic concept classifiers and updating the concept affinity relations to the second multimedia collection based upon the local smoothness over the concept affinity relations and the local smoothness over data affinity relations.
摘要翻译： 一种基于适应一组语义概念分类器并且更新用于对第一多媒体集合的语义概念集合进行分类而开发的概念亲和度关系来对第二多媒体集合上的一组语义概念进行分类的方法。 该方法包括从不同的域提供第二多媒体集合，并且处理器通过基于概念上的局部平滑度来适应语义概念分类器并且将概念兴趣关系更新到第二多媒体集合来自动地对来自第二多媒体集合的语义概念进行分类 亲和关系和数据关联关系的局部平滑度。
-
公开(公告)号：US08358856B2
公开(公告)日：2013-01-22
申请号：US12331927
申请日：2008-12-10
申请人： Alexander C. Loui , Jiang Wei
发明人： Alexander C. Loui , Jiang Wei
IPC分类号： G06K9/62
CPC分类号： G06K9/00664 , G06F17/30256 , G06F17/30802 , G06F17/30805 , G06F17/30808 , G06K9/00711
摘要： A system and method for semantic event detection in digital image content records is provided in which an event-level “Bag-of-Features” (BOF) representation is used to model events, and generic semantic events are detected in a concept space instead of an original low-level visual feature space based on the BOF representation.
摘要翻译： 提供了一种用于数字图像内容记录中的语义事件检测的系统和方法，其中使用事件级特征（BOF）表示来对事件进行建模，并且在概念空间中而不是原始信息中检测到通用语义事件 基于BOF表示的低级视觉特征空间。
-
67.发明授权公开(公告)号：US08028249B2
公开(公告)日：2011-09-27
申请号：US11196991
申请日：2005-09-08
申请人： Alexander C. Loui , Frank Marino
发明人： Alexander C. Loui , Frank Marino
CPC分类号： G06F17/30274 , G06F17/30064 , G06F17/30265
摘要： A display system and method for operating a display and a collection of digital multimedia objects are provided. A first selection set of predefined organizational metaphors is presented and a selection of a first organizational metaphor from the first selection set is received. A second selection set of predefined organizational metaphors other than the first selected organizational metaphor is presented and a selection of a second organizational metaphor from the second selection set is received. A result is presented on the display having one of at least two group icons, each group icon indicating a group of digital multimedia objects chosen from the collection according to rules associated with the selected organizational metaphors and the content of the digital multimedia objects or any metadata associated with the digital multimedia objects. Wherein the group of digital multimedia objects indicated by each group icon are chosen according to result presentation rules.
摘要翻译： 提供了一种用于操作显示器和数字多媒体对象的集合的显示系统和方法。 提出了预定义的组织隐喻的第一选择集，并且接收到来自第一选择集的第一组织隐喻的选择。 提出除了第一选定的组织隐喻之外的第二选择集预定义的组织隐喻，并且接收到来自第二选择集的第二组织隐喻的选择。 在具有至少两个组图标中的一个的显示器上呈现结果，每个组图标指示根据与所选择的组织隐喻相关联的规则以及数字多媒体对象的内容或任何元数据从集合中选择的一组数字多媒体对象 与数字多媒体对象相关联。 其中，根据结果呈现规则选择由每个组图标指示的数字多媒体对象组。
-
68.发明授权公开(公告)号：US07855810B2
公开(公告)日：2010-12-21
申请号：US11111365
申请日：2005-04-21
CPC分类号： G03D15/003 , G06F17/30265 , H04N1/00132 , H04N1/00135 , H04N1/00167 , H04N1/00193 , H04N1/00196 , H04N1/00198
摘要： A method, system and software program for automatically organizing digital images obtained from a plurality of hardcopy media. A plurality of hardcopy media are scanned so as to obtain both the image side and non-image side the of hardcopy media including capturing any watermark present on non-image side. The watermark on the non-mage side is used for automatically organizing digital images.
摘要翻译： 一种用于自动组织从多个硬拷贝媒体获得的数字图像的方法，系统和软件程序。 扫描多个硬拷贝介质以便获得硬拷贝介质的图像侧和非图像侧，包括捕获非图像侧上存在的任何水印。 非法师侧的水印用于自动组织数字图像。
-
公开(公告)号：US07813560B2
公开(公告)日：2010-10-12
申请号：US11679914
申请日：2007-02-28
申请人： Bryan D. Kraus , Alexander C. Loui
发明人： Bryan D. Kraus , Alexander C. Loui
CPC分类号： G06F17/30265 , G06F17/30247 , G06F17/3028 , G06K2209/27
摘要： A method for automatically classifying images into a final set of events including receiving a first plurality of images having date-time and a second plurality of images with incomplete date-time information; determining one or more time differences of the first plurality of images based on date-time clustering of the images and classify the first plurality of images into a first set of possible events; analyzing the second plurality of images using scene content and metadata cues and selecting images which correspond to different events in the first set of possible events and combining them into their corresponding possible events to thereby produce a second set of possible events; and using image scene content to verify the second set of possible events and to change the classification of images which correspond to different possible events to thereby provide the final set of events.
摘要翻译： 一种用于将图像自动分类为最终事件集的方法，包括接收具有日期时间的第一多个图像和具有不完整的日期时间信息的第二多个图像; 基于所述图像的日期时间聚类确定所述第一多个图像的一个或多个时间差，并将所述第一多个图像分类为第一组可能事件; 使用场景内容和元数据提示来分析第二多个图像，并且选择对应于第一组可能事件中的不同事件的图像，并将它们组合成其相应的可能事件，从而产生第二组可能事件; 并且使用图像场景内容来验证第二组可能的事件并且改变对应于不同可能事件的图像的分类，从而提供最终的事件集合。
-
公开(公告)号：US07643686B2
公开(公告)日：2010-01-05
申请号：US11197243
申请日：2005-08-04
申请人： Bryan D. Kraus , Alexander C. Loui
发明人： Bryan D. Kraus , Alexander C. Loui
IPC分类号： G06K9/62
CPC分类号： G06F17/30265
摘要： In a method for classifying a sequence of records into events based upon feature values, such as time and/or location, associated with each of the records, feature differences between consecutive records are determined. The feature differences are ranked. A sequence of three or more clusters of feature differences is computed. The clusters are arranged in decreasing order of relative likelihood of respective feature differences representing separations between events. The records can be inclusive of images.
摘要翻译： 在基于与每个记录相关联的特征值（例如时间和/或位置）将记录序列分类为事件的方法中，确定连续记录之间的特征差异。 功能差异排名。 计算三个或更多个特征差异簇的序列。 这些簇以表示事件之间的分离的各个特征差的相对似然性的递减顺序排列。 记录可以包含图像。
-
-
-
-
-
-
-
-
-
搜索结果
119 条记录 (耗时 0.047 秒)
