公开(公告)号：US20090079871A1

公开(公告)日：2009-03-26

申请号：US11858628

申请日：2007-09-20

申请人： Xian-Sheng Hua ,  Tao Mei ,  Linjun Yang ,  Shipeng Li

发明人： Xian-Sheng Hua ,  Tao Mei ,  Linjun Yang ,  Shipeng Li

IPC分类号： H04N9/74

CPC分类号： G11B27/28 ,  G11B27/036 ,  H04N21/2365 ,  H04N21/4347 ,  H04N21/812 ,  H04N21/8456 ,  H04N21/854

摘要： Systems and methods for determining insertion points in a first video stream are described. The insertions points being configured for inserting at least one second video into the first video. In accordance with one embodiment, a method for determining the insertion points includes parsing the first video into a plurality of shots. The plurality of shots includes one or more shot boundaries. The method then determines one or more insertion points by balancing a discontinuity metric and an attractiveness metric of each shot boundary.

摘要翻译： 描述用于确定第一视频流中的插入点的系统和方法。 插入点被配置用于将至少一个第二视频插入到第一视频中。 根据一个实施例，用于确定插入点的方法包括将第一视频解析成多个镜头。 多个镜头包括一个或多个镜头边界。 然后，该方法通过平衡不连续度量和每个镜头边界的吸引度度量来确定一个或多个插入点。

公开(公告)号：US20090006368A1

公开(公告)日：2009-01-01

申请号：US11771219

申请日：2007-06-29

申请人： Tao Mei ,  Xian-Sheng Hua ,  Bo Yang ,  Linjun Yang ,  Shipeng Li

发明人： Tao Mei ,  Xian-Sheng Hua ,  Bo Yang ,  Linjun Yang ,  Shipeng Li

IPC分类号： G06F17/30 ,  G06F3/00

CPC分类号： H04N7/17318 ,  G06F16/735 ,  G06F16/78 ,  G06F16/7844 ,  G06F16/7847 ,  H04N21/466 ,  H04N21/4667 ,  H04N21/472

摘要： Automatic video recommendation is described. The recommendation does not require an existing user profile. The source videos are directly compared to a user selected video to determine relevance, which is then used as a basis for video recommendation. The comparison is performed with respect to a weighted feature set including at least one content-based feature, such as a visual feature, an aural feature and a content-derived textural feature. Multimodal implementation including multimodal features (e.g., visual, aural and textural) extracted from the videos is used for more reliable relevance ranking. One embodiment uses an indirect textural feature generated by automatic text categorization based on a set of predefined category hierarchy. Another embodiment uses self-learning based on user click-through history to improve relevance ranking.

摘要翻译： 描述了自动视频推荐。 该建议不需要现有的用户配置文件。 源视频直接与用户选择的视频进行比较，以确定相关性，然后将其用作视频推荐的基础。 相对于包括至少一个基于内容的特征（例如视觉特征，听觉特征和内容导出的纹理特征）的加权特征集执行比较。 使用从视频提取的包括多模态特征（例如，视觉，听觉和纹理）的多模实现用于更可靠的相关性排名。 一个实施例使用基于一组预定义类别层次的自动文本分类生成的间接纹理特征。 另一个实施例使用基于用户点击历史的自学习来提高相关性排名。

公开(公告)号：US20090319883A1

公开(公告)日：2009-12-24

申请号：US12141921

申请日：2008-06-19

申请人： Tao Mei ,  Xian-Sheng Hua ,  Wei-Ying Ma ,  Emily Kay Moxley

发明人： Tao Mei ,  Xian-Sheng Hua ,  Wei-Ying Ma ,  Emily Kay Moxley

IPC分类号： G06F17/00 ,  G06F17/30

CPC分类号： G06F16/70

摘要： Described is a technology in which a new video is automatically annotated based on terms mined from the text associated with similar videos. In a search phase, searching by one or more various search modalities (e.g., text, concept and/or video) finds a set of videos that are similar to a new video. Text associated with the new video and with the set of videos is obtained, such as by automatic speech recognition that generates transcripts. A mining mechanism combines the associated text of the similar videos with that of the new video to find the terms that annotate the new video. For example, the mining mechanism creates a new term frequency vector by combining term frequency vectors for the set of similar videos with a term frequency vector for the new video, and provides the mined terms by fitting a zipf curve to the new term frequency vector.

摘要翻译： 描述了一种技术，其中基于从与相似视频相关联的文本挖掘的术语自动地注释新的视频。 在搜索阶段，通过一个或多个各种搜索模态（例如，文本，概念和/或视频）的搜索找到类似于新视频的一组视频。 获得与新视频和视频集相关联的文本，例如通过产生抄本的自动语音识别。 挖掘机制将相似视频的相关文本与新视频的相关文本相结合，以找到注释新视频的术语。 例如，采矿机制通过将类似视频集合的术语频率矢量与新视频的术语频率矢量组合来创建新的术语频率矢量，并通过将zipf曲线拟合到新的术语频率矢量来提供开采术语。

公开(公告)号：US20090290802A1

公开(公告)日：2009-11-26

申请号：US12125057

申请日：2008-05-22

申请人： Xian-Sheng Hua ,  Guo-Jun Qi ,  Yong Rui ,  Tao Mei ,  Hong-Jiang Zhang

发明人： Xian-Sheng Hua ,  Guo-Jun Qi ,  Yong Rui ,  Tao Mei ,  Hong-Jiang Zhang

IPC分类号： G06K9/62

CPC分类号： G06K9/34

摘要： The concurrent multiple instance learning technique described encodes the inter-dependency between instances (e.g. regions in an image) in order to predict a label for a future instance, and, if desired the label for an image determined from the label of these instances. The technique, in one embodiment, uses a concurrent tensor to model the semantic linkage between instances in a set of images. Based on the concurrent tensor, rank-1 supersymmetric non-negative tensor factorization (SNTF) can be applied to estimate the probability of each instance being relevant to a target category. In one embodiment, the technique formulates the label prediction processes in a regularization framework, which avoids overfitting, and significantly improves a learning machine's generalization capability, similar to that in SVMs. The technique, in one embodiment, uses Reproducing Kernel Hilbert Space (RKHS) to extend predicted labels to the whole feature space based on the generalized representer theorem.

摘要翻译： 所描述的并发多实例学习技术编码实例（例如，图像中的区域）之间的相互依赖性，以便预测将来实例的标签，以及如果需要，从这些实例的标签确定的图像的标签。 在一个实施例中，该技术使用并发张量来对一组图像中的实例之间的语义联系进行建模。 基于并发张量，可以应用秩1超对称非负张量因子分解（SNTF）来估计每个实例与目标类别相关的概率。 在一个实施例中，该技术在正则化框架中制定标签预测过程，其避免过拟合，并且显着地提高学习机器的泛化能力，类似于SVM中的标准预测过程。 在一个实施例中，该技术使用再生核希尔伯特空间（RKHS）来基于广义代表定理将预测标签扩展到整个特征空间。

公开(公告)号：US20100205202A1

公开(公告)日：2010-08-12

申请号：US12369421

申请日：2009-02-11

申请人： Linjun Yang ,  Meng Wang ,  Zhengjun Zha ,  Tao Mei ,  Xian-Sheng Hua

发明人： Linjun Yang ,  Meng Wang ,  Zhengjun Zha ,  Tao Mei ,  Xian-Sheng Hua

IPC分类号： G06F17/30

CPC分类号： G06F17/3064 ,  G06F17/30277 ,  G06F17/30864

摘要： Techniques described herein enable better understanding of the intent of a user that submits a particular search query. These techniques receive a search request for images associated with a particular query. In response, the techniques determine images that are associated with the query, as well as other keywords that are associated with these images. The techniques then cluster, for each set of images associated with one of these keywords, the set of images into multiple groups. The techniques then rank the images and determine a representative image of each cluster. Finally, the tools suggest, to the user that submitted the query, to refine the search based on user selection of a keyword and a representative image. Thus, the techniques better understand the user's intent by allowing the user to refine the search based on another keyword and based on an image on which the user wishes to focus the search.

摘要翻译： 本文描述的技术能够更好地理解提交特定搜索查询的用户的意图。 这些技术接收与特定查询相关联的图像的搜索请求。 作为响应，这些技术确定与查询相关联的图像以及与这些图像相关联的其他关键词。 然后，对于与这些关键词之一相关联的每组图像，该技术将该组图像聚类成多个组。 然后，技术对图像进行排序并确定每个聚类的代表图像。 最后，工具向提交查询的用户建议，根据用户对关键字和代表图像的选择来优化搜索。 因此，这些技术通过允许用户基于另一个关键字来改进搜索并且基于用户希望集中搜索的图像来更好地理解用户的意图。

公开(公告)号：US08452794B2

公开(公告)日：2013-05-28

申请号：US12369421

申请日：2009-02-11

申请人： Linjun Yang ,  Meng Wang ,  Zhengjun Zha ,  Tao Mei ,  Xian-Sheng Hua

发明人： Linjun Yang ,  Meng Wang ,  Zhengjun Zha ,  Tao Mei ,  Xian-Sheng Hua

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/3064 ,  G06F17/30277 ,  G06F17/30864

摘要： Techniques described herein enable better understanding of the intent of a user that submits a particular search query. These techniques receive a search request for images associated with a particular query. In response, the techniques determine images that are associated with the query, as well as other keywords that are associated with these images. The techniques then cluster, for each set of images associated with one of these keywords, the set of images into multiple groups. The techniques then rank the images and determine a representative image of each cluster. Finally, the tools suggest, to the user that submitted the query, to refine the search based on user selection of a keyword and a representative image. Thus, the techniques better understand the user's intent by allowing the user to refine the search based on another keyword and based on an image on which the user wishes to focus the search.

摘要翻译： 本文描述的技术能够更好地理解提交特定搜索查询的用户的意图。 这些技术接收与特定查询相关联的图像的搜索请求。 作为响应，这些技术确定与查询相关联的图像以及与这些图像相关联的其他关键词。 然后，对于与这些关键词之一相关联的每组图像，该技术将该组图像聚类成多个组。 然后，技术对图像进行排序并确定每个聚类的代表图像。 最后，工具向提交查询的用户建议，根据用户对关键字和代表图像的选择来优化搜索。 因此，这些技术通过允许用户基于另一个关键字来改进搜索并且基于用户希望集中搜索的图像来更好地理解用户的意图。