公开(公告)号：WO2012044668A1

公开(公告)日：2012-04-05

申请号：PCT/US2011/053641

申请日：2011-09-28

Applicant: GOOGLE INC. ,  BENGIO, Samy ,  WESTON, Jason E.

Inventor： BENGIO, Samy ,  WESTON, Jason E.

IPC: G06K9/62

CPC classification number: G06K9/6282

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for label embedding trees for large multi-class tasks. In one aspect, a method includes mapping each image in a plurality of images and each label in a plurality of labels into a multi-dimensional label embedding space. A tree of label predictors is trained with the plurality of mapped images such that an error function is minimized in which the error function counts an error for each mapped image if any of the label predictors at any depth of the tree incorrectly predicts that the mapped image belongs to the label predictor's respective label set.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于标签嵌入用于大型多类任务的树。 一方面，一种方法包括将多个图像中的每个图像和多个标签中的每个标签映射成多维标签嵌入空间。 使用多个映射图像训练标签预测器的树，使得误差函数被最小化，其中如果在树的任何深度处的任何标签预测器错误地预测了映射图像，则误差函数计算每个映射图像的误差 属于标签预测器的相应标签集。

公开(公告)号：WO2012154470A1

公开(公告)日：2012-11-15

申请号：PCT/US2012/036140

申请日：2012-05-02

Applicant: GOOGLE INC. ,  HEITZ, Geremy A., III ,  BERENZWEIG, Adam ,  WESTON, Jason E. ,  WEISS, Ron J. ,  GOLDMAN, Sally A. ,  WALTERS, Thomas ,  BENGIO, Samy ,  ECK, Douglas ,  PONTE, Jay M. ,  RIFKIN, Ryan M.

Inventor： HEITZ, Geremy A., III ,  BERENZWEIG, Adam ,  WESTON, Jason E. ,  WEISS, Ron J. ,  GOLDMAN, Sally A. ,  WALTERS, Thomas ,  BENGIO, Samy ,  ECK, Douglas ,  PONTE, Jay M. ,  RIFKIN, Ryan M.

IPC: G06F17/30

CPC classification number: G06F17/30772 ,  G06F17/30743

Abstract: Generating a playlist may include designating a seed track in an audio library; identifying audio tracks in the audio library having constructs that are within a range of a corresponding construct of the seed track, where the constructs for the audio tracks are derived from frequency representations of the audio tracks, and the corresponding construct for the seed track is derived from a frequency representation of the seed track; and generating the playlist using at least some of the audio tracks that were identified.

Abstract translation: 生成播放列表可以包括在音频库中指定种子轨道; 识别具有在种子轨道的对应构造的范围内的构造的音频库中的音频轨道，其中音频轨道的构造从音频轨道的频率表示导出，并且导出种子轨道的相应构造 从种子轨迹的频率表示; 以及使用所识别的至少一些音轨生成播放列表。

公开(公告)号：WO2012058577A1

公开(公告)日：2012-05-03

申请号：PCT/US2011/058362

申请日：2011-10-28

Applicant: GOOGLE INC. ,  MAKADIA, Ameesh ,  WESTON, Jason E.

Inventor： MAKADIA, Ameesh ,  WESTON, Jason E.

IPC: G06F17/30

CPC classification number: G06F17/30029 ,  G06F17/30026 ,  G06F17/30047 ,  G06F17/3005

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing joint image-audio queries. In one aspect, a method includes receiving, from a client device, a joint image-audio query including query image data and query audio data. Query image feature data is determined from the query image data. Query audio feature data is determined from the audio data. The query image feature data and the query audio feature data are provided to a joint image-audio relevance model trained to generate relevance scores for a plurality of resources, each resource including resource image data defining a resource image for the resource and text data defining resource text for the resource. Each relevance score is a measure of the relevance of corresponding resource to the joint image-audio query. Data defining search results indicating the order of the resources is provided to the client device.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于处理联合图像 - 音频查询。 一方面，一种方法包括从客户端设备接收包括查询图像数据和查询音频数据的联合图像音频查询。 从查询图像数据确定查询图像特征数据。 从音频数据确定查询音频特征数据。 将查询图像特征数据和查询音频特征数据提供给被训练为生成多个资源的相关性分数的联合图像 - 音频相关性模型，每个资源包括定义资源的资源图像的资源图像数据和定义资源的文本数据 资源的文本。 每个相关性分数是对应资源与联合图像 - 音频查询的相关性的度量。 将指示资源顺序的搜索结果的数据提供给客户端设备。

公开(公告)号：EP2633439A1

公开(公告)日：2013-09-04

申请号：EP11784547.9

申请日：2011-10-28

Applicant: Google Inc.

Inventor： MAKADIA, Ameesh ,  WESTON, Jason E.

IPC: G06F17/30

CPC classification number: G06F17/30029 ,  G06F17/30026 ,  G06F17/30047 ,  G06F17/3005

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing joint image-audio queries. In one aspect, a method includes receiving, from a client device, a joint image-audio query including query image data and query audio data. Query image feature data is determined from the query image data. Query audio feature data is determined from the audio data. The query image feature data and the query audio feature data are provided to a joint image-audio relevance model trained to generate relevance scores for a plurality of resources, each resource including resource image data defining a resource image for the resource and text data defining resource text for the resource. Each relevance score is a measure of the relevance of corresponding resource to the joint image-audio query. Data defining search results indicating the order of the resources is provided to the client device.

公开(公告)号：EP2707815A1

公开(公告)日：2014-03-19

申请号：EP12722228.9

申请日：2012-05-02

Applicant: Google Inc.

Inventor： HEITZ, Geremy A., III ,  BERENZWEIG, Adam ,  WESTON, Jason E. ,  WEISS, Ron J. ,  GOLDMAN, Sally A. ,  WALTERS, Thomas ,  BENGIO, Samy ,  ECK, Douglas ,  PONTE, Jay M. ,  RIFKIN, Ryan M.

IPC: G06F17/30

CPC classification number: G06F17/30772 ,  G06F17/30743

Abstract: Generating a playlist may include designating a seed track in an audio library; identifying audio tracks in the audio library having constructs that are within a range of a corresponding construct of the seed track, where the constructs for the audio tracks are derived from frequency representations of the audio tracks, and the corresponding construct for the seed track is derived from a frequency representation of the seed track; and generating the playlist using at least some of the audio tracks that were identified.