-
公开(公告)号：US09779304B2
公开(公告)日：2017-10-03
申请号：US14823946
申请日：2015-08-11
Applicant: Google Inc.
Inventor： Balakrishnan Varadarajan , George Dan Toderici , Apostol Natsev , Nitin Khandelwal , Sudheendra Vijayanarasimhan , Weilong Yang , Sanketh Shetty
CPC classification number: G06K9/00718 , G06F17/30784 , G06F17/3082 , G06K9/52 , G06K9/6201 , G06K9/6256 , G06K9/627 , H04N5/265
Abstract: A system and methodology provide for annotating videos with entities and associated probabilities of existence of the entities within video frames. A computer-implemented method identifies an entity from a plurality of entities identifying characteristics of video items. The computer-implemented method selects a set of features correlated with the entity based on a value of a feature of a plurality of features, determines a classifier for the entity using the set of features, and determines an aggregation calibration function for the entity based on the set of features. The computer-implemented method selects a video frame from a video item, where the video frame having associated features, and determines a probability of existence of the entity based on the associated features using the classifier and the aggregation calibration function.
-
公开(公告)号：US20170252924A1
公开(公告)日：2017-09-07
申请号：US15448013
申请日：2017-03-02
Applicant: Google Inc.
Inventor： Sudheendra Vijayanarasimhan , Eric Jang , Peter Pastor Sampedro , Sergey Levine
CPC classification number: B25J9/163 , B25J9/1612 , B25J9/1697 , G05B13/027 , G05B19/18 , G06N3/008 , G06N3/0454 , G06N3/08 , G06N3/084 , Y10S901/36
Abstract: Deep machine learning methods and apparatus related to manipulation of an object by an end effector of a robot. Some implementations relate to training a semantic grasping model to predict a measure that indicates whether motion data for an end effector of a robot will result in a successful grasp of an object; and to predict an additional measure that indicates whether the object has desired semantic feature(s). Some implementations are directed to utilization of the trained semantic grasping model to servo a grasping end effector of a robot to achieve a successful grasp of an object having desired semantic feature(s).
-
公开(公告)号：US09607224B2
公开(公告)日：2017-03-28
申请号：US14712071
申请日：2015-05-14
Applicant: Google Inc.
Inventor： Min-hsuan Tsai , Sudheendra Vijayanarasimhan , Tomas Izo , Sanketh Shetty , Balakrishnan Varadarajan
CPC classification number: G06K9/00765 , G06K9/6269 , G06K9/66 , H04N5/91
Abstract: A solution is provided for temporally segmenting a video based on analysis of entities identified in the video frames of the video. The video is decoded into multiple video frames and multiple video frames are selected for annotation. The annotation process identifies entities present in a sample video frame and each identified entity has a timestamp and confidence score indicating the likelihood that the entity is accurately identified. For each identified entity, a time series comprising of timestamps and corresponding confidence scores is generated and smoothed to reduce annotation noise. One or more segments containing an entity over the length of the video are obtained by detecting boundaries of the segments in the time series of the entity. From the individual temporal segmentation for each identified entity in the video, an overall temporal segmentation for the video is generated, where the overall temporal segmentation reflects the semantics of the video.
-
公开(公告)号：US20160180200A1
公开(公告)日：2016-06-23
申请号：US14933256
申请日：2015-11-05
Applicant: Google Inc.
Inventor： Sudheendra Vijayanarasimhan , Jay Yagnik
CPC classification number: G06K9/6267 , G06K9/66 , G06N3/04 , G06N3/082
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classification using a neural network. One of the methods for processing an input through each of multiple layers of a neural network to generate an output, wherein each of the multiple layers of the neural network includes a respective multiple nodes includes for a particular layer of the multiple layers: receiving, by a classification system, an activation vector as input for the particular layer, selecting one or more nodes in the particular layer using the activation vector and a hash table that maps numeric values to nodes in the particular layer, and processing the activation vector using the selected nodes to generate an output for the particular layer.
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，用于使用神经网络进行分类。 用于处理通过神经网络的多个层中的每一层的输入以产生输出的方法之一，其中所述神经网络的所述多个层中的每一个包括针对所述多个层的特定层的相应多个节点包括：通过 分类系统，作为特定层的输入的激活向量，使用激活向量选择特定层中的一个或多个节点，以及将数值映射到特定层中的节点的哈希表，以及使用所选择的处理激活向量 节点来生成特定层的输出。
-
公开(公告)号：US09914213B2
公开(公告)日：2018-03-13
申请号：US15448013
申请日：2017-03-02
Applicant: Google Inc.
Inventor： Sudheendra Vijayanarasimhan , Eric Jang , Peter Pastor Sampedro , Sergey Levine
CPC classification number: B25J9/163 , B25J9/1612 , B25J9/1697 , G05B13/027 , G05B19/18 , G06N3/008 , G06N3/0454 , G06N3/08 , G06N3/084 , Y10S901/36
Abstract: Deep machine learning methods and apparatus related to manipulation of an object by an end effector of a robot. Some implementations relate to training a semantic grasping model to predict a measure that indicates whether motion data for an end effector of a robot will result in a successful grasp of an object; and to predict an additional measure that indicates whether the object has desired semantic feature(s). Some implementations are directed to utilization of the trained semantic grasping model to servo a grasping end effector of a robot to achieve a successful grasp of an object having desired semantic feature(s).
-
Patent Agency Ranking
公开(公告)号：US20170323183A1
公开(公告)日：2017-11-09
申请号：US15656192
申请日：2017-07-21
Applicant: Google Inc.
Inventor： Sudheendra Vijayanarasimhan , Jay Yagnik
CPC classification number: G06K9/6267 , G06K9/66 , G06N3/04 , G06N3/082
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classification using a neural network. One of the methods for processing an input through each of multiple layers of a neural network to generate an output, wherein each of the multiple layers of the neural network includes a respective multiple nodes includes for a particular layer of the multiple layers: receiving, by a classification system, an activation vector as input for the particular layer, selecting one or more nodes in the particular layer using the activation vector and a hash table that maps numeric values to nodes in the particular layer, and processing the activation vector using the selected nodes to generate an output for the particular layer.
-
公开(公告)号：US20160335499A1
公开(公告)日：2016-11-17
申请号：US14712071
申请日：2015-05-14
Applicant: Google Inc.
Inventor： Min-hsuan Tsai , Sudheendra Vijayanarasimhan , Tomas Izo , Sanketh Shetty , Balakrishnan Varadarajan
CPC classification number: G06K9/00765 , G06K9/6269 , G06K9/66 , H04N5/91
Abstract: A solution is provided for temporally segmenting a video based on analysis of entities identified in the video frames of the video. The video is decoded into multiple video frames and multiple video frames are selected for annotation. The annotation process identifies entities present in a sample video frame and each identified entity has a timestamp and confidence score indicating the likelihood that the entity is accurately identified. For each identified entity, a time series comprising of timestamps and corresponding confidence scores is generated and smoothed to reduce annotation noise. One or more segments containing an entity over the length of the video are obtained by detecting boundaries of the segments in the time series of the entity. From the individual temporal segmentation for each identified entity in the video, an overall temporal segmentation for the video is generated, where the overall temporal segmentation reflects the semantics of the video.
Abstract translation: 提供了一种解决方案，用于基于在视频的视频帧中识别的实体的分析来对视频进行时间分割。 将视频解码为多个视频帧，并选择多个视频帧进行注释。 注释过程识别存在于样本视频帧中的实体，并且每个识别的实体具有指示实体准确识别的可能性的时间戳和置信度分数。 对于每个识别的实体，产生并平滑包括时间戳和对应的置信度分数的时间序列以减少注释噪声。 通过检测实体的时间序列中的段的边界来获得包含视频长度上的实体的一个或多个段。 根据视频中每个被识别实体的个体时间分割，生成视频的总体时间分割，其中整体时间分段反映视频的语义。
-
公开(公告)号：US20160070962A1
公开(公告)日：2016-03-10
申请号：US14848216
申请日：2015-09-08
Applicant: Google Inc.
Inventor： Sanketh Shetty , Tomas Izo , Min-Hsuan Tsai , Sudheendra Vijayanarasimhan , Apostol Natsev , Sami Abu-El-Haija , George Dan Toderici , Susanna Ricco , Balakrishnan Varadarajan , Nicola Muscettola , WeiHsin Gu , Weilong Yang , Nitin Khandelwal , Phuong Le
CPC classification number: G06K9/00718 , G06F17/30787 , G06K9/00744 , G06K9/00751 , G06K9/00765 , G06K2209/27
Abstract: A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.
Abstract translation: 提供了一种用于选择视频的代表性帧的计算机实现的方法。 该方法包括接收视频并识别视频的每个帧的一组特征。 特征包括基于帧的特征和语义特征。 识别语义概念的可能性的语义特征作为视频帧中的内容呈现。 随后生成视频的一组视频段。 每个视频段包括来自视频的帧的按时间顺序的子集，并且每个帧与语义特征中的至少一个相关联。 该方法至少基于语义特征为每个视频段的帧子集的每帧生成分数，并且基于视频段中的帧的分数为每个视频段选择代表性的帧。 代表性的框架代表和总结视频段。
-
公开(公告)号：US09627004B1
公开(公告)日：2017-04-18
申请号：US14883461
申请日：2015-10-14
Applicant: Google Inc.
Inventor： Balakrishnan Varadarajan , Sanketh Shetty , Apostol Natsev , Nitin Khandelwal , Weilong Yang , Sudheendra Vijayanarasimhan , WeiHsin Gu , Nicola Muscettola
IPC: H04N9/80 , H04N5/77 , G11B27/10 , G06K9/00 , G06K9/46 , G06F17/30 , G06F17/24 , H04N21/2743 , H04N21/234 , H04N21/235
CPC classification number: G11B27/10 , G06F17/241 , G06F17/30799 , G06F17/3082 , G06K9/00744 , G06K9/6259 , G06K9/6277 , G06K2209/27 , H04N21/23418 , H04N21/251 , H04N21/278 , H04N21/4828 , H04N21/84 , H04N21/8456
Abstract: A system and methodology provide for annotating videos with entities and associated probabilities of existence of the entities within video frames. A computer-implemented method selects an entity from a plurality of entities identifying characteristics of a video item, where the video item has associated metadata. The computer-implemented method receives probabilities of existence of the entity in video frames of the video item, and selects a video frame determined to comprise the entity responsive to determining the video frame having a probability of existence of the entity greater than zero. The computer-implemented method determines a scaling factor for the probability of existence of the entity using the metadata of the video item, and determines an adjusted probability of existence of the entity by using the scaling factor to adjust the probability of existence of the entity. The computer-implemented method labels the video frame with the adjusted probability of existence.
-
公开(公告)号：US20160306804A1
公开(公告)日：2016-10-20
申请号：US15195105
申请日：2016-06-28
Applicant: Google Inc.
Inventor： Balakrishnan Varadarajan , Sudheendra Vijayanarasimhan , Sanketh Shetty , Nisarg Dilipkumar Kothari , Nicholas Delmonico Rizzolo
CPC classification number: G06F17/30551 , G06F17/30029 , G06F17/30554 , G06F17/30867 , G10L25/54 , H04L51/32 , H04L67/306
Abstract: Methods, systems, and media for presenting comments based on correlation with content are provided. In some implementations, a method for presenting ranked comments is provided, the method comprising: receiving, using a hardware processor, content data related to an item of content; receiving, using the hardware processor, comment data related to a comment associated with the item of content; determining, using the hardware processor, a degree of correlation between at least a portion of the comment data and one or more portions of the content data; determining, using the hardware processor, a priority for the comment based on the degree of correlation; and presenting, using the hardware processor, the comment based on the priority.
Abstract translation: 提供了基于与内容相关性来呈现评论的方法，系统和媒体。 在一些实现中，提供了一种用于呈现排名评论的方法，所述方法包括：使用硬件处理器接收与内容项相关的内容数据; 使用所述硬件处理器接收与所述内容项相关联的评论相关的评论数据; 使用所述硬件处理器确定所述评论数据的至少一部分与所述内容数据的一个或多个部分之间的相关程度; 基于所述相关程度来确定所述硬件处理器的所述评论的优先级; 以及基于所述优先级，使用所述硬件处理器来呈现所述注释。
-
-
-
-
-
-
-
-
-
Search Results
14
records
(took 0.017 seconds)
