公开(公告)号：WO2016038522A1

公开(公告)日：2016-03-17

申请号：PCT/IB2015/056783

申请日：2015-09-05

Applicant: GOOGLE INC.

Inventor： SHETTY, Sanketh ,  IZO, Tomas ,  TSAI, Min-hsuan ,  VIJAYANARASIMHAN, Sudheendra ,  NATSEV, Apostol ,  ABU-EL-HAIJA, Sami ,  TODERICI, George ,  RICCO, Susanna ,  VARADARAJAN, Balakrishnan ,  MUSCETTOLA, Nicola ,  GU, Weihsin ,  YANG, Weilong ,  KHANDELWAL, Nitin ,  LE, Phuong

IPC: H04N21/8549 ,  H04N21/854

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片段。 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。 代表帧代表和总结视频段。

公开(公告)号：WO2017025860A1

公开(公告)日：2017-02-16

申请号：PCT/IB2016/054653

申请日：2016-08-02

Applicant: GOOGLE INC.

Inventor： VARADARAJAN, Balakrishnan ,  TODERICI, George ,  NATSEV, Apostol ,  KHANDELWAL, Nitin ,  VIJAYANARASIMHAN, Sudheendra ,  YANG, Weilong ,  SHETTY, Sanketh

IPC: G06F17/30

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.

Abstract translation: 系统和方法提供用实体注释视频和在视频帧内存在实体的相关概率。 计算机实现的方法从识别视频项目的特征的多个实体中识别实体。 计算机实现的方法基于多个特征的特征的值来选择与实体相关的一组特征，使用该特征集来确定实体的分类器，并且基于该特征确定该实体的聚合校准功能 的功能集。 计算机实现的方法从视频项目中选择视频帧，其中具有相关联特征的视频帧，并且使用分类器和聚合校准功能基于相关联的特征来确定实体的存在概率。