-
公开(公告)号：US20190244052A1
公开(公告)日：2019-08-08
申请号：US16386239
申请日：2019-04-16
CPC分类号： G06K9/4671 , G06F16/71 , G06F16/739 , G06F16/9566 , G06K9/00228 , G06K9/00281 , G06K9/00295 , G06K9/00315 , G06K9/00718 , G06K9/00744 , G06K9/00751 , G06K9/00765 , G06K9/00771 , G06K9/46 , G06K2009/00738 , G06T7/73
摘要： A system and method for analyzing behavior in a video is described. The method includes extracting a plurality of salient fragments of a video; building a database of the plurality of salient fragments; generating a focalized visualization, based on a time anchor, from the one or more salient fragments of the video; tagging a human subject in the focalized visualization with a unique identifier; analyzing the focalized visualization, based on the unique identifier, to generate a behavior score; and providing the behavior score via the user device.
-
2.发明申请公开(公告)号：US20190244031A1
公开(公告)日：2019-08-08
申请号：US16388017
申请日：2019-04-18
申请人： GoPro, Inc.
CPC分类号： G06K9/00751 , G06F16/739 , G06F16/743 , G06K9/00765 , G06K2009/00738 , G06T7/70 , G06T2207/30244 , G11B27/10 , H04N5/2252 , H04N5/247
摘要： First video information defining first video content may be accessed. The first video content may have been captured by a first image sensor from a first conveyance position. Second video information defining second video content may be accessed. The second video content may have been captured by a second image sensor from a second conveyance position. A first highlight criterion may be selected for the first video content based on the first conveyance position. A second highlight criterion may be selected for the second video content based on the second conveyance position. A first set of highlight moments within the first video content may be identified based on the first criterion. A second set of highlight moments within the second video content may be identified based on the second criterion. The identification of the first set of highlight moments and the second set of highlight moments may be stored.
-
公开(公告)号：US20190197316A1
公开(公告)日：2019-06-27
申请号：US15855275
申请日：2017-12-27
IPC分类号： G06K9/00 , G06F17/30 , G11B27/34 , G11B27/031 , H04N21/472 , H04N21/435 , H04N21/8549 , H04N21/433
CPC分类号： G06K9/00751 , G06F16/7867 , G11B27/031 , G11B27/34 , H04N21/4334 , H04N21/435 , H04N21/47205 , H04N21/8549
摘要： A video-related method, system and device are disclosed herein. The method, system and device relate to videos and information of participants in events. The method, system and device, in an embodiment, involve receiving a plurality of clip inputs during a recording session that results in a video, receiving at least one descriptor of a participant, and enabling an interface to display the video in response to a search that is based, at least in part, on the descriptor.
-
公开(公告)号：US20190197315A1
公开(公告)日：2019-06-27
申请号：US15850697
申请日：2017-12-21
申请人： Facebook, Inc.
发明人： Ying Zhang , Shengbo Guo
CPC分类号： G06K9/00751 , G06F3/048 , G06F17/241 , G06K9/00456 , G06Q50/01
摘要： Exemplary embodiments relate to the automatic generation of captions for visual media in the form of a consistent story or narrative. According to some embodiments, story generation may be applied to a live video. As a user records live video, a system may analyze metadata, the frames of the video, and/or the audio to extract context information. The system may integrate this information with information from the user's social network and a personalized language model built using public-facing language from the user. The system may generate multiple captions for the video, where subsequent captions are based at least partially on previous captions. Captions may be generated in a story format so as to be consistent with each other. Information that is inconsistent with the story may be excluded from the captions unless contextual factors indicate that the story should change subject.
-
公开(公告)号：US20190191226A1
公开(公告)日：2019-06-20
申请号：US15846351
申请日：2017-12-19
申请人： Yahoo Holdings, Inc.
IPC分类号： H04N21/8549 , G11B27/031 , G06K9/00 , H04N21/2187 , H04N21/234
CPC分类号： H04N21/8549 , G06K9/00751 , G11B27/031 , H04N21/2187 , H04N21/23418 , H04N21/23424
摘要： One or more computing devices, systems, and/or methods for generating and/or presenting time-lapse videos and/or live-stream videos are provided. For example, a plurality of video frames may be extracted from a video. A first set of video frames and a second set of video frames may be identified from the plurality of video frames. The first set of video frames may be combined to generate a first time-lapse video frame and the second set of video frames may be combined to generate a second time-lapse video frame. A time-lapse video may be generated based upon the first time-lapse video frame and the second time-lapse video frame. In another example, a time-lapse video may be generated based upon a recorded video associated with a live-stream video. The time-lapse video may be presented. Responsive to a completion of the presenting the time-lapse video, the live-stream video may be presented.
-
公开(公告)号：US10327046B1
公开(公告)日：2019-06-18
申请号：US15846351
申请日：2017-12-19
申请人： Oath Inc.
IPC分类号： H04N5/93 , H04N21/8549 , G11B27/031 , H04N21/234 , H04N21/2187 , G06K9/00
CPC分类号： H04N21/8549 , G06K9/00751 , G11B27/031 , H04N21/2187 , H04N21/23418 , H04N21/23424
摘要： One or more computing devices, systems, and/or methods for generating and/or presenting time-lapse videos and/or live-stream videos are provided. For example, a plurality of video frames may be extracted from a video. A first set of video frames and a second set of video frames may be identified from the plurality of video frames. The first set of video frames may be combined to generate a first time-lapse video frame and the second set of video frames may be combined to generate a second time-lapse video frame. A time-lapse video may be generated based upon the first time-lapse video frame and the second time-lapse video frame. In another example, a time-lapse video may be generated based upon a recorded video associated with a live-stream video. The time-lapse video may be presented. Responsive to a completion of the presenting the time-lapse video, the live-stream video may be presented.
-
7.发明申请公开(公告)号：US20180357489A1
公开(公告)日：2018-12-13
申请号：US16003008
申请日：2018-06-07
发明人： Debasish MITRA , Hitesh CHAWLA
CPC分类号： G06K9/00751 , G06K9/00744 , G06K9/6272 , G06K9/6276 , G06N5/003 , G06N7/00 , H04L65/4076 , H04N21/23418 , H04N21/812
摘要： The present disclosure provides a computer-implemented method and system for adaptively reducing detection time in real time supervised detection of televised ads in media content of a channel. The method includes reception of the media content and selection of a set of frames per second from the media content. The method includes extraction of keypoints from each selected frame and derivation of binary descriptors from extracted keypoints. The method includes assignment of weight value to each binary descriptor and creation of a special pyramid of the binary descriptors. The method includes obtaining a first vocabulary of binary descriptors for each selected frame and accessing a second vocabulary of binary descriptors. The method includes comparison of each binary descriptor in the first vocabulary with binary descriptors in second vocabulary. The method includes progressively scoring each selected frame of the media content and detecting a first ad in the media content.
-
8.发明授权公开(公告)号：US10061986B2
公开(公告)日：2018-08-28
申请号：US15210708
申请日：2016-07-14
发明人： Leonid Sigal , Shugao Ma
CPC分类号： G06K9/00751 , G06K9/00335 , G06K9/00671 , G06K9/00718 , G06K9/00744 , G06K9/4628 , G06K2009/00738 , G06K2209/21 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06T7/62 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G11B27/102 , H04L65/4069
摘要： There is provided a system comprising a memory and a processor configured to receive a media content depicting an activity, extract a first plurality of features from a first segment of the media content, make a first prediction that the media content depicts a first activity based on the first plurality of features, wherein the first prediction has a first confidence level, extract a second plurality of features from a second segment of the media content, the second segment temporally following the first segment in the media content, make a second prediction that the media content depicts the first activity based on the second plurality of features, wherein the second prediction has a second confidence level, determine that the media content depicts the first activity based on the first prediction and the second prediction, wherein the second confidence level is at least as high as the first confidence level.
-
公开(公告)号：US10013487B2
公开(公告)日：2018-07-03
申请号：US15007872
申请日：2016-01-27
申请人： VISCOVERY PTE. LTD.
发明人： Kuo-Don Hsi , Chun-Chieh Huang , Yen-Cheng Chen
CPC分类号： G06F16/7837 , G06F16/735 , G06F16/7834 , G06F16/7867 , G06K9/00751 , G06K9/6265
摘要： A system and a method for multi-modal fusion based fault tolerant video content recognition is disclosed. The method conducts multi-modal recognition on an input video to extract multiple components and their respective appearance time in the video. Next, the multiple components are categorized and recognized respectively via different algorithms. Next, when the recognition confidence of any component is insufficient, a cross-validation with other components is performed to increase the recognition confidence and improve the fault tolerance of the components. Furthermore, when the recognition confidence of an individual component is insufficient, the recognition continues and tracks the component, spatially and temporally when it applies, until frames of high recognition confidence in the continuous time period is reached. Finally, multi-modal fusion is performed to summarize and resolve any recognition discrepancies between the multiple components, and to generate indices for every time frame for the ease of future text-based queries.
-
公开(公告)号：US20180137360A1
公开(公告)日：2018-05-17
申请号：US15629663
申请日：2017-06-21
CPC分类号： G06K9/00718 , G06F16/3331 , G06K9/00751 , G06K9/627 , G06K2009/00738 , G06N3/0454 , G06N3/08
摘要： A method, a computer-readable medium, and an apparatus for zero-exemplar event detection are provided. The apparatus may receive a plurality of text blocks, each of which may describe one of a plurality of pre-defined events. The apparatus may receive a plurality of training videos, each of which may be associated with one of the plurality of text blocks. The apparatus may propagate each text block through a neural network to obtain a textual representation in a joint space of textual and video representations. The apparatus may propagate each training video through the neural network to obtain a visual representation in the joint space. The apparatus may adjust parameters of the neural network to reduce, for each pair of associated text block and training video, the distance in the joint space between the textual representation of the associated text block and the visual representation of the associated training video.
-
-
-
-
-
-
-
-
-
搜索结果
577 条记录 (耗时 0.022 秒)
