-
公开(公告)号：US10699128B2
公开(公告)日：2020-06-30
申请号：US15271250
申请日：2016-09-21
Applicant: Cisco Technology, Inc.
Inventor： Amitay Stern , Yoav Glazner
IPC: G06K9/00
Abstract: Methods and systems for comparing content are provided. A recognizable object which appears in frames of a reference video file is recognized. A meta-feature of the recognizable object is determined. A first vector indicative of the meta-feature of the identified recognizable object in the reference video file is created. The meta-feature of the identified recognizable object which appears in a suspect video file is determined. A second vector indicative of the meta-feature of the identified recognizable object in the suspect video file is created. A correlation between the first vector and the second vector is determined. The correlation between the first vector and the second vector is indicative of a degree of confidence that the suspect video file is a copy of the reference video file.
-
公开(公告)号：US10237614B2
公开(公告)日：2019-03-19
申请号：US15490916
申请日：2017-04-19
Applicant: Cisco Technology, Inc.
Inventor： Yoav Glazner , Amitay Stern
Abstract: In one embodiment, a method comprising receiving data of a plurality of viewports generated from a content item during rendering of the content item, receiving data about at least one feature included in the content item, comparing the data of the plurality of viewports with the data about the at least one feature included in the content item, and computing a score representing to what extent the at least one feature is included in the plurality of viewports. Related apparatus and methods are also described.
-
公开(公告)号：US20180082121A1
公开(公告)日：2018-03-22
申请号：US15271250
申请日：2016-09-21
Applicant: Cisco Technology, Inc.
Inventor： Amitay Stern , Yoav GLAZNER
Abstract: In one embodiment, a system, apparatus and method are described, the system having at least one storage device for storing a reference video file including a plurality of frames in which an identifiable recognizable object appears, a suspect video file including a plurality of frames in which the identifiable recognizable object appears, a computer including a processor to determine, on a per frame basis, at least one meta-feature of the identifiable recognizable object which appears in each frame of the reference video file, create a first vector for the reference video file, the first vector being a vector of the determined at least one meta-feature of the identifiable recognizable object which appears in each frame of the reference video file, determine, on a per frame basis, the at least one meta-feature of the identifiable recognizable object which appears in each frame of the suspect video file, create a second vector for the suspect video file, the second vector being a vector of the determined at least one meta-feature of the identifiable recognizable object which appears in each frame of the suspect video file, and calculate a correlation between the first vector and the second vector and thereupon apply a statistical method to determine a measure of the correlation between the first vector and the second vector, a result of the statistical method being indicative of a degree of confidence, and an interface for the processor to output a result on the basis of the degree of confidence, the result indicative of a degree of certainty that the suspect video file is a copy of the reference video file. Related systems, apparatus and methods are also described.
-
Patent Agency Ranking
公开(公告)号：US20180077170A1
公开(公告)日：2018-03-15
申请号：US15261960
申请日：2016-09-11
Applicant: Cisco Technology, Inc.
Inventor： Yoav GLAZNER , Amitay Stern
IPC: H04L29/06
CPC classification number: H04L63/123 , G06F21/10 , H04N21/4623
Abstract: In one embodiment, a method comprises: in response to a request of a user device to access first content, sending a challenge, relating to digital video included in second content, the challenge at least indicative of positions that include a plurality of frames; receiving a response to the challenge, the response at least indicative of values; attempting to validate the response, including determining values of pixels in the digital video associated with positions indicated by at least one of: the challenge or the response, and comparing the values indicated by the response, or a function thereof, to the determined values, or a function thereof; and performing at least one action relating to access to the first content, dependent on whether or not the attempt to validate the response was successful.
-
公开(公告)号：US11176452B2
公开(公告)日：2021-11-16
申请号：US15444351
申请日：2017-02-28
Applicant: Cisco Technology, Inc.
Inventor： Uri Porat , Yoav Glazner , Amitay Stern
Abstract: In one embodiment, a system, apparatus and a method is described, the system, apparatus and a method including, a storage device and a memory operative to store target content items, a comparator operative to compare one content item of the target content items with the other target content items, and, at least on the basis of comparing the one content item of the target content items with the other content items of the target content items, to develop a correlation graph between each one content item of the target content items and the other content items of the target content items, and a machine learning system operative to receive the correlation graph and to output a decision, on the basis of in the correlation graph, indicating if the content items represented in the correlation graph are pirated content items or not. Related system, apparatuses and methods are also described.
-
公开(公告)号：US10511611B2
公开(公告)日：2019-12-17
申请号：US15261960
申请日：2016-09-11
Applicant: Cisco Technology, Inc.
Inventor： Yoav Glazner , Amitay Stern
IPC: H04L29/06 , H04N21/4623 , G06F21/10
Abstract: In one embodiment, a method comprises: in response to a request of a user device to access first content, sending a challenge, relating to digital video included in second content, the challenge at least indicative of positions that include a plurality of frames; receiving a response to the challenge, the response at least indicative of values; attempting to validate the response, including determining values of pixels in the digital video associated with positions indicated by at least one of: the challenge or the response, and comparing the values indicated by the response, or a function thereof, to the determined values, or a function thereof; and performing at least one action relating to access to the first content, dependent on whether or not the attempt to validate the response was successful.
-
公开(公告)号：US20180367822A1
公开(公告)日：2018-12-20
申请号：US15626131
申请日：2017-06-18
Applicant: Cisco Technology, Inc.
Inventor： Yoav GLAZNER , Amitay Stern
IPC: H04N21/218 , H04L29/06 , H04N19/23 , H04N21/4728 , H04N21/845
Abstract: In one embodiment, a method includes storing data used by a processor, and selecting different bitrates for streaming of a plurality of picture part streams of a video content item to a client device based on available bandwidth and historic data of how much at least one region of a plurality of pictures of the video content item has been rendered for viewing during rendering of the video content item by the client device, wherein each one picture part stream of the plurality of picture part streams conveys a different part of each one picture of the plurality of pictures, and is encoded at a plurality of bitrates. Related apparatus and methods are also described.
-
公开(公告)号：US20180310059A1
公开(公告)日：2018-10-25
申请号：US15490916
申请日：2017-04-19
Applicant: Cisco Technology, Inc.
Inventor： Yoav GLAZNER , Amitay Stern
IPC: H04N21/442 , G06F17/30 , G06K9/64 , H04N21/84 , G06K9/00
CPC classification number: H04N21/44218 , G06F17/30784 , G06T7/00 , H04N21/21805 , H04N21/44222 , H04N21/816 , H04N21/84
Abstract: In one embodiment, a method comprising receiving data of a plurality of viewports generated from a content item during rendering of the content item, receiving data about at least one feature included in the content item, comparing the data of the plurality of viewports with the data about the at least one feature included in the content item, and computing a score representing to what extent the at least one feature is included in the plurality of viewports. Related apparatus and methods are also described.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.016 seconds)
