公开(公告)号：US20180039820A1

公开(公告)日：2018-02-08

申请号：US15227151

申请日：2016-08-03

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： LEE BEGEJA ,  ZHU LIU ,  YADONG MU ,  BERNARD S. RENGER ,  DAVID CRAWFORD GIBBON ,  BEHZAD SHAHRARAY ,  RAGHURAMAN GOPALAN ,  ERIC ZAVESKY

IPC: G06K9/00 ,  H04N7/18 ,  G06T7/20

CPC classification number: G06K9/00221 ,  G06K9/00288 ,  G06K9/00684 ,  G06K9/00711 ,  G06K9/00771 ,  G06K2009/00738 ,  G06T7/20 ,  G06T2207/20081 ,  G06T2207/30201 ,  G11B27/028 ,  H04N7/181

Abstract: Aspects of the subject disclosure may include, for example, systems and methods aggregating video content and adjusting the aggregate video content according to a training model. The adjusted aggregate video content comprises a first subset of the images and does not comprise a second subset of the images. The first subset of the images is determined by the training model based on a plurality of categories corresponding to a plurality of events. The illustrative embodiments also include presenting the adjusted aggregate video content and receiving identifications for the first subset of the images in the aggregate video content. Further, the illustrative embodiments include adjusting the training model according to the identifications and providing the adjusted training model to a network device. Other embodiments are disclosed.

公开(公告)号：US20170316287A1

公开(公告)日：2017-11-02

申请号：US15655145

申请日：2017-07-20

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： YADONG MU ,  ZHU LIU

IPC: G06K9/66 ,  G06F17/30 ,  G06N3/04 ,  G06K9/62

CPC classification number: G06K9/66 ,  G06F16/285 ,  G06F16/51 ,  G06F16/5838 ,  G06K9/6217 ,  G06N3/04 ,  G06N3/0454

Abstract: A method for classifying images using a neural network is described. The method utilizes the neural network to generate a deep hash data structure. In one embodiment, the method includes receiving, at a neural network, first data corresponding to a plurality of images of a training image set. The method includes adjusting parameters of the neural network based on concurrent application at the neural network of multiple loss functions to second data corresponding to the plurality of images to generate adjusted parameters. The method includes generating a deep hash data structure based on the adjusted parameters of the neural network. The method further includes sending, via a transmitter to a device, third data corresponding to the deep hash data structure.

公开(公告)号：US20160352675A1

公开(公告)日：2016-12-01

申请号：US15232159

申请日：2016-08-09

Applicant: AT&T Intellectual Property I, L.P.

Inventor： David Crawford Gibbon ,  LEE BEGEJA ,  RAGHURAMAN GOPALAN ,  ZHU LIU ,  AMY RUTH REIBMAN ,  BERNARD S. RENGER ,  BEHZAD SHAHRARAY ,  ERIC ZAVESKY

IPC: H04L12/58 ,  H04L29/08

CPC classification number: H04L51/32 ,  H04L65/403 ,  H04L67/02 ,  H04L67/327 ,  H04N5/765 ,  H04N9/8205 ,  H04N9/8227 ,  H04N21/2743 ,  H04N21/4223 ,  H04N21/4788 ,  H04N21/6377

Abstract: Aspects of the subject disclosure may include, for example, receiving a plurality of media content instances, where each media content instance of the plurality of media content instances comprises origination information, identifying a common event from the origination information of each media content instance of the plurality of media content instances, determining a plurality of viewing perspectives of the plurality of media content instances responsive to identifying the common event, and sending an alert to a social network to enable access to a viewing perspective of the plurality of viewing perspectives.

Abstract translation: 主题公开内容的各方面可以包括例如接收多个媒体内容实例，其中多个媒体内容实例中的每个媒体内容实例包括发起信息，从每个媒体内容实例的始发信息中识别公共事件 多个媒体内容实例，响应于识别公共事件来确定多个媒体内容实例的多个观看视角，以及向社交网络发送警报以使得能够访问多个观看视角的观看视角。

公开(公告)号：US20180041805A1

公开(公告)日：2018-02-08

申请号：US15226630

申请日：2016-08-02

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： DAVID CRAWFORD GIBBON ,  YADONG MU ,  LEE BEGEJA ,  BERNARD S. RENGER ,  RAGHURAMAN GOPALAN ,  BEHZAD SHAHRARAY ,  ZHU LIU ,  ERIC ZAVESKY

IPC: H04N21/45 ,  H04N21/442 ,  H04N21/214 ,  H04N21/258 ,  H04N21/25 ,  H04N21/482

CPC classification number: H04N21/4532 ,  H04N21/214 ,  H04N21/252 ,  H04N21/25841 ,  H04N21/44222 ,  H04N21/4524 ,  H04N21/4826

Abstract: Aspects of the subject disclosure may include, for example, a system and method for selecting media content for a group of persons located at a venue. The system and method identify a plurality of viewers in a vicinity of a venue that has one or more display devices from location data and extracts a content viewing preference of each viewer from their profile data. The process includes aggregating the content viewing preference of each of the plurality of viewers to generate an aggregated content profile. Based on the aggregated content profile, a list of content is generated. Next, a first group of viewers approaching a viewing range of a display device are sensed by imaging data. Any conflicts between content viewing preferences of the first group of viewers are detected and resolved based on weighting the viewing preferences of the group. Other embodiments are disclosed.

公开(公告)号：US20170257669A1

公开(公告)日：2017-09-07

申请号：US15058335

申请日：2016-03-02

Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

Inventor： ZHU LIU ,  LEE BEGEJA ,  DAVID CRAWFORD GIBBON ,  RAGHURAMAN GOPALAN ,  YADONG MU ,  BERNARD S. RENGER ,  BEHZAD SHAHRARAY ,  ERIC ZAVESKY

IPC: H04N21/442 ,  H04N21/81 ,  H04N21/4223 ,  H04N21/4147 ,  H04N21/466 ,  H04N21/44 ,  H04N21/2668 ,  H04N21/8549 ,  G06K9/00 ,  H04N21/422

CPC classification number: H04N21/44218 ,  G06K9/00228 ,  H04N21/2668 ,  H04N21/4147 ,  H04N21/42201 ,  H04N21/4223 ,  H04N21/4325 ,  H04N21/44008 ,  H04N21/44222 ,  H04N21/458 ,  H04N21/4667 ,  H04N21/812 ,  H04N21/8133 ,  H04N21/8549

Abstract: A method includes determining a level of user engagement associated with content of a program displayed at a first display device and comparing the level of user engagement to a threshold. If the level of user engagement satisfies the threshold, the method includes generating an advertisement associated with the content displayed at the first display device and determining whether the user is within a distance of the first display device during a commercial break of the program. The method also includes displaying the advertisement at the first display device during the commercial break if the user is within the distance of the first display device and displaying the advertisement at a second display device during the commercial break if the user is not within the distance of the first display device. If the level of user engagement fails to satisfy the threshold, generation of the advertisement is bypassed.