公开(公告)号：US20220116436A1

公开(公告)日：2022-04-14

申请号：US17556084

申请日：2021-12-20

Applicant: Facebook, Inc.

Inventor： Allison Hartnett ,  Kristin Lindsey George ,  Abhishek Parthasarathy ,  Hemal Khatri ,  Tomer Bar

IPC: H04L65/611 ,  H04L65/1069 ,  H04N21/2187 ,  H04N7/14 ,  H04N21/6405

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for accurately, flexibly, and efficiently broadcasting public combined live video streams from multiple participant devices, which change over the course of the live broadcast, as well as generating dynamic user interfaces that streamline adding, removing, and swapping participant devices from the public combined live video stream. In particular, a live video streaming system facilitates compositing live video streams from multiple participant devices into a public combined live video stream within a digital room before broadcasting the public combined live video stream to viewer devices. In addition, the live video stream smoothly and efficiently transitions new participant devices from a digital waiting room to the public combined live video stream as well as switches current participant devices from the public combined live video stream to a digital waiting room, all while maintaining live video stream of the participant devices.

公开(公告)号：US20220070504A1

公开(公告)日：2022-03-03

申请号：US17011605

申请日：2020-09-03

Applicant: Facebook, Inc.

Inventor： Allison Hartnett ,  Kristin Lindsey George ,  Abhishek Parthasarathy ,  Hemal Khatri ,  Tomer Bar

IPC: H04N21/2343 ,  H04N21/442 ,  H04N21/2187 ,  H04N21/4788 ,  H04N7/15

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for accurately, flexibly, and efficiently broadcasting public combined live video streams from multiple participant devices, which change over the course of the live broadcast, as well as generating dynamic user interfaces that streamline adding, removing, and swapping participant devices from the public combined live video stream. In particular, a live video streaming system facilitates compositing live video streams from multiple participant devices into a public combined live video stream within a digital room before broadcasting the public combined live video stream to viewer devices. In addition, the live video stream smoothly and efficiently transitions new participant devices from a digital waiting room to the public combined live video stream as well as switches current participant devices from the public combined live video stream to a digital waiting room, all while maintaining live video stream of the participant devices.

公开(公告)号：US20220070243A1

公开(公告)日：2022-03-03

申请号：US17392112

申请日：2021-08-02

Applicant: Facebook, Inc.

Inventor： Allison Hartnett ,  Kristin Lindsey George ,  Abhishek Parthasarathy ,  Hemal Khatri ,  Tomer Bar

IPC: H04L29/06 ,  H04N21/2187 ,  H04N7/14 ,  H04N21/6405

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for accurately, flexibly, and efficiently broadcasting public combined live video streams from multiple participant devices, which change over the course of the live broadcast, as well as generating dynamic user interfaces that streamline adding, removing, and swapping participant devices from the public combined live video stream. In particular, a live video streaming system facilitates compositing live video streams from multiple participant devices into a public combined live video stream within a digital room before broadcasting the public combined live video stream to viewer devices. In addition, the live video stream smoothly and efficiently transitions new participant devices from a digital waiting room to the public combined live video stream as well as switches current participant devices from the public combined live video stream to a digital waiting room, all while maintaining live video stream of the participant devices.

公开(公告)号：US20190238610A1

公开(公告)日：2019-08-01

申请号：US16383005

申请日：2019-04-12

Applicant: Facebook, Inc.

Inventor： Hermes Germi Pique Corchs ,  Kirill A. Pugin ,  Razvan Gabriel Racasanu ,  Colin Todd Miller ,  Ragavan Srinivasan ,  Tomer Bar ,  Bryce David Redd

IPC: H04L29/06 ,  H04N21/81 ,  H04N21/658 ,  H04N21/44 ,  H04N21/4223 ,  H04N21/414 ,  H04N21/472 ,  G06K9/00 ,  G06T11/60

CPC classification number: H04L65/604 ,  G06K9/00221 ,  G06K9/00288 ,  G06T11/60 ,  G06T2207/30201 ,  H04L65/602 ,  H04L65/605 ,  H04L65/607 ,  H04N21/41407 ,  H04N21/4223 ,  H04N21/44008 ,  H04N21/47205 ,  H04N21/6582 ,  H04N21/8133

Abstract: A video effects application executes on a client device having an image capture device and receives video data captured by the image capture device. The video effects application extracts information from the captured video data and stores the extracted information as metadata associated with the captured video data. For example, the video effects application identifies objects in the captured video data or identifies optical flow of the captured video data and stores the identified objects or identified optical flow as metadata associated with the captured video data. The video effects application stores information describing modifications to the captured video data in association with the captured video data. When the captured video data is presented, the captured video data, associated metadata, and information describing the modifications is communicated to a renderer, which uses the metadata to perform the identified modifications to the captured video data when presenting the captured video data.

公开(公告)号：US20170236007A1

公开(公告)日：2017-08-17

申请号：US15587326

申请日：2017-05-04

Applicant: Facebook, Inc.

Inventor： Dan Barak ,  Tomer Bar ,  Kun Chen

IPC: G06K9/00 ,  G06K9/20

CPC classification number: G06K9/00671 ,  G06K9/00288 ,  G06K9/00677 ,  G06K9/00979 ,  G06K9/2081

Abstract: Systems, methods, and non-transitory computer-readable media can receive a selection of an image. An object included in the image can be detected. An image portion that includes the object can be extracted from the image. The image portion can be provided for image analysis based on one or more object recognition processes. An identifier for the object can be received. The identifier can be determined based on the one or more object recognition processes being applied to the image portion.

公开(公告)号：US20160328096A1

公开(公告)日：2016-11-10

申请号：US14706921

申请日：2015-05-07

Applicant: Facebook, Inc.

Inventor： Thai Gia Tran ,  Christophe Marcel Rene Tauziet ,  Judy Liu ,  Jeffrey Lin ,  Tomer Bar ,  Kejia Zhu

IPC: G06F3/0482 ,  G06T1/00

CPC classification number: G06T11/60 ,  G06F16/48

Abstract: A plurality of media content items associated with a user and stored locally can be identified. Information associated with the plurality can be acquired. The information can include time data, location data, and/or social graph data. It can be determined, based on the information, that a collection of media content items, out of the plurality, are related. A layout customized for the collection can be generated. Moreover, the collection of media content items that are determined to be related can be identified. The collection can be presented as a collage based on the layout customized for the collection. Contextual information associated with the collage can be acquired. The contextual information can include time data, location data, and/or social graph data. A particular virtual overlaying template can be selected based on the contextual information. The collage can be presented in conjunction with the particular virtual overlaying template.

Abstract translation: 可以识别与用户相关联并存储在本地的多个媒体内容项目。 可以获取与多个相关联的信息。 该信息可以包括时间数据，位置数据和/或社交图表数据。 可以基于该信息来确定多个媒体内容项目的集合是相关的。 可以生成为集合定制的布局。 此外，可以识别确定为相关的媒体内容项目的集合。 该集合可以根据为集合定制的布局呈现为拼贴。 可以获取与拼贴相关联的上下文信息。 上下文信息可以包括时间数据，位置数据和/或社交图表数据。 可以基于上下文信息来选择特定的虚拟覆盖模板。 拼贴可以与特定的虚拟覆盖模板一起呈现。

公开(公告)号：US20160267674A1

公开(公告)日：2016-09-15

申请号：US14656276

申请日：2015-03-12

Applicant: Facebook, Inc.

Inventor： Dan Barak ,  Tomer Bar ,  Kun Chen

IPC: G06T7/00 ,  G06K9/00

CPC classification number: G06K9/00671 ,  G06K9/00288 ,  G06K9/00677 ,  G06K9/00979 ,  G06K9/2081

Abstract: Systems, methods, and non-transitory computer-readable media can receive a selection of an image. An object included in the image can be detected. An image portion that includes the object can be extracted from the image. The image portion can be provided for image analysis based on one or more object recognition processes. An identifier for the object can be received. The identifier can be determined based on the one or more object recognition processes being applied to the image portion.

Abstract translation: 系统，方法和非暂时的计算机可读介质可以接收图像的选择。 可以检测包括在图像中的对象。 可以从图像中提取包括对象的图像部分。 图像部分可以被提供用于基于一个或多个对象识别处理的图像分析。 可以接收对象的标识符。 可以基于应用于图像部分的一个或多个对象识别处理来确定标识符。