-
公开(公告)号:EP4033768A2
公开(公告)日:2022-07-27
申请号:EP22156245.7
申请日:2016-02-19
申请人: Facebook, Inc.
IPC分类号: H04N21/2187 , H04N21/24 , H04N21/2743 , H04N21/4788
摘要: One or more embodiments of the disclosure provide systems and methods for providing media presentations to users of a media presentation system. A media presentation generally includes a one or more media streams provided by one or more capturing users of the media presentation system. In one or more embodiments, a user of the media presentation system may share a media presentation with a viewing user. The media presentation system can provide a number of features to produce a media stream within a media presentation.
-
公开(公告)号:EP4009653A1
公开(公告)日:2022-06-08
申请号:EP22151156.1
申请日:2018-08-02
申请人: Facebook, Inc.
IPC分类号: H04N21/4788 , H04N21/63 , H04N21/643
摘要: Exemplary embodiments relate to the application of coordinated or cooperative effects to a coordinated activity. A coordinated activity protocol is provided for synchronizing interactive effects and experiences across multiple devices. The protocol allows effects to be initiated and coordinated on multiple devices via a real-time communications (RTC) channel. Messages may be exchanged to cooperatively initiate the effect, and (once initiated) generic data may be exchanged via application programming interface (API) calls. According to some embodiments, the coordinated activity is a shared video experience, such as a video conference or shared video-watching experience. According to other embodiments, the coordinated activity relates to other types of experiences, such as single- or multi-player games, shared book reading, communal interactions with a photo album, etc.
-
公开(公告)号:EP4002278A1
公开(公告)日:2022-05-25
申请号:EP21208617.7
申请日:2021-11-16
申请人: Facebook, Inc.
发明人: OQUAB, Maxime , STOCK, Pierre , GAFNI, Oran , HAZIZA, Daniel , XU, Tao , ZHANG, Peizhao , CELEBI, Onur , LABATUT, Patrick , PEYRONEL, Thibault , COUPRIE, Camille
摘要: A first device may receive, from a second device, a reference landmark map identifying locations of facial features of a user of the second device depicted in a reference image and a feature map, generated based on the reference image, representing an identity of the user. The first device may receive, from the second device, a current compressed landmark map based on a current image of the user and decompress the current compressed landmark map to generate a current landmark map. The first device may update the feature map based on a motion field generated using the reference landmark map and the current landmark map. The first device may generate scaling factors based on a normalization facial mask of predetermined facial features of the user. The first device may generate an output image of the user by decoding the updated feature map using the scaling factors.
-
公开(公告)号:EP3991397A1
公开(公告)日:2022-05-04
申请号:EP20751731.9
申请日:2020-06-11
申请人: Facebook, Inc.
发明人: TSAI, Chia-Yang , LI, Handong
-
公开(公告)号:EP3968237A1
公开(公告)日:2022-03-16
申请号:EP21163649.3
申请日:2021-03-19
申请人: Facebook, Inc.
发明人: KOMURAVELLI, Rakesh , NAIR, Krishnakumar Narayanan , DIRIL, Abdulkadir Utku , ZADEH, Ehsan Khish Ardestani , HAO, Yuchen , SCHATZ, Martin , ULRICH, Thomas Mark , WU, Olivia , KADKOL, Anup Ramesh , FIROOZSHAHIAN, Amin
摘要: A processor system comprises a plurality of processing elements. Each processing element includes a corresponding convolution processor unit configured to perform a portion of a groupwise convolution. The corresponding convolution processor unit determines multiplication results by multiplying each data element of a portion of data elements in a convolution data matrix with a corresponding data element in a corresponding groupwise convolution weight matrix. The portion of data elements in the convolution data matrix that are multiplied belong to different channels and different groups. For each specific channel of the different channels, the corresponding convolution processor unit sums together at least some of the multiplication results belonging to the same specific channel to determine a corresponding channel convolution result data element. The processing elements sum together a portion of the channel convolution result data elements from a group of different convolution processor units to determine a groupwise convolution result data element.
-
-
公开(公告)号:EP3958196A1
公开(公告)日:2022-02-23
申请号:EP21171768.1
申请日:2021-05-03
申请人: Facebook, Inc.
发明人: WANG, Xiao , TSAI, Josselyn , OLSON, Ryan , SARKAR, Shilpa , TSAY, Derek
摘要: Techniques are described that enable a user to create a collection of content posts on a social networking system. In some cases, a social networking system receives multiple content posts to be shared, and shares the multiple content posts with a first group of user accounts. The social networking system receives a request to create a collection of one or more content posts of the multiple content posts, where the request includes a descriptor associated with the collection. The social networking system generates the collection of the one or more content posts including the descriptor, and provides the collection to a second group of user accounts.
-
公开(公告)号:EP3937085A1
公开(公告)日:2022-01-12
申请号:EP21153047.2
申请日:2021-01-22
申请人: Facebook, Inc.
发明人: NAIR, Krishnakumar Narayanan , KOMURAVELLI, Rakesh , DIRIL, Abdulkadir Utku , ZADEH, Ehsan Khish Ardestani , HAO, Yuchen , SCHATZ, Martin , ULRICH, Thomas Mark , WU, Olivia , KADKOL, Anup Ramesh , FIROOZSHAHIAN, Amin
摘要: A processor system comprises a first and second group of registers and a hardware channel convolution processor unit. The first group of registers is configured to store data elements of channels of a portion of a convolution data matrix. Each register stores at least one data element from each channel. The second group of registers is configured to store data elements of convolution weight matrices including a separate convolution weight matrix for each channel. Each register stores at least one data element from each convolution weight matrix. The hardware channel convolution processor unit is configured to multiply each data element in the first group of registers with a corresponding data element in the second group of registers and sum together the multiplication results for each specific channel to determine corresponding channel convolution result data elements in a corresponding channel convolution result matrix.
-
公开(公告)号:EP3935477A1
公开(公告)日:2022-01-12
申请号:EP20713776.1
申请日:2020-02-10
申请人: Facebook, Inc.
发明人: ZHANG, Boyang , HESCH, Joel, Amado
IPC分类号: G06F3/01 , A63B24/00 , G06F3/0346 , G06T7/73 , G02B27/01
-
公开(公告)号:EP3920543A1
公开(公告)日:2021-12-08
申请号:EP21174083.2
申请日:2021-05-17
申请人: Facebook, Inc.
IPC分类号: H04N21/4788 , H04N21/414 , H04N21/4223 , H04N21/2743 , H04N21/81 , H04N21/854 , H04N21/234
摘要: Techniques are described herein that enable and assist a user to generate customized video content and alter the video content without altering the customizations. For example, a social networking system may receive, from a user account associated with the social networking system, an input to create video content and add visual customizations to the video content. In some examples, the social networking system may also receive input from the user to alter the video content by altering the length of the video clip and/or adding a second video clip. The social networking system then alters the video content while maintain the previous customizations. The social networking system may then save the altered video content as a draft or share the altered video content to other users on the social networking system.
-
-
-
-
-
-
-
-
-