公开(公告)号：US11895068B2

公开(公告)日：2024-02-06

申请号：US17372981

申请日：2021-07-12

Applicant: Snap Inc.

Inventor： Jianchao Yang ,  Yuke Zhu ,  Ning Xu ,  Kevin Dechau Tang ,  Jia Li

IPC: H04L51/10 ,  G06F16/22 ,  G06F16/51 ,  G06F16/583 ,  G06N20/00 ,  G06F16/9535 ,  G06F16/954 ,  G06F16/2457 ,  G06F16/951 ,  G06N3/04 ,  G06N3/08 ,  G06V20/00 ,  H04L51/52 ,  G06T7/00 ,  H04L67/01 ,  H04L67/55

CPC classification number: H04L51/10 ,  G06F16/22 ,  G06F16/24578 ,  G06F16/51 ,  G06F16/5854 ,  G06F16/951 ,  G06F16/954 ,  G06F16/9535 ,  G06N3/04 ,  G06N3/08 ,  G06N20/00 ,  G06V20/35 ,  H04L51/52 ,  G06T7/0002 ,  G06T2207/20084 ,  G06T2207/30168 ,  H04L67/01 ,  H04L67/55

Abstract: Systems, devices, methods, media, and instructions for automated image processing and content curation are described. In one embodiment a server computer system receives a plurality of content communications from a plurality of client devices, each content communication comprising an associated piece of content and a corresponding metadata. Each content communication is processed to determine associated context values for each piece of content, each associated context value comprising at least one content value generated by machine vision processing of the associated piece of content. A first content collection is automatically generated based on context values, and a set of user accounts are associated with the collection. An identifier associated with the first content collection is published to user devices associated with user accounts. In various additional embodiments, different content values, image processing operations, and content selection operations are used to curate content collections.

公开(公告)号：US11755910B2

公开(公告)日：2023-09-12

申请号：US17878591

申请日：2022-08-01

Applicant: Snap Inc.

Inventor： Yuncheng Li ,  Zhou Ren ,  Ning Xu ,  Enxu Yan ,  Tan Yu

IPC: G06N3/08 ,  G06T7/55 ,  G06T7/33 ,  G06V20/64 ,  G06F18/214 ,  G06F18/2431 ,  G06V10/82 ,  G06V10/44 ,  G06V20/20 ,  G06V20/40

CPC classification number: G06N3/08 ,  G06F18/214 ,  G06F18/2431 ,  G06T7/344 ,  G06T7/55 ,  G06V10/454 ,  G06V10/82 ,  G06V20/20 ,  G06V20/41 ,  G06V20/64

Abstract: Systems and methods are disclosed for capturing multiple sequences of views of a three-dimensional object using a plurality of virtual cameras. The systems and methods generate aligned sequences from the multiple sequences based on an arrangement of the plurality of virtual cameras in relation to the three-dimensional object. Using a convolutional network, the systems and methods classify the three-dimensional object based on the aligned sequences and identify the three-dimensional object using the classification.

公开(公告)号：US11557324B2

公开(公告)日：2023-01-17

申请号：US17303817

申请日：2021-06-08

Applicant: Snap Inc.

Inventor： Jia Li ,  Nathan Litke ,  Jose Jesus (Joseph) Paredes ,  Rahul Bhupendra Sheth ,  Daniel Szeto ,  Ning Xu ,  Jianchao Yang

IPC: H04N21/218 ,  H04N21/2343 ,  H04N21/431 ,  H04N21/44 ,  H04N21/4402 ,  H04N21/4728 ,  H04N21/63 ,  G11B27/10 ,  G11B27/031

Abstract: Systems and methods are described for determining a first media item related to an event, of a plurality of stored media items each comprising video content related to the event, that was captured in a device orientation corresponding to a first device orientation detected for the first computing device; providing, to the first computing device, the first media item to be displayed on the first computing device; in response to a detected change to a second device orientation for the first computing device, determining a second media item that was captured in a device orientation corresponding to the second device orientation detected for the first computing device; and providing, to the first computing device, the second media item to be displayed on the first computing device.

公开(公告)号：US11551042B1

公开(公告)日：2023-01-10

申请号：US16552393

申请日：2019-08-27

Applicant: Snap Inc.

Inventor： Jianfei Yu ,  Luis Carlos Dos Santos Marujo ,  Venkata Satya Pradeep Karuturi ,  Leonardo Ribas Machado das Neves ,  Ning Xu ,  William Brendel

IPC: G06F40/30 ,  G06K9/62 ,  G06N3/08 ,  G06N20/20 ,  G06N3/04 ,  G06F40/284 ,  G10L25/30 ,  G06F40/295 ,  G06F40/279 ,  G06F40/289 ,  G10L15/18 ,  G10L15/16

Abstract: Sentiment classification can be implemented by an entity-level multimodal sentiment classification neural network. The neural network can include left, right, and target entity subnetworks. The neural network can further include an image network that generates representation data that is combined and weighted with data output by the left, right, and target entity subnetworks to output a sentiment classification for an entity included in a network post.

公开(公告)号：US11422996B1

公开(公告)日：2022-08-23

申请号：US16396119

申请日：2019-04-26

Applicant: Snap Inc.

Inventor： Lawrence Jason Muhlstein ,  Leonardo Ribas Machado das Neves ,  Yanen Li ,  Ning Xu

IPC: G06F16/22 ,  G06N3/08 ,  G06F3/0481 ,  G06F3/0488

Abstract: A neural network system can select content based on user and item content embeddings in an approach that can be updated in real time on the user device without server support. Requests for content sent to the server can include an anonymous user embedding that includes data describing the user's inputs. The content that is nearest to the user embedding in a joint embedding space can be returned as suggested content.

公开(公告)号：US20220230277A1

公开(公告)日：2022-07-21

申请号：US17714764

申请日：2022-04-06

Applicant: Snap Inc.

Inventor： Guohui Wang ,  Sumant Milind Hanumante ,  Ning Xu ,  Yuncheng Li

IPC: G06T3/40 ,  G06N3/08 ,  G06N3/04 ,  G06T1/20 ,  G06T11/60 ,  G06N3/063

Abstract: Remote distribution of multiple neural network models to various client devices over a network can be implemented by identifying a native neural network and remotely converting the native neural network to a target neural network based on a given client device operating environment. The native neural network can be configured for execution using efficient parameters, and the target neural network can use less efficient but more precise parameters.

公开(公告)号：US20220172003A1

公开(公告)日：2022-06-02

申请号：US17547548

申请日：2021-12-10

Applicant: Snap Inc.

Inventor： Jianchao Yang ,  Ning Xu ,  Jian Ren

IPC: G06K9/62

Abstract: Disclosed herein are arrangements that facilitate the transfer of knowledge from models for a source data-processing domain to models for a target data-processing domain. A convolutional neural network space for a source domain is factored into a first classification space and a first reconstruction space. The first classification space stores class information and the first reconstruction space stores domain-specific information. A convolutional neural network space for a target domain is factored into a second classification space and a second reconstruction space. The second classification space stores class information and the second reconstruction space stores domain-specific information. Distribution of the first classification space and the second classification space is aligned.

公开(公告)号：US20220156956A1

公开(公告)日：2022-05-19

申请号：US17589459

申请日：2022-01-31

Applicant: Snap Inc.

Inventor： Kun Duan ,  Daniel Ron ,  Chongyang Ma ,  Ning Xu ,  Shenlong Wang ,  Sumant Milind Hanumante ,  Dhritiman Sagar

IPC: G06T7/536 ,  G06T11/60

Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.

公开(公告)号：US11276190B2

公开(公告)日：2022-03-15

申请号：US16859468

申请日：2020-04-27

Applicant: Snap Inc.

Inventor： Kun Duan ,  Daniel Ron ,  Chongyang Ma ,  Ning Xu ,  Shenlong Wang ,  Sumant Milind Hanumante ,  Dhritiman Sagar

IPC: G06T7/536 ,  G06T11/60

Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.

公开(公告)号：US11159743B2

公开(公告)日：2021-10-26

申请号：US16722721

申请日：2019-12-20

Applicant: Snap Inc.

Inventor： Jia Li ,  Nathan Litke ,  Jose Jesus (Joseph) Paredes ,  Rahul Bhupendra Sheth ,  Daniel Szeto ,  Ning Xu ,  Jianchao Yang

IPC: H04N5/93 ,  H04N5/262 ,  G06K9/00 ,  G06K9/62

Abstract: Systems and methods are described for determining that the user interaction with a display of a computing device during display of a video comprising a sequence of frames indicates a region of interest in a current frame of the sequence of frames of the displayed video. For each frame of the sequence of frames after the current frame, the frame is cropped to generate a cropped frame comprising a portion of the frame including the region of interest in the frame, the cropped frame is enlarged based on a display size corresponding to an angle or orientation of the computing device during display of the video, and the enlarged cropped frame replaces the frame such that the enlarged cropped frame is displayed in the sequence of frames of the video on the display of the computing device instead of the frame.