公开(公告)号：US20210183033A1

公开(公告)日：2021-06-17

申请号：US17123493

申请日：2020-12-16

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Christopher Yale Crutchfield ,  Emre Yamangil

IPC: G06T5/40 ,  G06T7/90 ,  G06T5/00 ,  G06N3/08 ,  H04L29/08 ,  G06K9/00 ,  G06N20/00

Abstract: A mobile device can implement a neural network-based style transfer scheme to modify an image in a first style to a second style. The style transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The style transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.

公开(公告)号：US12079904B2

公开(公告)日：2024-09-03

申请号：US17980879

申请日：2022-11-04

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Wisam Dakka ,  Christopher Yale Crutchfield ,  Aymeric Damien ,  Emre Yamangil ,  Chunhui Zhu

IPC: G06T11/00 ,  G06F16/51 ,  G06N3/04 ,  G06T11/60 ,  G06V10/44 ,  G06V10/82 ,  G06V30/194

CPC classification number: G06T11/001 ,  G06N3/04 ,  G06T11/60 ,  G06V10/82 ,  G06V30/194 ,  G06F16/51 ,  G06V10/454

Abstract: Manipulating images using computationally expensive machine learning schemes can be implemented using server-generated models of the machine learning schemes that are transmitted to a client device for application. The schemes can include convolutional neural networks having a kernel comprising a plurality of low-rank matrices.

公开(公告)号：US12038932B2

公开(公告)日：2024-07-16

申请号：US17387134

申请日：2021-07-28

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Wisam Dakka ,  Andrei Damian ,  Jiwoon Jeon ,  Ranveer Kunal ,  Andre Madeira ,  Michael Brian Murray ,  Emre Yamangil ,  Diwakar Punjani ,  Yantao Zheng

IPC: G06F16/2457 ,  H04L29/08 ,  H04L67/50 ,  G06Q50/00

CPC classification number: G06F16/24578 ,  H04L67/535 ,  G06Q50/01

Abstract: Disclosed are implementations for ranking a feed in a social network. In one aspect, a method of generating a feed includes identifying a group of users associated with a first user, identify notifications for the first user based on the group of users, determine one or more actions that may result from each of the identified notifications, rank the notifications based on the one or more determined actions; and display the notifications to the first user according to the ranking.

公开(公告)号：US20230283654A1

公开(公告)日：2023-09-07

申请号：US18195813

申请日：2023-05-10

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Christopher Yale Crutchfield ,  Emre Yamangil

IPC: H04L67/04 ,  G06T5/40 ,  G06T7/90 ,  G06T5/00 ,  G06N3/08 ,  G06N20/00 ,  G06V40/16 ,  G06V10/774 ,  G06V10/82

CPC classification number: H04L67/04 ,  G06T5/40 ,  G06T7/90 ,  G06T5/009 ,  G06N3/08 ,  G06T5/001 ,  G06N20/00 ,  G06V40/161 ,  G06V10/7753 ,  G06V10/82 ,  G06V40/175 ,  G06T2207/20132 ,  G06Q50/01

Abstract: A mobile device can implement a neural network-based style transfer scheme to modify an image in a first style to a second style. The style transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The style transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.

公开(公告)号：US11532110B2

公开(公告)日：2022-12-20

申请号：US16923563

申请日：2020-07-08

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Emre Yamangil ,  Wisam Dakka ,  Aymeric Damien ,  Emre Yamangil ,  Chunhui Zhu

IPC: G06T11/60 ,  G06N3/04 ,  G06V30/194 ,  G06F16/51

Abstract: Manipulating images using computationally expensive machine learning schemes can be implemented using server-generated models of the machine learning schemes that are transmitted to a client device for application. The schemes can include convolutional neural networks having a kernel comprising a plurality of low-rank matrices.

公开(公告)号：US20220029944A1

公开(公告)日：2022-01-27

申请号：US17493111

申请日：2021-10-04

Applicant: Snap Inc.

Inventor： Theresa Barton ,  Yanping Chen ,  Lucas Ou-Yang ,  Emre Yamangil ,  Keyang Zhang ,  Jiwoon Jeon ,  Jaewook Chung ,  Wisam Dakka ,  Xin Chen

IPC: H04L12/58 ,  G06F11/30 ,  G06F11/34

Abstract: Disclosed are methods and systems for ranking content. In one aspect, a method of ranking content for display includes identifying, via hardware processing circuitry, interactions by a single account with content pairs, each of the content in the content pairs included in a plurality of content, aggregating, via the hardware processing circuitry, the identified interactions across a plurality of accounts, associating, via the hardware processing circuitry, probabilities with each content in the plurality of content based on the aggregated interactions, ranking, via the hardware processing circuitry, the plurality of content based on the associated probabilities; and selecting, via the hardware processing circuitry, content ranked above a threshold for display.

公开(公告)号：US11106686B1

公开(公告)日：2021-08-31

申请号：US16203548

申请日：2018-11-28

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Wisam Dakka ,  Andrei Damian ,  Jiwoon Jeon ,  Ranveer Kunal ,  Andre Madeira ,  Michael Brian Murray ,  Emre Yamangil ,  Diwakar Punjani ,  Yantao Zheng

IPC: G06F16/30 ,  G06F7/00 ,  G06F16/2457 ,  H04L29/08 ,  G06Q50/00

Abstract: Disclosed are implementations for ranking a feed in a social network. In one aspect, a method of generating a feed includes identifying a group of users associated with a first user, identify notifications for the first user based on the group of users, determine one or more actions that may result from each of the identified notifications, rank the notifications based on the one or more determined actions; and display the notifications to the first user according to the ranking.

公开(公告)号：US11068141B1

公开(公告)日：2021-07-20

申请号：US16265355

申请日：2019-02-01

Applicant: Snap Inc.

Inventor： Theresa Barton ,  Yanping Chen ,  Jaewook Chung ,  Christopher Yale Crutchfield ,  Aymeric Damien ,  Sergei Kotcur ,  Igor Kudriashov ,  Sergey Tulyakov ,  Andrew Wan ,  Emre Yamangil

IPC: G06F3/00 ,  G06F3/0484 ,  G06K9/00 ,  G06F3/0482 ,  G06T7/11 ,  H04N5/265 ,  H04N5/262 ,  G06F3/0481

Abstract: A system of machine learning schemes can be configured to efficiently perform image processing tasks on a user device, such as a mobile phone. The system can selectively detect and transform individual regions within each frame of a live streaming video. The system can selectively partition and toggle image effects within the live streaming video.

公开(公告)号：US20200334883A1

公开(公告)日：2020-10-22

申请号：US16923563

申请日：2020-07-08

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Wisam Dakka

IPC: G06T11/60 ,  G06N3/04 ,  G06K9/66

Abstract: Manipulating images using computationally expensive machine learning schemes can be implemented using server-generated models of the machine learning schemes that are transmitted to a client device for application. The schemes can include convolutional neural networks having a kernel comprising a plurality of low-rank matrices.

公开(公告)号：US10672096B1

公开(公告)日：2020-06-02

申请号：US16659561

申请日：2019-10-21

Applicant: Snap Inc.

Inventor： Yanping Chen ,  Jaewook Chung ,  Wisam Dakka

IPC: G06T15/00 ,  G06T1/20 ,  G06N3/08 ,  G06T11/00 ,  G06N3/04 ,  G06N3/063

Abstract: A multistage neural network system can store neural networks as shader programs on GPU memory. Neural network weights can be stored as shader objects or textures on the GPU memory. The GPU can receive a number of neural network image processing tasks to perform on images captured by a client device. The GPU can execute the tasks per driver parameters and display results in real time or near real time on the client device.