公开(公告)号：US11080351B1

公开(公告)日：2021-08-03

申请号：US16505681

申请日：2019-07-08

Applicant: Snap Inc.

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

IPC: G06F16/9535 ,  G06N20/00 ,  G06F16/954 ,  H04L29/08 ,  H04L12/58 ,  H04L29/06

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：US20210073597A1

公开(公告)日：2021-03-11

申请号：US16949856

申请日：2020-11-17

Applicant: Snap Inc.

Inventor： Wei Han ,  Jianchao Yang ,  Ning Zhang ,  Jia Li

IPC: G06K9/62 ,  G06K9/46 ,  G06K9/52 ,  G06K9/66 ,  G06T3/40

Abstract: Systems, devices, media, and methods are presented for identifying and categorically labeling objects within a set of images. The systems and methods receive an image depicting an object of interest, detect at least a portion of the object of interest within the image using a multilayer object model, determine context information, and identify the object of interest included in two or more bounding boxes.

公开(公告)号：US10776663B1

公开(公告)日：2020-09-15

申请号：US16521956

申请日：2019-07-25

Applicant: Snap Inc.

Inventor： Lidiia Bogdanovych ,  William Brendel ,  Samuel Edward Hare ,  Fedir Poliakov ,  Guohui Wang ,  Xuehan Xiong ,  Jianchao Yang ,  Linjie Yang

IPC: G06K9/62 ,  G06T7/11 ,  G06T7/194 ,  G06N3/08 ,  G06N3/04 ,  G06K9/68 ,  G06K9/74 ,  H04N5/76 ,  H04N5/445 ,  H04N7/14

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

公开(公告)号：US20200250870A1

公开(公告)日：2020-08-06

申请号：US15929298

申请日：2020-04-23

Applicant: Snap Inc.

Inventor： Nicholas Richard Allen ,  Sheldon Chang ,  Maria Pavlovskaia ,  Amer Shahanawaz ,  Jianchao Yang

IPC: G06T11/60 ,  G06Q50/00

Abstract: Systems and methods are provided for receiving, at a server computer, a plurality of content messages from a plurality of content sources, each content message comprising media content, for each of the plurality of content messages received, associating the media content with a predetermined media collection, and storing the content message in a database. The system and methods further providing for causing the plurality of content messages to be displayed on an operator device with other content messages associated with the media collection, determining that a predetermined trigger related to the media collection has been activated, updating an identifier of the media collection from a first indicator to a second indicator indicating an action needs to be taken on the media collection, and causing the updated identifier with the second indicator to be displayed on an operator device.

公开(公告)号：US10382373B1

公开(公告)日：2019-08-13

申请号：US15253492

申请日：2016-08-31

Applicant: Snap Inc.

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

IPC: G06F15/16 ,  H04L12/58 ,  G06K9/00 ,  G06F16/22 ,  G06F16/51 ,  G06F16/583 ,  G06T7/00

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 content message from a first content source, and analyzes the content message to determine one or more quality scores and one or more content values associated with the content message. The server computer system analyzes the content message with a plurality of content collections of the database to identify a match between at least one of the one or more content values and a topic associated with at least a first content collection of the one or more content collections and automatically adds the content message to the first content collection based at least in part on the match. In various embodiments, different content values, image processing operations, and content selection operations are used to curate content collections.

公开(公告)号：US10198671B1

公开(公告)日：2019-02-05

申请号：US15348501

申请日：2016-11-10

Applicant: SNAP INC.

Inventor： Linjie Yang ,  Kevin Dechau Tang ,  Jianchao Yang ,  Jia Li

IPC: G06K9/62 ,  G06T11/60 ,  G06T7/00

Abstract: A dense captioning system and method is provided for processing an image to produce a feature map of the image, analyzing the feature map to generate proposed bounding boxes for a plurality of visual concepts within the image, analyzing the feature map to determine a plurality of region features of the image, and analyzing the feature map to determine a context feature for the image. For each region feature of the plurality of region features of the image, the dense captioning system further provides for analyzing the region feature to determine a detection score for the region feature, calculating a caption for a bounding box for a visual concept in the image using the region feature and the context feature, and localizing the visual concept by adjusting the bounding box around the visual concept based on the caption to generate an adjusted bounding box for the visual concept.

公开(公告)号：US12136026B2

公开(公告)日：2024-11-05

申请号：US18222649

申请日：2023-07-17

Applicant: Snap Inc.

Inventor： Yingzhen Yang ,  Jianchao Yang ,  Ning Xu

IPC: G06K9/00 ,  G06N3/04 ,  G06T5/20 ,  G06T7/10

Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

公开(公告)号：US20240046072A1

公开(公告)日：2024-02-08

申请号：US18489730

申请日：2023-10-18

Applicant: Snap Inc.

Inventor： Linjie Yang ,  Jianchao Yang ,  Xuehan Xiong ,  Yanran Wang

IPC: G06N3/045 ,  G06N3/08 ,  G06T7/10 ,  G06F17/18 ,  H04L51/52

CPC classification number: G06N3/045 ,  G06N3/08 ,  G06T7/10 ,  G06F17/18 ,  H04L51/52

Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.

公开(公告)号：US11887357B2

公开(公告)日：2024-01-30

申请号：US17547548

申请日：2021-12-10

Applicant: Snap Inc.

Inventor： Jianchao Yang ,  Ning Xu ,  Jian Ren

IPC: G06K9/62 ,  G06V10/774 ,  G06F18/214 ,  G06F18/24 ,  G06F18/21 ,  G06F18/25 ,  G06V30/19 ,  G06V10/776 ,  G06V10/82 ,  H04L51/212

CPC classification number: G06V10/7753 ,  G06F18/217 ,  G06F18/2155 ,  G06F18/24 ,  G06F18/254 ,  G06V10/776 ,  G06V10/82 ,  G06V30/1916 ,  G06V30/19173 ,  H04L51/212

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：US20230359859A1

公开(公告)日：2023-11-09

申请号：US18222649

申请日：2023-07-17

Applicant: Snap Inc.

Inventor： Yingzhen Yang ,  Jianchao Yang ,  Ning Xu

IPC: G06N3/04 ,  G06T7/10 ,  G06T5/20

CPC classification number: G06N3/04 ,  G06T7/10 ,  G06T5/20

Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.