中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

55 records (took 0.032 seconds)

    WEAKLY SUPERVISED SEMANTIC PARSING
    11.
    发明公开
    WEAKLY SUPERVISED SEMANTIC PARSING 审中-公开

    公开(公告)号：US20230290174A1

    公开(公告)日：2023-09-14

    申请号：US18318556

    申请日：2023-05-16

    Applicant: Snap Inc.

    Inventor： Yuncheng Li ,  Linjie Yang ,  Ning Zhang ,  Zhengyuan Yang

    IPC: G06V40/10 ,  G06F17/15 ,  G06N3/04 ,  G06T7/136

    CPC classification number: G06V40/107 ,  G06F17/15 ,  G06N3/04 ,  G06T7/136

    Abstract: Segmentation of an image into individual body parts is performed based on a trained model. The model is trained with a plurality of training images, each training image representing a corresponding training figure. The model is also trained with a corresponding plurality of segmentations of the training figures. Each segmentation is generated by positioning body parts between defined positions of joints of the represented figure. The body parts are represented by body part templates obtained from a template library, with the templates defining characteristics of body parts represented by the templates.

    Encoding and decoding a stylized custom graphic
    12.
    发明授权
    Encoding and decoding a stylized custom graphic 有权

    公开(公告)号：US11024058B2

    公开(公告)日：2021-06-01

    申请号：US16846949

    申请日：2020-04-13

    Applicant: Snap Inc.

    Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

    IPC: G06T9/00 ,  H04L12/58 ,  G06N3/04

    Abstract: Disclosed are methods for encoding information in a graphic image. The information may be encoded so as to have a visual appearance that adopts a particular style, so that the encoded information is visually pleasing in the environment in which it is displayed. An encoder and decoder are trained during an integrated training process, where the encoder is tuned to minimize a loss when its encoded images are decoded. Similarly, the decoder is also trained to minimize loss when decoding the encoded images. Both the encoder and decoder may utilize a convolutional neural network in some aspects to analyze data and/or images. Once data is encoded, a style from a sample image is transferred to the encoded data. When decoding, the decoder may largely ignore the style aspects of the encoded data and decode based on a content portion of the data.

    ENCODING AND DECODING A STYLIZED CUSTOM GRAPHIC
    14.
    发明申请
    ENCODING AND DECODING A STYLIZED CUSTOM GRAPHIC 审中-公开

    公开(公告)号：US20200242812A1

    公开(公告)日：2020-07-30

    申请号：US16846949

    申请日：2020-04-13

    Applicant: Snap Inc.

    Inventor： Drake Austin Rehfeld ,  Rahul Bhupendra Sheth ,  Ning Zhang

    IPC: G06T9/00 ,  H04L12/58 ,  G06N3/04

    Abstract: Disclosed are methods for encoding information in a graphic image. The information may be encoded so as to have a visual appearance that adopts a particular style, so that the encoded information is visually pleasing in the environment in which it is displayed. An encoder and decoder are trained during an integrated training process, where the encoder is tuned to minimize a loss when its encoded images are decoded. Similarly, the decoder is also trained to minimize loss when decoding the encoded images. Both the encoder and decoder may utilize a convolutional neural network in some aspects to analyze data and/or images. Once data is encoded, a style from a sample image is transferred to the encoded data. When decoding, the decoder may largely ignore the style aspects of the encoded data and decode based on a content portion of the data.

    Feedback adversarial learning
    16.
    发明授权
    Feedback adversarial learning 有权

    公开(公告)号：US11604963B2

    公开(公告)日：2023-03-14

    申请号：US17808274

    申请日：2022-06-22

    Applicant: Snap Inc.

    Inventor： Jacob Minyoung Huh ,  Shao-Hua Sun ,  Ning Zhang

    IPC: G06N3/04 ,  G06V30/194 ,  G06N3/08

    Abstract: Disclosed is a feedback adversarial learning framework, a recurrent framework for generative adversarial networks that can be widely adapted to not only stabilize training but also generate higher quality images. In some aspects, a discriminator's spatial outputs are distilled to improve generation quality. The disclosed embodiments model the discriminator into the generator, and the generator learns from its mistakes over time. In some aspects, a discriminator architecture encourages the model to be locally and globally consistent.

    EFFICIENT HUMAN POSE TRACKING IN VIDEOS
    17.
    发明申请
    EFFICIENT HUMAN POSE TRACKING IN VIDEOS 有权

    公开(公告)号：US20230010480A1

    公开(公告)日：2023-01-12

    申请号：US17660462

    申请日：2022-04-25

    Applicant: Snap, Inc.

    Inventor： Yuncheng Li ,  Linjie Luo ,  Xuecheng Nie ,  Ning Zhang

    IPC: G06T7/246 ,  G06T7/73 ,  G06V20/40

    Abstract: Systems, devices, media and methods are presented for a human pose tracking framework. The human pose tracking framework may identify a message with video frames, generate, using a composite convolutional neural network, joint data representing joint locations of a human depicted in the video frames, the generating of the joint data by the composite convolutional neural network done by a deep convolutional neural network operating on one portion of the video frames, a shallow convolutional neural network operating on a another portion of the video frames, and tracking the joint locations using a one-shot learner neural network that is trained to track the joint locations based on a concatenation of feature maps and a convolutional pose machine. The human pose tracking framework may store, the joint locations, and cause presentation of a rendition of the joint locations on a user interface of a client device.

    Systems and methods for digital image editing
    18.
    发明授权
    Systems and methods for digital image editing 有权

    公开(公告)号：US11386261B2

    公开(公告)日：2022-07-12

    申请号：US16946948

    申请日：2020-07-13

    Applicant: Snap Inc.

    Inventor： Rahul Sheth ,  Kevin Dechau Tang ,  Ning Zhang

    IPC: G06F40/169 ,  G06F3/0482 ,  G06F3/04842 ,  G06T11/60 ,  H04W4/80

    Abstract: A system according to various exemplary embodiments includes a processor and a user interface, communication module, and memory coupled to the processor. The memory stores instructions that, when executed by the processor, cause the system to: retrieve a digital image from a server using the communication module; present the digital image on a display of the user interface; receive edits to the digital image via the user interface; generate, based on the edits, a modified digital image, wherein generating the modified digital image includes transforming a format of the digital image to include a field containing an identifier associated with the modified digital image; and transmit the modified digital image to the server using the communication module.

    Weakly supervised semantic parsing
    19.
    发明授权
    Weakly supervised semantic parsing 有权

    公开(公告)号：US11182603B1

    公开(公告)日：2021-11-23

    申请号：US16450376

    申请日：2019-06-24

    Applicant: Snap Inc.

    Inventor： Yuncheng Li ,  Linjie Yang ,  Ning Zhang ,  Zhengyuan Yang

    IPC: G06K9/00 ,  G06F17/15 ,  G06N3/04 ,  G06T7/136

    Abstract: Segmentation of an image into individual body parts is performed based on a trained model. The model is trained with a plurality of training images, each training image representing a corresponding training figure. The model is also trained with a corresponding plurality of segmentations of the training figures. Each segmentation is generated by positioning body parts between defined positions of joints of the represented figure. The body parts are represented by body part templates obtained from a template library, with the templates defining characteristics of body parts represented by the templates.

Patent Agency Ranking