中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5279 records (took 0.056 seconds)

    EMBEDDINGS REPRESENTING VISUAL AUGMENTATIONS
    133.
    发明公开
    EMBEDDINGS REPRESENTING VISUAL AUGMENTATIONS 审中-公开

    公开(公告)号：US20240355063A1

    公开(公告)日：2024-10-24

    申请号：US18304078

    申请日：2023-04-20

    Applicant: Snap Inc.

    Inventor： Zhenpeng Zhou ,  Patrick Poirson ,  Maksim Gusarov ,  Chen Wang ,  Oleg Tovstyi

    IPC: G06T19/00 ,  G06T1/00 ,  G06V10/74 ,  H04N5/262

    CPC classification number: G06T19/006 ,  G06T1/0021 ,  G06V10/761 ,  H04N5/2621

    Abstract: An input video item that includes a target visual augmentation is accessed. A machine learning model uses the input video item to generate an embedding. The embedding may comprise a vector representation of a visual effect of the target visual augmentation. The machine learning model is trained, in an unsupervised training phase, to minimize loss between training video representations generated within each of a plurality of training sets. Each training set comprises a plurality of different training video items that each include a predefined visual augmentation. Based on the generation of the embedding of the input video item, the target visual augmentation is mapped to an augmentation identifier.

    RECOMMENDING CONTENT USING MULTIMODAL MEMORY EMBEDDINGS
    135.
    发明公开
    RECOMMENDING CONTENT USING MULTIMODAL MEMORY EMBEDDINGS 审中-公开

    公开(公告)号：US20240354641A1

    公开(公告)日：2024-10-24

    申请号：US18613645

    申请日：2024-03-22

    Applicant: Snap Inc.

    Inventor： William Miles Miller ,  Aleksei Stoliar

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: Described is a system for gathering interaction data from use of one or more interaction functions by a first user, wherein the interaction data includes data in different modalities and generating a multimodal memory for the interaction data by applying the interaction data to a first machine learning model. The system also identifies a prompt for the first user and processes a combination of data associated with the prompt and the multimodal memory using a second machine learning model to generate recommended content for the first user. The system then proceeds to apply the recommended content to a first interaction client of the first user.

    PRESENTING PARTICIPANT REACTIONS WITHIN A VIRTUAL WORKING ENVIRONMENT
    136.
    发明公开
    PRESENTING PARTICIPANT REACTIONS WITHIN A VIRTUAL WORKING ENVIRONMENT 审中-公开

    公开(公告)号：US20240353969A1

    公开(公告)日：2024-10-24

    申请号：US18758150

    申请日：2024-06-28

    Applicant: Snap Inc.

    Inventor： Brandon Francis ,  Andrew Cheng-min Lin ,  Walton Lin

    IPC: G06F3/04815 ,  G06F3/04817 ,  G06Q10/10 ,  G06T19/00

    CPC classification number: G06F3/04815 ,  G06F3/04817 ,  G06Q10/10 ,  G06T19/003

    Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for presenting participant reactions within a virtual working environment. The program and method provide a configuration interface for configuring a virtual working environment for plural participants, the configuration interface for specifying groups of participants, each group comprising respective participants selected from among the plural participants; receive first user input, provided via the configuration interface, specifying a first group of participants; provide, for each participant in the first group, display of a reactions interface with user-selectable buttons to indicate respective reactions for displaying to the first group; receive second user input, provided via the reactions interface, selecting one of the user-selectable buttons to indicate a reaction for displaying to the first group; and provide, for each participant in the first group, display of a reaction icon corresponding to the reaction.

    Face animation synthesis
    139.
    发明授权
    Face animation synthesis 有权

    公开(公告)号：US12125147B2

    公开(公告)日：2024-10-22

    申请号：US17663176

    申请日：2022-05-12

    Applicant: Snap Inc.

    Inventor： Pavel Savchenkov ,  Yurii Volkov ,  Jeremy Baker Voss

    IPC: G06T19/00 ,  G06N20/00 ,  G06T13/40 ,  H04L51/046

    CPC classification number: G06T19/006 ,  G06N20/00 ,  G06T13/40 ,  H04L51/046 ,  G06T2200/24

    Abstract: A methodology for training a machine learning model to generate color-neutral input face images is described. For each training face image from a training dataset that is used for training the model, the training system generates an input face image, which has the color and lighting of a randomly selected image from the set of color source images, and which has facial features and expression of a face object from the training face image. Because, during training, the machine learning model is “confused” by changing the color and lighting of a training face image to a randomly selected different color and lighting, the trained machine learning model generates a color neutral embedding representing facial features from the training face image.

    Safeguarding location visitation information
    140.
    发明授权
    Safeguarding location visitation information 有权

    公开(公告)号：US12124607B2

    公开(公告)日：2024-10-22

    申请号：US17644297

    申请日：2021-12-14

    Applicant: Snap Inc.

    Inventor： Ioannis Kotsogiannis Teftsoglou ,  Mohammad Zaheri Darkahi

    IPC: G06F21/62 ,  G06Q50/00

    CPC classification number: G06F21/6245 ,  G06Q50/01

    Abstract: Various embodiments safeguard location visitation information, such as visitation counter information, for a location or place that can be visited by one or more users of a user-based system. According to various embodiments, one or more of the techniques or mechanisms described herein can be used to safeguard user visitation information on a user-based platform: a user's allow list (or block list) that indicates which location visitation information for the user can be shown to another user on the platform; using a visitation category, such as a label, in place of a visitation count when displaying information with respect to a location; using a count of users on a user's connected-users list to determine how visitation count information for a location will be presented or displayed to the user; or adding a certain level of noise to location visitation information that is presented to a user.

Patent Agency Ranking