中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

10 records (took 0.014 seconds)

    STOCHASTIC TRAJECTORY PREDICTION USING SOCIAL GRAPH NETWORKS
    2.
    发明申请
    STOCHASTIC TRAJECTORY PREDICTION USING SOCIAL GRAPH NETWORKS 有权

    公开(公告)号：US20220292867A1

    公开(公告)日：2022-09-15

    申请号：US17635792

    申请日：2019-09-16

    Applicant: INTEL CORPORATION

    Inventor： Lidan ZHANG ,  Qi She ,  Ping Guo

    IPC: G06V40/10 ,  G06N3/04 ,  G06T7/73 ,  G06T7/12 ,  G06T7/246 ,  G06V10/82

    Abstract: Systems, methods, apparatuses, and computer program products to provide stochastic trajectory prediction using social graph networks. An operation may comprise determining a first feature vector describing destination features of a first person depicted in an image, generating a directed graph for the image based on all people depicted in the image, determining, for the first person, a second feature vector based on the directed graph and the destination features, sampling a value of a latent variable from a learned prior distribution, the latent variable to correspond to a first time interval, and generating, based on the sampled value and the feature vectors by a hierarchical long short-term memory (LSTM) executing on a processor, an output vector comprising a direction of movement and a speed of the direction of movement of the first person at a second time interval, subsequent to the first time interval.

    SPECTRAL NONLOCAL BLOCK FOR A NEURAL NETWORK AND METHODS, APPARATUS, AND ARTICLES OF MANUFACTURE TO CONTROL THE SAME
    3.
    发明申请
    SPECTRAL NONLOCAL BLOCK FOR A NEURAL NETWORK AND METHODS, APPARATUS, AND ARTICLES OF MANUFACTURE TO CONTROL THE SAME 有权

    公开(公告)号：US20220138555A1

    公开(公告)日：2022-05-05

    申请号：US17088328

    申请日：2020-11-03

    Applicant: Intel Corporation

    Inventor： Lidan Zhang ,  Lei Zhu ,  Qi She ,  Ping Guo

    IPC: G06N3/08

    Abstract: Examples methods, apparatus, and articles of manufacture corresponding to a spectral nonlocal block have been disclosed. An example apparatus includes a first convolution filter to perform a first convolution using input features and first weighted kernels to generate first weighted input features, the input features corresponding to data of a neural network; an affinity matrix generator to: perform a second convolution using the input features and second weighted kernels to generate second weighted input features; perform a third convolution using the input features and third weighted kernels to generate third weighted input features; and generate an affinity matrix based on the second and third weighted input features; a second convolution filter to perform a fourth convolution using the first weighted input features and fourth weighted kernels to generate fourth weighted input features; and a accumulator to transmit output features corresponding to a spectral nonlocal operator.

    ONLINE LEARNING METHOD AND SYSTEM FOR ACTION RECOGNITION
    5.
    发明公开
    ONLINE LEARNING METHOD AND SYSTEM FOR ACTION RECOGNITION 审中-公开

    公开(公告)号：US20230410487A1

    公开(公告)日：2023-12-21

    申请号：US18250498

    申请日：2020-11-30

    Applicant: Intel Corporation

    Inventor： Lidan Zhang ,  Qi She ,  Ping Guo ,  Yimin Zhang

    IPC: G06V10/778 ,  G06V20/40 ,  G06V10/82 ,  G06V40/20

    CPC classification number: G06V10/778 ,  G06V20/41 ,  G06V20/44 ,  G06V10/82 ,  G06V40/20 ,  G06V20/46

    Abstract: Performing online learning for a model to detect unseen actions in an action recognition system is disclosed. The method includes extracting semantic features in a semantic domain from semantic action labels, transforming the semantic features from the semantic domain into mixed features in a mixed domain, and storing the mixed features in a feature database. The method further includes extracting visual features in a visual domain from a video stream and determining if the visual features indicate an unseen action in the video stream. If no unseen action is determined, applying an offline classification model to the visual features to identify seen actions, assigning identifiers to the identified seen actions, transforming the visual features from the visual domain into mixed features in the mixed domain, and storing the mixed features and seen action identifiers in the feature database. If an unseen action is determined, transforming the visual features from the visual domain into mixed features in the mixed domain, applying a continual learner model to mixed features from the feature database to identify unseen actions in the video stream, assigning identifiers to the identified unseen actions, and storing the unseen action identifiers in the feature database.

    Methods and apparatus to match images using semantic features
    6.
    发明授权
    Methods and apparatus to match images using semantic features 有权

    公开(公告)号：US11341736B2

    公开(公告)日：2022-05-24

    申请号：US16768559

    申请日：2018-03-01

    Applicant: Intel Corporation

    Inventor： Yimin Zhang ,  Haibing Ren ,  Wei Hu ,  Ping Guo

    IPC: G06V10/75 ,  G06K9/62 ,  G06V10/20 ,  G06V10/46

    Abstract: Methods and apparatus to match images using semantic features are disclosed. An example apparatus includes a semantic labeler to determine a semantic label for each of a first set of points of a first image and each of a second set of points of a second image; a binary robust independent element features (BRIEF) determiner to determine semantic BRIEF descriptors for a first subset of the first set of points and a second subset of the second set of points based on the semantic labels; and a point matcher to match first points of the first subset of points to second points of the second subset of points based on the semantic BRIEF descriptors.

    TRAINING ONE-SHOT INSTANCE SEGMENTERS USING SYNTHESIZED IMAGES
    7.
    发明申请
    TRAINING ONE-SHOT INSTANCE SEGMENTERS USING SYNTHESIZED IMAGES 有权

    公开(公告)号：US20210248418A1

    公开(公告)日：2021-08-12

    申请号：US16972931

    申请日：2018-08-29

    Applicant: Intel Corporation

    Inventor： Ping Guo ,  Wei Hu ,  Yimin Zhang ,  Renjing Pei

    IPC: G06K9/62 ,  G06T5/50 ,  G06T7/194 ,  G06T11/40

    Abstract: An example apparatus for generating synthesized images includes a receiver to receive a frame, a mask and external images. The apparatus also includes a foreground augmenter to generate augmented foregrounds in the frame based on the mask. The apparatus includes a background augmenter to generate augmented backgrounds based on the frame, the mask, and the external images. The apparatus also further includes an image synthesizer to generate a synthesized image based on the generated augmented foregrounds and the augmented backgrounds.

    Trajectory prediction using directed graph and destination features
    8.
    发明授权
    Trajectory prediction using directed graph and destination features 有权

    公开(公告)号：US12198460B2

    公开(公告)日：2025-01-14

    申请号：US17635792

    申请日：2019-09-16

    Applicant: INTEL CORPORATION

    Inventor： Lidan Zhang ,  Qi She ,  Ping Guo

    IPC: G06V40/10 ,  G06N3/044 ,  G06N3/048 ,  G06T7/12 ,  G06T7/246 ,  G06T7/73 ,  G06V10/82 ,  G06Q50/00

    Abstract: Systems, methods, apparatuses, and computer program products to provide stochastic trajectory prediction using social graph networks. An operation may comprise determining a first feature vector describing destination features of a first person depicted in an image, generating a directed graph for the image based on all people depicted in the image, determining, for the first person, a second feature vector based on the directed graph and the destination features, sampling a value of a latent variable from a learned prior distribution, the latent variable to correspond to a first time interval, and generating, based on the sampled value and the feature vectors by a hierarchical long short-term memory (LSTM) executing on a processor, an output vector comprising a direction of movement and a speed of the direction of movement of the first person at a second time interval, subsequent to the first time interval.

Patent Agency Ranking